CVPR2018-papers

1. Transductive Unbiased Embedding for Zero-Shot Learning
2. Frustum PointNets for 3D Object Detection from RGB-D Data
3. Enhancing the Spatial Resolution of Stereo Images using a Parallax Prior
4. DiverseNet: When One Right Answer Is Not Enough
5. SSNet: Scale Selection Network for Online 3D Action Prediction
6. Very Large-Scale Global SfM by Distributed Motion Averaging
7. PAD-Net: Multi-Tasks Guided Prediciton-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing
8. Dynamic Feature Learning for Partial Face Recognition
9. Context-aware Deep Feature Compression for High-speed Visual Tracking
10. Between-class Learning for Image Classification
11. DVQA: Understanding Data Visualizations via Question Answering
12. Human Appearance Transfer
13. Learning to Segment Every Thing
14. Globally Optimal Inlier Set Maximization for Atlanta Frame Estimation
15. Re-weighted Adversarial Adaptation Network for Unsupervised Domain Adaptation
16. Learning to Compare: Relation Network for Few-Shot Learning
17. Arbitrary Style Transfer with Deep Feature Reshuffle
18. Dynamic Scene Deblurring Using Spatially Variant Recurrent Neural Networks
19. Robust Video Content Alignment and Compensation for Rain Removal in a CNN Framework
20. Guided Proofreading of Automatic Segmentations for Connectomics
21. Deep PhaseNet for Video Frame Interpolation
22. Context-aware Synthesis for Video Frame Interpolation
23. Lean Multiclass Crowdsourcing
24. Unsupervised Deep Generative Adversarial Hashing Network
25. R-FCN-3000 at 30fps: Decoupling Detection and Classification
26. Tips and Tricks for Visual Question Answering: Learnings from the 2017 Challenge
27. Gated Fusion Network for Single Image Dehazing
28. Learning a Complete Image Indexing Pipeline
29. Mask-guided Contrastive Attention Model for Person Re-Identification
30. Learning Pose Specific Representations by Predicting different Views
31. Deep Mutual Learning
32. Improving Occlusion and Hard Negative Handling for Single-Stage Object Detectors
33. Defense against adversarial attacks using guided denoiser
34. Learning Attentions: Residual Attentional Siamese Network for High Performance Online Visual Tracking
35. Structure Inference Net: Object Detection Using Scene-Level Context and Instance-Level Relationships
36. Decorrelated Batch Normalization
37. On the Duality Between Retinex and Image Dehazing
38. CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes
39. The Perception-Distortion Tradeoff
40. Image Blind Denoising With Generative Adversarial Network Based Noise Modeling
41. Distort-and-Recover: Color Enhancement using Deep Reinforcement Learning
42. A Low Power, High Throughput, Fully Event-Based Stereo System
43. Regularizing RNNs for Caption Generation by Reconstructing The Past with The Present
44. End-to-end Flow Correlation Tracking with Spatial-temporal Attention
45. Exploiting Transitivity for Learning Person Re-identification Models on a Budget
46. Imagination-IQA: No-reference Image Quality Assessment via Adversarial Learning
47. Egocentric Activity Recognition on a Budget
48. Person Transfer GAN to Bridge Domain Gap for Person Re-Identification
49. Duplex Generative Adversarial Network for Unsupervised Domain Adaptation
50. Fine-grained Video Captioning for Sports Narrative
51. High Performance Visual Tracking with Siamese Region Proposal Network
52. Adversarially Occluded Samples for Person Re-identification
53. MatNet: Modular Attention Network for Referring Expression Comprehension
54. Low-Latency Video Semantic Segmentation
55. MapNet: An Allocentric Spatial Memory for Mapping Environments
56. Fast End-to-End Trainable Guided Filter
57. Partial Transfer Learning with Selective Adversarial Networks
58. Reconstruction Network for Video Captioning
59. Improving Landmark Localization with Semi-Supervised Learning
60. Unsupervised Person Image Synthesis in Arbitrary Poses
61. Efficient Large-scale Approximate Nearest Neighbor Search on OpenCL FPGA
62. Deep End-to-End Time-of-Flight Imaging
63. Augmenting Crowd-Sourced 3D Reconstructions using Semantic Detections
64. DocUNet: Document Image Unwarping via A Stacked U-Net
65. Geometry Aware Optimization for Deep Learning: The Good Practice
66. Learning to Detect Features in Texture Images
67. LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation
68. Spatially-Adaptive Filter Units for Deep Neural Networks
69. Revisiting Video Saliency: A Large-scale Benchmark and a New Model
70. Real-World Repetition Estimation by Div, Grad and Curl
71. Learning Visual Knowledge Memory Networks for Visual Question Answering
72. Attention-aware Compositional Network for Person Re-Identification
73. Sim2Real View Invariant Visual Servoing by Recurrent Control
74. Time-resolved Light Transport Decomposition for Thermal Photometric Stereo
75. Trapping Light for Time of Flight
76. A Unifying Contrast Maximization Framework for Event Cameras, with Applications to Motion, Depth, and Optical Flow Estimation
77. Global versus Localized Generative Adversarial Nets
78. Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions
79. Learning a Toolchain for Image Restoration
80. CNN based Learning using Reflection and Retinex Models for Intrinsic Image Decomposition
81. Feature Quantization for Defending Against Distortion of Images
82. A Minimalist Approach to Type-Agnostic Detection of Quadrics in Point Clouds
83. Quantization of Fully Convolutional Networks for Accurate Biomedical Image Segmentation
84. Aperture Supervision for Monocular Depth Estimation
85. Divide and Conquer for Full-Resolution Light Field Deblurring
86. Multi-shot Pedestrian Re-identification via Sequential Decision Making
87. Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features
88. Depth-Aware Stereo Video Retargeting
89. Multistage Adversarial Losses for Pose-Based Human Image Synthesis
90. Multi-Content GAN for Few-Shot Font Style Transfer
91. Multi-Cue Correlation Filters for Robust Visual Tracking
92. A Causal And-Or Graph Model for Visibility Fluent Reasoning in Tracking Interacting Objects
93. Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
94. Improving Color Reproduction Accuracy in the Camera Imaging Pipeline
95. Net2Vec: Quantifying and Explaining how Concepts are Encoded by Filters in Deep Neural Networks
96. Sketch-a-Classifier: Sketch-based Photo Classifier Generation
97. Learning Time/Memory-Efficient Deep Architectures with Budgeted Super Networks
98. TOM-Net: Learning Transparent Object Matting from a Single Image
99. Estimation of Camera Locations in Highly Corrupted Scenarios: All About the Base, No Shape Trouble
100. Direction-aware Spatial Context Features for Shadow Detection
101. Neural Motifs: Scene Graph Parsing with Global Context
102. Object Referring in Videos with Language and Human Gaze
103. Learning Transferable Architectures for Scalable Image Recognition
104. View Extrapolation of Human Body from a Single Image
105. Probabilistic Plant Modeling via Multi-View Image-to-Image Translation
106. Learning a Discriminative Prior for Blind Image Deblurring
107. Optimal Structured Light a la Carte
108. Revisiting Deep Intrinsic Image Decompositions
109. GAGAN: Geometry Aware Generative Adverserial Networks
110. Learning Multi-grid Generative ConvNets by Minimal Contrastive Divergence
111. Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root Normalization
112. Diversity Regularized Spatiotemporal Attention for Video-based Person Re-identification
113. Variational Autoencoders for Deforming 3D Mesh Models
114. Rotation Averaging and Strong Duality
115. 3D Hand Pose Estimation: From Current Achievements to Future Goals
116. Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions
117. A Robust Generative Framework for Generalized Zero-Shot Learning
118. Two can play this Game: Visual Dialog with Discriminative Visual Question Generation and Visual Question Answering
119. Rotation-sensitive Regression for Oriented Scene Text Detection
120. Adversarial Feature Augmentation for Unsupervised Domain Adaptation
121. Deep Regression Forests for Age Estimation
122. FOTS: Fast Oriented Text Spotting with a Unified Network
123. SoS-RSC: A Sum-of-Squares Polynomial Approach to Robustifying Subspace Clustering Algorithms
124. Efficient Subpixel Refinement with Symbolic Linear Predictors
125. Self-Supervised Feature Learning by Learning to Spot Artifacts
126. PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation
127. Scale-recurrent Network for Deep Image Deblurring
128. Multi-Cell Classification by Convolutional Dictionary Learning with Class Proportion Priors
129. Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks
130. On the convergence of PatchMatch and its variants
131. Clinical Skin Lesion Diagnosis using Representations Inspired by Dermatologist Criteria
132. PoTion: Pose MoTion Representation for Action Recognition
133. Zigzag Learning for Weakly Supervised Object Detection
134. VITAL: VIsual Tracking via Adversarial Learning
135. Crowd Counting with Deep Negative Correlation Learning
136. Multi-Label Zero-Shot Learning with Structured Knowledge Graphs
137. Learning a Discriminative Filter Bank within a CNN for Fine-grained Recognition
138. A Closer Look at Spatiotemporal Convolutions for Action Recognition
139. Dual Attention Matching Network for Context-Aware Feature Sequence based Person Re-Identification
140. End-to-End Deep Kronecker-Product Matching for Person Re-identification
141. Consensus Maximization for Semantic Region Correspondences
142. SBNet: Sparse Block’s Network for Fast Inference
143. Action Sets: Weakly Supervised Action Segmentation without Ordering Constraints
144. Group Consistent Similarity Learning via Deep CRFs for Person Re-Identification
145. Now You Shake Me: Towards Automatic 4D Cinema
146. Defocus Blur Detection via Multi-Stream Bottom-Top-Bottom Fully Convolutional Network
147. Interpret Neural Networks by Identifying Critical Data Routing Paths
148. Deep Reinforcement Learning of Region Proposal Networks for Object Detection
149. Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
150. Finding It": Weakly-Supervised Reference-Aware Visual Grounding in Instructional Video"
151. Semantic Visual Localization
152. DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks
153. Composing Two Objects of Interest for Flying Camera Photography
154. Kernelized Subspace Pooling for Deep Local Descriptors
155. Learning to Generate Time-Lapse Videos Using Multi-Stage Dynamic Generative Adversarial Networks
156. Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks
157. Deep Lesion Graph in the Wild: Relationship Learning and Organization of Significant Radiology Image Findings in a Diverse Large-scale Lesion Database
158. An Efficient and Provable Approach for Mixture Proportion Estimation Using Linear Independence Assumption
159. Eliminating Background-bias for Robust Person Re-identification
160. Geometry-Aware Network for Non-Rigid Shape Prediction from a Single View
161. High-order tensor regularization with application to attribute ranking
162. Taskonomy: Disentangling Task Transfer Learning
163. BlockDrop: Dynamic Inference Paths in Residual Networks
164. Attend and Interact: Higher-Order Object Interactions for Video Understanding
165. Bilateral Ordinal Relevance Multi-instance Regression for Facial Action Unit Intensity Estimation
166. CarFusion: Combining Point Tracking and Part Detection for Dynamic 3D Reconstruction of Vehicles
167. Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-Identification
168. Large Scale Fine-Grained Categorization and the Effectiveness of Domain-Specific Transfer Learning
169. BPGrad: Towards Global Optimality in Deep Learning via Branch and Pruning
170. Improved Human Pose Estimation through Adversarial Data Augmentation
171. ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
172. SINT++: Robust Visual Tracking via Adversarial Hard Positive Generation
173. Structured Uncertainty Prediction Networks
174. Geometry-Guided CNN for Self-supervised Video Representation learning
175. Low-Shot Recognition with Imprinted Weights
176. Self-supervised Learning of Geometrically Stable Features Through Probabilistic Introspection
177. Disentangling Structure and Aesthetics for Content-aware Image Completion
178. A Volumetric Descriptive Network for 3D Object Synthesis
179. Interpretable Convolutional Neural Networks
180. Single Image Dehazing via Conditional Generative Adversarial Network
181. Neural Inverse Kinematics for Unsupervised Motion Retargetting
182. Environment Upgrade Reinforcement Learning for Non-differentiable Multi-stage Pipelines
183. Teaching Categories to Human Learners with Visual Explanations
184. Facelet-Bank for Fast Portrait Manipulation
185. Convolutional Sequence to Sequence Model for Human Dynamics
186. Human Semantic Parsing for Person Re-identification
187. Latent RANSAC
188. LiDAR-Video Driving Dataset: Learning Driving Policies Effectively
189. Actor and Observer: Joint Modeling of First and Third-Person Videos
190. Controllable Video Generation with Sparse Trajectories
191. What have we learned from deep representations for action recognition?
192. Bidirectional Attentive Fusion with Context Gating for Dense Video Captioning
193. Language-Based Image Editing with Recurrent attentive Models
194. Graph-Cut RANSAC
195. Optimizing Filter Size in Convolutional Neural Networks for Facial Action Unit Recognition
196. Memory Based Online Learning of Deep Representations from Video Streams
197. Deep Layer Aggregation
198. Learning Convolutional Networks for Content-weighted Image Compression
199. Self-supervised Multi-level Face Model Learning for Monocular Reconstruction at over 250Hz
200. Efficient, sparse representation of manifold distance matrices for classical scaling
201. Visual to Sound: Generating Natural Sound for Videos in the Wild
202. A Prior-Less Method for Multi-Face Tracking in Unconstrained Videos
203. Real-Time Rotation-Invariant Face Detection with Progressive Calibration Networks
204. Self-calibrating polarising radiometric calibration
205. Pix3D: Dataset and Methods for 3D Object Modeling from a Single Image
206. Learning to Promote Saliency Detectors
207. Pose Transferrable Person Re-Identification
208. Hashing as Tie-Aware Learning to Rank
209. Baseline Desensitizing In Translation Averaging
210. Conditional Image-to-Image Translation
211. Blind Predicting Similar Quality Map for Image Quality Assessment
212. Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?
213. CNN Driven Sparse Multi-Level B-spline Image Registration
214. Through-Wall Human Pose Estimation Using Radio Signals
215. xUnit: Learning a Spatial Activation Function for Efficient Image Restoration
216. CLIP-Q: Deep Network Compression Learning by In-Parallel Pruning-Quantization
217. FoldingNet: Interpretable Unsupervised Learning on 3D Point Clouds
218. Weakly Supervised Coupled Networks for Visual Sentiment Analysis
219. Ring loss: Convex Feature Normalization for Face Recognition
220. Fast Spectral Ranking for Similarity Search
221. PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning
222. AMNet: Memorability Estimation with Attention
223. Webly Supervised Learning Meets Zero-shot Learning: A Hybrid Approach for Fine-grained Classification
224. End-to-End Learning of Motion Representation for Video Understanding
225. Smooth Neighbors on Teacher Graphs for Semi-supervised Learning
226. SeedNet : Automatic Seed Generation with Deep Reinforcement Learning for Robust Interactive Segmentation
227. Deep Spatio-Temporal Random Fields for Efficient Video Segmentation
228. Perturbative Neural Networks: Rethinking Convolution in CNNs
229. SYQ: Learning Symmetric Quantization For Efficient Deep Neural Networks
230. Neural 3D Mesh Renderer
231. Deep Parametric Continuous Convolutional Neural Networks
232. Visual Question Reasoning on General Dependency Tree
233. Non-local Neural Networks
234. Light field intrinsics with a deep encoder-decoder network
235. Feature Space Transfer for Data Augmentation
236. Motion Segmentation by Exploiting Complementary Geometric Models
237. Context Contrasted Feature and Gated Multi-scale Aggregation for Scene Segmentation
238. Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation
239. Towards a Mathematical Understanding of the Difficulty in Learning with Feedforward Neural Networks
240. Few-Shot Image Recognition by Predicting Parameters from Activations
241. Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion Compensation
242. CLEAR: Cumulative LEARning for One-Shot One-Class Image Recognition
243. Pose-Robust Face Recognition via Deep Residual Equivariant Mapping
244. Deep Cross-media Knowledge Transfer
245. Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs
246. A Weighted Sparse Sampling and Smoothing Frame Transition Approach for Semantic Fast-Forward First-Person Videos
247. Recurrent Slice Networks for 3D Segmentation on Point Clouds
248. Dimensionalitys Blessing: Detecting the distributions underlying images
249. Augmented Skeleton Space Transfer for Depth-based Hand Pose Estimation
250. Robust Classification with Convolutional Prototype Learning
251. DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density Estimation
252. ICE-BA: Efficient, Consistent and Efficient Bundle Adjustment for Visual-Inertial SLAM
253. Grounding Referring Expressions in Images by Variational Context
254. Pseudo-Mask Augmented Object Detection
255. Improvements to context based self-supervised learning
256. Left-Right Comparative Recurrent Model for Stereo Matching
257. Learning deep structured active contours end-to-end
258. Efficient and Deep Person Re-Identification using Multi-Level Similarity
259. Learning Intrinsic Image Decomposition from Watching the World
260. Learning to Understand Image Blur
261. Gaze Prediction in Dynamic $360^\circ$ Immersive Videos
262. Emotional Attention: A Study of Image Sentiment and Visual Attention
263. Single View Stereo Matching
264. Zero-shot Recognition via Semantic Embeddings and Knowledge Graphs
265. Video Representation Learning Using Discriminative Pooling
266. Probabilistic Joint Face-Skull Modelling for Facial Reconstruction
267. Indoor RGB-D Compass from a Single Line and Plane
268. pOSE: Pseudo Object Space Error for Initialization-Free Bundle Adjustment
269. Generative Adversarial Learning Towards Fast Weakly Supervised Detection
270. Seeing Temporal Modulation of Lights from Standard Cameras
271. Shape from Shading through Shape Evolution
272. Parallel Attention: A Unified Framework for Visual Object Discovery through Dialogs and Queries
273. Neural Style Transfer via Meta Networks
274. UV-GAN: Adversarial Facial UV Map Completion for Pose-invariant Face Recognition
275. Cascaded Pyramid Network for Multi-Person Pose Estimation
276. Detect-and-Track: Efficient Pose Estimation in Videos
277. SobolevFusion: 3D Reconstruction of Scenes Undergoing Free Non-rigid Motion
278. NAG: Network for Adversary Generation
279. Inferring Co-Attention in Social Scene Videos
280. Unsupervised Learning of Single View Depth Estimation and Visual Odometry with Deep Feature Reconstruction
281. Egocentric Basketball Motion Planning from a Single First-Person Image
282. Geometric robustness of deep networks: analysis and improvement
283. Pose-Guided Photorealistic Face Rotation
284. Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation
285. Importance Weighted Adversarial Nets for Partial Domain Adaptation
286. Towards High Performance Video Object Detection
287. SurfConv: Bridging 3D and 2D Convolution for RGBD Images
288. People, Penguins and Petri Dishes: Adapting Object Counting Models To New Visual Domains And Object Types Without Forgetting
289. Fully Convolutional Adaptation Networks for Semantic Segmentation
290. Towards Pose Invariant Face Recognition in the Wild
291. Interactive Image Segmentation with Latent Diversity
292. Label Denoising Adversarial Network (LDAN) for Inverse Lighting of Face Images
293. Detecting and Recognizing Human-Object Interactions
294. Deep Image Prior
295. 2D/3D Pose Estimation and Action Recognition using Multitask Deep Learning
296. Direct Shape Regression Networks for End-to-End Face Alignment
297. Disentangling Features in 3D Face Shapes for Joint Face Reconstruction and Recognition
298. Scale-Transferrable Object Detection
299. Learning by Asking Questions
300. 3D Pose Estimation and 3D Model Retrieval for Objects in the Wild
301. Deep Progressive Reinforcement Learning for Skeleton-based Action Recognition
302. Future Person Localization in First-Person Videos
303. 3D-RCNN: Instance-level 3D Scene Understanding via Render-and-Compare
304. Manifold Learning in Quotient Spaces
305. Image Correction via Deep Reciprocating HDR Transformation
306. Focus Manipulation Detection via Photometric Histogram Analysis
307. Density Adaptive Point Set Registration
308. Multi-view Harmonized Bilinear Network for 3D Object Recognition
309. SeGAN: Segmenting and Generating the Invisible
310. VizWiz Grand Challenge: Answering Visual Questions from Blind People
311. Sparse, Smart Contours to Represent and Edit Images
312. Generative Non-Rigid Shape Completion with Graph Convolutional Autoencoders
313. The power of ensembles for active learning in image classification
314. OLÉ: Orthogonal Low-rank Embedding, A Plug and Play Geometric Loss for Deep Learning
315. Learning Compositional Visual Concepts with Mutual Consistency
316. Adversarial Complementary Learning for Weakly Supervised Object Localization
317. Analytical Modeling of Vanishing Points and Curves in Catadioptric Cameras
318. Exploit the Unknown Gradually:~ One-Shot Video-Based Person Re-Identification by Stepwise Learning
319. Learning to Sketch with Shortcut Cycle Consistency
320. Domain Adaptive Faster R-CNN for Object Detection in the Wild
321. Attentive Generative Adversarial Network for Raindrop Removal from A Single Image
322. Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN
323. Making Convolutional Networks Recurrent for Visual Sequence Learning
324. Multi-Task Adversarial Network for Disentangled Feature Learning
325. Fight ill-posedness with ill-posedness: Single-shot variational depth super-resolution from shading
326. Zero-Shot Sketch-Image Hashing
327. Learning to Localize Sound Source in Visual Scenes
328. Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation
329. Semi-parametric Image Synthesis
330. Multi-scale Location-aware Kernel Representation for Object Detection
331. W2F: A Weakly-Supervised to Fully-Supervised Framework for Object Detection
332. Generative Modeling using the Sliced Wasserstein Distance
333. MX-LSTM: mixing tracklets and vislets to jointly forecast trajectories and head poses
334. Dynamic Video Segmentation Network
335. Learning a Discriminative Feature Network for Semantic Segmentation
336. Video Person Re-identification with Competitive Snippet-similarity Aggregation and Co-attentive Snippet Embedding
337. Curve Reconstruction via the Global Statistics of Natural Curves
338. Single-Shot Refinement Neural Network for Object Detection
339. Density-aware Single Image De-raining using a Multi-stream Dense Network
340. Learning Answer Embeddings for Visual Question Answering
341. Attention Clusters: Purely Attention Based Local Feature Integration for Video Classification
342. Translating and Segmenting Multimodal Medical Volumes with Cycle- and Shape-Consistency Generative Adversarial Network
343. Learning from the Deep: A Revised Underwater Image Formation Model
344. Mean-Variance Loss for Deep Age Estimation from a Face
345. Disentangled Person Image Generation
346. Deep Sparse Coding for Invariant Multimodal Halle Berry Neurons
347. DeepMVS: Learning Multi-View Stereopsis
348. Embodied Question Answering
349. Deflecting Adversarial Attacks with Pixel Deflection
350. Dynamic-Structured Semantic Propagation Network
351. Integrated facial landmark localization and super-resolution of real-world very low resolution faces in arbitrary poses with GANs
352. A Two-Step Disentanglement Method
353. Towards Effective Low-bitwidth Convolutional Neural Networks
354. Natural and Effective Obfuscation by Head Inpainting
355. Learning-Compression" algorithms for neural net pruning"
356. Salient Object Detection Driven by Fixation Prediction
357. Scalable Dense Non-rigid Structure-from-Motion: A Grassmannian Perspective
358. Uncalibrated Photometric Stereo under Natural Illumination
359. Learning Monocular 3D Human Pose estimation on weakly-supervised Multi-view Images
360. An Unsupervised Learning Model for Deformable Medical Image Registration
361. Learning Deep Correspondence through Prior and Posterior Feature Constancy
362. Anticipating Traffic Accidents with Adaptive Loss and Large-scale Incident DB
363. A2-RL: Aesthetics Aware Reinforcement Learning for Image Cropping
364. Learned Shape-Tailored Descriptors for Segmentation
365. One-shot Action Localization by Sequence Matching Network
366. Robust Physical-World Attacks on Deep Learning Visual Classification
367. What Makes a Video a Video: Analyzing Temporal Information in Video Understanding Models and Datasets
368. Bidirecional Retrieval Made Simple
369. Reward Learning by Instruction
370. MegaDepth: Learning Single-View Depth Prediction from Internet Photos
371. Cross-Dataset Adaptation for Visual Question Answering
372. Interpretable Video Captioning via Trajectory Structured Localization
373. MoCoGAN: Decomposing Motion and Content for Video Generation
374. Left/Right Asymmetric Layer Skippable Networks
375. Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation
376. Unsupervised Discovery of Object Landmarks as Structural Representations
377. Learning Deep Descriptors with Scale-Aware Triplet Networks
378. Robust Depth Estimation from Auto Bracketed Images
379. Aligning Infinite-Dimensional Covariance Matrices in Reproducing Kernel Hilbert Spaces for Domain Adaptation
380. Local and Global Optimization Techniques in Graph-based Clustering
381. Learning from Millions of 3D Scans for Large-scale 3D Face Recognition
382. CBMV: A Coalesced Bidirectional Matching Volume for Disparity Estimation
383. Image Collection Pop-up: 3D Reconstruction and Clustering of Rigid and Non-Rigid Categories
384. Ordinal Depth Supervision for 3D Human Pose Estimation
385. Learning to Hash by Discrepancy Minimization
386. MapNet: Geometry-Aware Learning of Maps for Camera Localization
387. Im2Struct: Recovering 3D Shape Structure from a Single RGB Image
388. A Pose-Sensitive Embedding for Person Re-Identification with Expanded Cross Neighborhood Re-Ranking
389. Analytic Expressions for Probabilistic Moments of PL-DNN with Gaussian Input
390. Cross-Domain Self-supervised Multi-task Feature Learning Using Synthetic Game Imagery
391. Coding Kendall's Shape Trajectories for 3D Action Recognition
392. Camera Pose Estimation with Unknown Principal Point
393. Learning Spatial-Aware Regressions for Visual Tracking
394. The Easy, The Medium and The Hard: Adapting Across Varied Domain Shifts
395. Detach and Adapt: Learning Cross-Domain Disentangled Deep Representation
396. A Hybrid L1-L0 Layer Decomposition Model for Tone Mapping
397. LIME: Live Intrinsic Material Estimation
398. Learning Representations for Single Cells in Microscopy Images
399. Transparency by Design: Closing the Gap Between Performance and Interpretabilty in Visual Reasoning
400. clcNet: Improving the Efficiency of Convolutional Neural Network using Channel Local Convolutions
401. Spanning Patches: Deep Patch Selection for Fast Multi-View Stereo
402. LAMV: Learning to align and match videos with kernelized temporal layers
403. Single Image Reflection Separation with Perceptual Losses
404. Structure from Recurrent Motion: From Rigidity to Recurrency
405. Customized Image Narrative Generation via Interactive Visual Question Generation and Answering
406. Relation Networks for Object Detection
407. An End-to-End TextSpotter with Explicit Alignment and Attention
408. Photometric Stereo in Participating Media Considering Shape-Dependent Forward Scatter
409. Sliced Wasserstein Distance for Learning Gaussian Mixture Models
410. Generative Adversarial Image Synthesis with Decision Tree Latent Controller
411. Disentangling 3D Pose in A Dendritic CNN for Unconstrained 2D Face Alignment
412. Learning Multi-Instance Enriched Image Representation via Non-Greedy Simultaneous L1 -Norm Minimization and Maximization
413. Separating Self-Expression and Visual Content in Hashtag Supervision
414. Residual Dense Network for Image Super-Resolution
415. Hand PointNet: 3D Hand Pose Estimation using Point Sets
416. Human-centric Indoor Scene Synthesis Using Stochastic Grammar
417. Learning Facial Action Units from Web Images with Scalable Weakly Supervised Clustering
418. Occlusion Aware Unsupervised Learning of Optical Flow
419. Domain Generalization with Adversarial Feature Learning
420. A Hierarchical Generative Model for Eye Image Synthesis and Eye Gaze Estimation
421. PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image
422. Deep Learning under Privileged Information Using Heteroscedastic Dropout
423. Frame-Recurrent Video Super-Resolution
424. Nonlocal Low-Rank Tensor Factor Analysis for Image Restoration
425. Content-Sensitive Supervoxels via Uniform Tessellations on Video Manifolds
426. Planar Shape Detection at Structural Scales
427. Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking
428. Learning to Parse Wireframes in Images of Man-Made Environments
429. Harmonious Attention Network for Person Re-Identication
430. Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks
431. Every Smile is Unique: Landmark-guided Diverse Smile Generation
432. Multi-Scale Weighted Nuclear Norm Image Restoration
433. FeaStNet: Feature-Steered Graph Convolutions for 3D Shape Analysis
434. Lightweight Probabilistic Deep Networks
435. Learning Depth from Monocular Videos using Direct Methods
436. Thoracic Disease Identification and Localization with Limited Supervision
437. SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation
438. Memory Matching Networks for One-Shot Image Recognition
439. Compressed Video Action Recognition
440. FFNet: Video Fast-Forwarding via Reinforcement Learning
441. Representing and Learning High Dimensional Data with the Optimal Transport Map from a Probabilistic Viewpoint
442. ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans
443. Fully Convolutional Attention Network for Multimodal Reasoning
444. Lions and Tigers and Bears: Capturing Non-Rigid, 3D, Articulated Shape from Images
445. Recurrent Pixel Embedding for Instance Grouping
446. Name-removed-for-review: A Multi-camera HD Dataset for Dense Unscripted Pedestrian Detection
447. SGAN: An Alternative Training of Generative Adversarial Networks
448. Learning Markov Clustering Networks for Scene Text Detection
449. Occlusion-Aware Rolling Shutter Rectification of 3D Scenes
450. Beyond Gröbner Bases: Basis Selection for Minimal Solvers
451. Improving Object Localization with Fitness NMS and Bounded IoU Loss
452. Generative Adversarial Perturbations
453. Deep Photo Enhancer: Unsupervised Learning of Image Enhancement from Photographs with GANs
454. Eye In-Painting with Exemplar Generative Adversarial Networks
455. Encoder-Decoder Alignment for Zero-Pair Image-to-Image Translation
456. Learning Structure and Strength of CNN Filters for Small Sample Size Training
457. Path Aggregation Network for Instance Segmentation
458. Learning Superpixels with Segmentation-Aware Affinity Loss
459. Data Distillation: Towards Omni-Supervised Learning
460. Deep Diffeomorphic Transformer Networks
461. CodeSLAM --- Learning a Compact, Optimisable Representation for Dense Visual SLAM
462. Glimpse Clouds: Human Activity Recognition from Unstructured Feature Points
463. Learning Latent Super-Events to Detect Multiple Activities in Videos
464. MegDet: A Large Mini-Batch Object Detector
465. Lose The Views: Limited Angle CT Reconstruction via Implicit Sinogram Completion
466. Unsupervised Domain Adaptation with Similarity-Based Classifier
467. Visual Feature Attribution using Wasserstein GANs
468. Tell Me Where To Look: Guided Attention Inference Network
469. Towards Open-Set Identity Preserving Face Synthesis
470. Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination
471. Multi-Evidence Fusion and Filtering for Weakly Supervised Object Recognition, Detection and Segmentation
472. Deep Material-aware Cross-spectral Stereo Matching
473. MakeupGAN: Makeup Transfer via Cycle-Consistent Adversarial Networks
474. M3: Multimodal Memory Modelling for Video Captioning
475. Fooling Vision and Language Models Despite Localization and Attention Mechanism
476. Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies
477. Jointly Localizing and Describing Events for Dense Video Captioning
478. The Best of Both Worlds: Combining CNNs and Geometric Constraints for Hierarchical Motion Segmentation
479. End-to-end learning of keypoint detector and descriptor for pose invariant 3D matching
480. LDMNet: Low Dimensional Manifold Regularized Neural Networks
481. 3D Human Pose Estimation in the Wild by Adversarial Learning
482. Fast Video Object Segmentation by Reference-Guided Mask Propagation
483. End-to-End Dense Video Captioning with Masked Transformer
484. Towards dense object tracking in a 2D honeybee hive
485. Appearance-and-Relation Networks for Video Classification
486. StarGAN: Unified Generative Adversarial Networks for Controllable Multi-Domain Image-to-Image Translation
487. Answer with Grounding Snippets: Focal Visual-Text Attention for Visual Question Answering
488. GANerated Hands for Real-Time 3D Hand Tracking from Monocular RGB
489. Weakly Supervised Human Body Part Parsing via Pose-Guided Knowledge Transfer
490. ClusterNet: Detecting Small Objects in Large Scenes by Exploiting Spatio-Temporal Information
491. Structured Set Matching Networks for One-Shot Part Labeling
492. Real-Time Seamless Single Shot 6D Object Pose Prediction
493. Triplet-Center Loss for Multi-View 3D Object Retrieval
494. Pixels, voxels, and views: A study of shape representations for single view 3D object shape prediction
495. Show Me a Story: Towards Coherent Neural Story Illustration
496. DeLS-3D: Deep Localization and Segmentation with a 3D Semantic Map
497. Missing Slice Recovery for Tensors Using a Low-rank Model in Embedded Space
498. 3D Semantic Segmentation with Submanifold Sparse Convolutional Networks
499. Learning Compact Recurrent Neural Networks with Block-Term Tensor Decomposition
500. Link and code: Fast indexing with graphs and compact regression codes
501. Two-Stream Convolutional Networks for Dynamic Texture Synthesis
502. Weakly Supervised Action Localization by Sparse Temporal Pooling Network
503. Viewpoint-aware Video Summarization
504. 4D Human Body Correspondences from Panoramic Depth Maps
505. Tighter Lifting-Free Convex Relaxations for Quadratic Matching Problems
506. Discovering Point Lights with Intensity Distance Fields
507. The Lovász-Softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks
508. Geometry-aware Deep Network for Single-Image Novel View Synthesis
509. Temporal Deformable Residual Networks for Action Segmentation in Videos
510. Seeing Small Faces from Robust Anchor's Perspective
511. Matryoshka Networks: Predicting 3D Geometry via Nested Shape Layers
512. On the Importance of Label Quality for Semantic Segmentation
513. AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions
514. First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations
515. Learning Deep Sketch Abstraction
516. Non-Linear Temporal Subspace Representations for Activity Recognition
517. A Biresolution Spectral framework for Product Quantization
518. Unsupervised Cross-dataset Person Re-identification by Transfer Learning of Spatio-temporal Patterns
519. Feature Super-Resolution: Make Machine See More Clearly
520. Finding Tiny Faces in the Wild with Generative Adversarial Network
521. DoubleFusion: Real-time Capture of Human Performance with Inner Body Shape from a Single Depth Sensor
522. Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective
523. Multi-view Consistency as Supervisory Signal for Learning Shape and Pose Prediction
524. Recognize Actions by Disentangling Components of Dynamics
525. Who Let The Dogs Out? Modeling Dog Behavior From Visual Data
526. Alive Caricature from 2D to 3D
527. Learning Steerable Filters for Rotation Equivariant CNNs
528. From source to target and back: Symmetric Bi-Directional Adaptive GAN
529. Monocular Relative Depth Perception with Web Stereo Data Supervision
530. Correlation Tracking via Joint Discrimination and Reliability Learning
531. Boosting Domain Adaptation by Discovering Latent Domains
532. HSA-RNN: Hierarchical Structure-Adaptive RNN for Video Summarization
533. Learning from Noisy Web Data with Category-level Supervision
534. Embodied Real-World Active Perception
535. Boosting Self-Supervised Learning via Knowledge Transfer
536. Video Captioning via Hierarchical Reinforcement Learning
537. Weakly Supervised Phrase Localization with Multi-Scale Anchored Transformer Network
538. Progressively Complementarity-aware Fusion Network for RGB-D Salient Object Detection
539. Wide Compression: Tensor Ring Nets
540. Demo2Vec: Reasoning Object Affordances from Online Videos
541. A High-Quality Denoising Dataset for Smartphone Cameras
542. Collaborative and Adversarial Network for Unsupervised domain adaptation
543. End-to-end weakly-supervised semantic alignment
544. Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
545. Feature Selective Networks for Object Detection
546. Unsupervised Learning of Depth and Egomotion from Monocular Video Using 3D Geometric Constraints
547. A Common Framework for Interactive Texture Transfer
548. Depth and Transient Imaging with Compressive SPAD Array Cameras
549. PointGrid: A Deep Network for 3D Shape Understanding
550. A Network Architecture for Point Cloud Classification via Automatic Depth Images Generation
551. Optimizing Local Feature Descriptors for Nearest Neighbor Matching
552. 4DFAB: A Large Scale 4D Database for Facial Expression Analysis and Biometric Applications
553. Zoom and Learn: Generalizing Deep Stereo Matching to Novel Domains
554. Photographic Text-to-Image Synthesis with a Hierarchically-nested Adversarial Network
555. Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal
556. What do Deep Networks Like to See?
557. On the Robustness of Semantic Segmentation Models to Adversarial Attacks
558. SketchMate: Deep Hashing for Million-Scale Human Sketch Retrieval
559. Progressive Attention Guided Recurrent Network for Salient Object Detection
560. IQA: Visual Question Answering in Interactive Environments
561. Boosting Adversarial Attacks with Momentum
562. Conditional Probability Models for Deep Image Compression
563. Cascade R-CNN: Delving into High Quality Object Detection
564. Scalable and Effective Deep CCA via Soft Decorrelation
565. Discriminability objective for training descriptive captions
566. Going from Image to Video Saliency: Augmenting Image Salience with Dynamic Attentional Push
567. Recurrent Scene Parsing with Perspective Understanding in the Loop
568. Semantic Video Segmentation by Gated Recurrent Flow Propagation
569. FlipDial: A Generative Model for Two-Way Visual Dialogue
570. Context Encoding for Semantic Segmentation
571. Deep Marching Cubes: Learning Explicit Surface Representations
572. Rethinking Feature Distribution for Loss Functions in Image Classification
573. Optical Flow Guided Feature: A Motion Representation for Video Action Recognition
574. Multimodal Explanations: Justifying Decisions and Pointing to the Evidence
575. HATS: Histograms of Averaged Time Surfaces for Robust Event-based Object Classification
576. Imagine it for me: Generative Adversarial Approach for Zero-Shot Learning from Noisy Texts
577. Co-Occurrence Template Matching
578. Defense against Universal Adversarial Perturbations
579. PPFNet: Global Context Aware Local Features for Robust 3D Point Matching
580. Dynamic Zoom-in Network for Fast Object Detection in Large Images
581. Objects as context for detecting their semantic parts
582. Spline Error Weighting for Robust Visual-Inertial Fusion
583. GeoNet: Geometric Neural Network for Joint Depth and Surface Normal Estimation
584. Where and Why Are They Looking? Jointly Inferring Human Attention and Intentions in Complex Tasks
585. Robust Facial Landmark Detection via a Fully-Convolutional Local-Global Context Network
586. Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net
587. CondenseNet: An Efficient DenseNet using Learned Group Convolutions
588. Burst Denoising with Kernel Prediction Networks
589. Leveraging Unlabeled Data for Crowd Counting by Learning to Rank
590. Recurrent Saliency Transformation Network: Incorporating Multi-Stage Visual Cues for Small Organ Segmentation
591. Classifier Learning with Prior Probabilities for Facial Action Unit Recognition
592. Active Fixation Control to Predict Saccade Sequences
593. Reflection Removal for Large-Scale 3D Point Clouds
594. Mesoscopic Facial Geometry inference Using Deep Neural Networks
595. VITON: An Image-based Virtual Try-on Network
596. Beyond the Pixel-Wise Loss for Topology-Aware Delineation
597. HashGAN: Deep Learning to Hash with Pair Conditional Wasserstein GAN
598. A Globally Optimal Solution to the Non-Minimal Relative Pose Problem
599. Learning distributions of shape trajectories from longitudinal datasets: a hierarchical model on a manifold of diffeomorphisms
600. Multispectral Image Intrinsic Decomposition via Low Rank Constraint
601. Dynamic Graph Generation Network: Generating Relational Knowledge from Diagrams
602. Alternating-Stereo VINS: Observability Analysis and Performance Evaluation
603. Im2Pano3D: Extrapolating 360 Structure and Semantics Beyond the Field of View
604. Style Aggregated Network for Facial Landmark Detection
605. VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
606. Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors
607. Deep Adversarial Subspace Clustering
608. Compassionately Conservative Balanced Cuts for Image Segmentation
609. Deformable GANs for Pose-based Human Image Generation
610. Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decoration
611. The iNaturalist Species Classification and Detection Dataset
612. Categorizing Concepts with Basic Level for Vision-to-Language
613. InverseFaceNet: Deep Monocular Inverse Face Rendering at over 250 Hz
614. Textbook Question Answering under Teacher Guidance with Memory Networks
615. Learning to Find Good Correspondences
616. Hyperparameter Optimization for Tracking with Continuous Deep Q-Learning
617. Adversarial Data Programming: Using GANs to Relax the Bottleneck of Curated Labeled Data
618. Weakly Supervised Facial Action Unit Recognition through Adversarial Training
619. Knowledge Aided Consistency for Weakly Supervised Phrase Grounding
620. Neighbors Do Help: Deeply Exploiting Local Structures of Point Clouds
621. The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
622. Dense 3D Regression for Hand Pose Estimation
623. Detail-Preserving Pooling in Deep Networks
624. Dense Decoder Shortcut Connections for Single-Pass Semantic Segmentation
625. Reinforcement Cutting-Agent Learning for Video Object Segmentation
626. SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis
627. Wrapped Gaussian Process Regression on Riemannian Manifolds
628. Document Enhancement using Visibility Detection
629. Learning Discriminative Evaluation Metrics for Image Captioning
630. GraphBit: Bitwise Interaction Mining via Deep Reinforcement Learning
631. Learning Intelligent Dialogs for Bounding Box Annotation
632. Efficient Diverse Ensemble for Discriminative Co-Tracking
633. Recovering Realistic Texture in Image Super-resolution by Spatial Feature Modulation
634. Mining on Manifolds: Metric Learning without Labels
635. Revisiting knowledge transfer for training object class detectors
636. GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose
637. Differential Attention for Visual Question Answering
638. A PID Controller Approach for Stochastic Optimization of Deep Networks
639. Bootstrapping the Performance of Webly Supervised Semantic Segmentation
640. Iterative Learning with Open-set Noisy Labels
641. A Papier-Mâché Approach to Learning 3D Surface Generation
642. Extreme 3D Face Reconstruction: Looking Past Occlusions
643. High-speed Tracking with Multi-kernel Correlation Filters
644. Attentive Fashion Grammar Network for Fashion Landmark Detection and Clothing Category Classification
645. Separating Style and Content for Generalized Style Transfer
646. Learning Dual Convolutional Neural Networks for Low-Level Vision
647. Wasserstein Introspective Neural Networks
648. Deep Semantic Face Deblurring
649. InLoc: Indoor Visual Localization with Dense Matching and View Synthesis
650. Temporal Hallucinating for Action Recognition with Few Still Images
651. Deep Texture Manifold for Ground Terrain Recognition
652. Discriminative Learning of Latent Features for Zero-Shot Recognition
653. Neural Sign Language Translation
654. GroupCap: Group-based Image Captioning with Structured Relevance and Diversity Constraints
655. Repulsion Loss: Detecting Pedestrians in a Crowd
656. Pulling Actions out of Context: Explicit Separation for Effective Combination
657. Deep Group-shuffling Random Walk for Person Re-identification
658. DenseASPP: Densely Connected Networks for Semantic Segmentation
659. A Variational U-Net for Conditional Appearance and Shape Generation
660. Universal Denoising Networks : A Novel CNN-based Network Architecture for Image Denoising
661. Automatic 3D Indoor Scene Modeling from Single Panorama
662. Five-point Fundamental Matrix Estimation for Uncalibrated Cameras
663. PU-Net: Point Cloud Upsampling Network
664. Generative Image Inpainting with Contextual Attention
665. Im2Flow: Motion Hallucination from Static Images for Action Recognition
666. Tagging Like Humans: Diverse and Distinct Image Annotation
667. TextureGAN: Controlling Deep Image Synthesis with Texture Patches
668. ISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive Sensing
669. Optimizing Video Object Detection via a Scale-Time Lattice
670. Context Embedding Networks
671. Motion-Guided Cascaded Refinement Network for Video Object Segmentation
672. RotationNet: Joint Object Categorization and Pose Estimation Using Multiviews from Unsupervised Viewpoints
673. Conditional Generative Adversarial Network for Structured Domain Adaptation
674. Large-scale Distance Metric Learning with Uncertainty
675. Hierarchical Novelty Detection for Visual Object Recognition
676. Deeper Look at Power Normalizations.
677. Disentangling Factors of Variation by Mixing Them
678. Beyond Holistic Object Recognition: Enriching Image Understanding with Part States
679. LSTM Pose Machines
680. End-to-end Recovery of Human Shape and Pose
681. Geometric Multi-Model Fitting with a Convex Relaxation Algorithm
682. Revisiting Salient Object Detection: Simultaneous Detection, Ranking, and Subitizing of Multiple Salient Objects
683. Modulated Convolutional Networks
684. High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
685. Learning Compressible 360° Video Isomers
686. Easy Identification from Better Constraints: Multi-Shot Person Re-Identification from Reference Constraints
687. TieNet: Text-Image Embedding Network for Common Thorax Disease Classification and Reporting in Chest X-rays
688. Good View Hunting: Learning Photo Composition from 1 Million View Pairs
689. Visual Relationship Learning with a Factorization-based Prior
690. Min-Entropy Latent Model for Weakly Supervised Object Detection
691. Boundary Flow: A Siamese Network that Predicts Boundary Motion without Training on Motion
692. SfSNet : Learning Shape, Reflectance and Illuminance of Faces `in the wild'
693. Facial Expression Recognition by De-expression Residue Learning
694. Empirical study of the topology and geometry of deep networks
695. Learning Globally Optimized Object Detector via Policy Gradient
696. Learning from Synthetic Data: Semantic Segmentation using Generative Adversarial Networks
697. Recurrent Residual Module for Fast Inference in Videos
698. Viewpoint-aware Attentive Multi-view Inference for Vehicle Re-identification
699. Weakly-Supervised Semantic Segmentation Network with Deep Seeded Region Growing
700. Deep Adversarial Metric Learning
701. Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision
702. Art of singular vectors and universal adversarial perturbations
703. Free supervision from video games
704. Unifying Identification and Context Learning for Person Recognition
705. DensePose: Multi-Person Dense Human Pose Estimation In The Wild
706. End-to-end Convolutional Semantic Embeddings
707. Convolutional Image Captioning
708. Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis
709. Efficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++
710. Nonlinear 3D Face Morphable Model
711. OATM: Occlusion Aware Template Matching by Consensus Set Maximization
712. Multi-Image Semantic Matching by Mining Consistent Features
713. Explicit Loss-Error-Aware Quantization for Deep Neural Networks
714. Modeling Facial Geometry using Compositional VAEs
715. Encoding Crowd Interaction with Deep Neural Network for Pedestrian Trajectory Prediction
716. DeepVoting: A Robust and Explainable Deep Network for Semantic Part Detection under Partial Occlusion
717. Attentional ShapeContextNet for Point Cloud Recognition
718. Weakly Supervised Instance Segmentation using Class Peak Response
719. Fast and Robust Estimation for Unit-Norm Constrained Linear Fitting Problems
720. Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
721. Multi-Level Factorisation Net for Person Re-Identification
722. Video Based Reconstruction of 3D People Models
723. Real-Time Monocular Depth Estimation using Synthetic Data with Domain Adaptation via Image Style Transfer
724. Logo Synthesis and Manipulation with Clustered Generative Adversarial Networks
725. Improved Fusion of Visual and Language Representations by Dense Symmetric Co-Attention for Visual Question Answering
726. Image Super-resolution via Dual-state Recurrent Neural Networks
727. Excitation Backprop for RNNs
728. Image Generation from Scene Graphs
729. Learning Spatial-Temporal Regularized Correlation Filters for Visual Tracking
730. Image Restoration by Estimating Frequency Distribution of Local Patches
731. Learning to Adapt Structured Output Space for Semantic Segmentation
732. Deep Spatial Feature Reconstruction for Partial Person Re-identification
733. Tight Nonconvex Relaxation of MAP Inference
734. Multiple Granularity Group Interaction Prediction
735. Accurate and Diverse Sampling of Sequences based on a ``Best of Many'' Sample Objective
736. Learning Rich Features for Image Manipulation Detection
737. DA-GAN: Instance-level Image Translation by Deep Attention Generative Adversarial Network
738. A Benchmark for Articulated Human Pose Estimation and Tracking
739. Preserving Semantic Relations for Zero-Shot Learning
740. Geometry-Aware Scene Text Detection with Instance Transformation Network
741. CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise
742. Joint Cuts and Matching of Partitions in One Graph
743. Fast and Accurate Online Video Object Segmentation via Tracking Parts
744. Learning Nested Structures in Deep Neural Networks
745. Practical Block-wise Neural Network Architecture Generation
746. AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation
747. Modifying Non-Local Variations Across Multiple Views
748. Connecting Pixels to Privacy and Utility: Automatic Redaction of Private Information in Images
749. Divide and Grow: Capturing Huge Diversity in Crowd Images with Incrementally Growing CNN
750. When will you do what? - Anticipating Temporal Occurrences of Activities
751. Visual Question Answering with Memory-Augmented Networks
752. Stochastic Variational Inference with Gradient Linearization
753. Human Pose Estimation with Parsing Induced Learner
754. 3D Registration of Curves and Surfaces using Local Differential Information
755. Deformation Aware Image Compression
756. PoseFlow: A Deep Motion Representation for Understanding Human Behaviors in Videos
757. MovieGraphs: Towards Understanding Human-Centric Situations from Videos
758. Hybrid Camera Pose Estimation
759. Fast Monte-Carlo Localization on Aerial Vehicles using Approximate Continuous Belief Representations
760. PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume
761. Hierarchical Recurrent Attention Networks for Structured Online Maps
762. Learning Less is More - 6D Camera Localization via 3D Surface Regression
763. Visual Question Generation as Dual Task of Visual Question Answering
764. 3D Object Detection with Latent Support Surfaces
765. An Analysis of Scale Invariance in Object Detection - SNIP
766. 3D Semantic Trajectory Reconstruction from 3D Pixel Continuum
767. KIPPI: KInetic Polygonal Partitioning of Images
768. COCO-Stuff: Thing and Stuff Classes in Context
769. Joint Optimization Framework for Learning with Noisy Labels
770. Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networks
771. Deep Cost-Sensitive and Order-Preserving Feature Learning for Cross-Population Age Estimation
772. Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments
773. Deep Back-Projection Networks For Super-Resolution
774. Generating a Fusion Image: One' s Identity and Another's Shape
775. V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map
776. Long-Term On-Board Prediction of People in Traffic Scenes under Uncertainty
777. Cross-modal Deep Variational Hand Pose Estimation
778. Learning to Estimate 3D Human Pose and Shape from a Single Color Image
779. Video Rain Removal By Multiscale Convolutional Sparse Coding
780. Toward Driving Scene Understanding: A Dataset for Learning Driver Behavior and Causal Reasoning
781. Learning 3D Shape Completion from Point Clouds with Weak Supervision
782. SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels
783. Salience Guided Depth Calibration for Perceptually Optimized Compressive Light Field 3D Display
784. Weakly-supervised Deep Convolutional Neural Network Learning for Facial Action Unit Intensity Estimation
785. Rolling Shutter and Radial Distortion are Features for High Frame Rate Multi-camera Tracking
786. Robust Hough Transform Based 3D Reconstruction from Circular Light Fields
787. Feedback-prop: Convolutional Neural Network Inference under Partial Evidence
788. Learning Strict Identity Mappings in Deep Residual Networks
789. Residual Parameter Transfer for Deep Domain Adaptation
790. Exploring Disentangled Feature Representation Beyond Face Identification
791. SPLATNet: Sparse Lattice Networks for Point Cloud Processing
792. Unsupervised Training for 3D Morphable Model Regression
793. A Bi-directional Message Passing Model for Salient Object Detection
794. Learning to See in the Dark
795. Erase or Fill? Deep Joint Recurrent Rain Removal and Reconstruction in Videos
796. Finding beans in burgers: Deep semantic-visual embedding with localization
797. Referring Relationships
798. Adversarially Learned One-Class Classifier for Novelty Detection
799. Surface Networks
800. Efficient parametrization of multi-domain deep neural networks
801. Recognizing Human Actions as Evolution of Pose Estimation Maps
802. Soccer on Your Tabletop
803. CVM-Net: Cross-View Matching Network for Image-Based Ground-to-Aerial Geo-Localization
804. Gesture Recognition: Focus on the Hands
805. Video Object Segmentation via Inference in A CNN-Based Higher-Order Spatio-Temporal MRF
806. Real-world Anomaly Detection in Surveillance Videos
807. Learning a Single Convolutional Super-Resolution Network for Multiple Degradations
808. Iterative Visual Reasoning Beyond Convolutions
809. Guide Me: Interacting with Deep Networks
810. PiCANet: Learning Pixel-wise Contextual Attention for Saliency Detection
811. Future Frame Prediction for Anomaly Detection A New Baseline
812. Structure Preserving Video Prediction
813. Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networks
814. Captioning Images with Style Transfer from Unaligned Text Corpora
815. Anatomical Priors in Convolutional Networks for Unsupervised Biomedical Segmentation
816. Illuminant Spectra-based Source Separation Using Flash Photography
817. 3D Human Pose Reconstruction and Action Classification in Robot Assisted Therapy of Children with Autism
818. Discrete-Continuous ADMM for Transductive Inference in Higher-Order MRFs
819. Classification Driven Dynamic Image Enhancement
820. Feature Generating Networks for Zero-Shot Learning
821. Beyond Trade-off: Accelerate FCN-based Face Detection with Higher Accuracy
822. MiCT: Mixed 3D/2D Convolutional Tube for Human Action Recognition
823. Unsupervised Learning and Segmentation of Complex Activities from Video
824. Sparse Photometric 3D Face Reconstruction Guided by Morphable Models
825. LSTM stack-based Neural Multi-sequence Alignment TeCHnique (NeuMATCH)
826. Inverse Composition Discriminative Optimization for Point Cloud Registration
827. Inference in Higher Order MRF-MAP Problems with Small and Large Cliques
828. Look at Boundary: A Boundary-Aware Face Alignment Algorithm
829. LEGO: Learning Edge with Geometry all at Once by Watching Videos
830. CosFace: Large Margin Cosine Loss for Deep Face Recognition
831. Learning Semantic Concepts and Order for Image and Sentence Matching
832. Learning to Look Around: Intelligently Exploring Unseen Environments for Unknown Tasks
833. Low-shot learning with large-scale diffusion
834. Multimodal Visual Concept Learning with Weakly Supervised Techniques
835. Cross-View Image Synthesis using Conditional Generative Adversarial Nets
836. Pixel-Wise Metric Learning for Blazingly Fast Video Object Segmentation
837. PieAPP: Perceptual Image-Error Assessment through Pairwise Preference
838. Cube Padding for Weakly-Supervised Saliency Prediction in 360$^{\circ}$ Videos
839. CRRN: Multi-Scale Guided Concurrent Reflection Removal Network
840. Stereoscopic Neural Style Transfer
841. Low-shot Learning from Imaginary Data
842. Fast, Simple, and Effective Resource-Constrained Structure Learning of Deep Networks
843. Unsupervised Sparse Dirichlet-Net for Hyperspectral Image Super-Resolution
844. Visual Grounding via Accumulated Attention
845. Event-based Vision meets Deep Learning on Steering Prediction for Self-driving Cars
846. Monocular 3D Pose and Shape Estimation of Multiple People in Natural Scenes
847. Actor and Action Video Segmentation from a Sentence
848. AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks
849. CartoonGAN: Generative Adversarial Networks for Photo Cartoonization
850. RayNet: Learning Volumetric 3D Reconstruction with Ray Potentials
851. Tracking Multiple Objects Outside the Line of Sight using Speckle Imaging
852. Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation
853. Densely Connected Pyramid Dehazing Network
854. Matching Adversarial Networks
855. Automatic Map Inference from Aerial Images
856. Polarimetric Dense Monocular SLAM
857. Learning Attribute Representations with Localization for Flexible Fashion Search
858. Self-Supervised Adversarial Hashing Networks for Cross-Modal Retrieval
859. Unsupervised CCA
860. Analyzing Filters Toward Efficient ConvNet
861. Good Appearance Features for Multi-Target Multi-Camera Tracking
862. Are You Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learning
863. Efficient Optimization for Rank-based Loss Functions
864. ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing
865. A Perceptual Measure for Deep Single Image Camera Calibration
866. Radially-Distorted Conjugate Translations
867. Multi-task Learning by Maximizing Statistical Dependence
868. Creating Capsule Wardrobes from Fashion Images
869. Towards Human-Machine Cooperation: Evolving Active Learning with Self-supervised Process for Object Detection
870. Synthesizing Images of Humans in Unseen Poses
871. Learning to Act Properly: Predicting and Explaining Affordances from Images
872. Pyramid Stereo Matching Network
873. Factoring Shape, Pose, and Layout from the 2D Image of a 3D Scene
874. A General Two-Step Quantization Approach for Low-bit Neural Networks with High Accuracy
875. GVCNN: Group-View Convolutional Neural Networks for 3D Shape Recognition
876. Convolutional Neural Networks with Alternately Updated Clique
877. Squeeze-and-Excitation Networks
878. NISP: Pruning Networks using Neuron Importance Score Propagation
879. Audio to Body Dynamics
880. ID-GAN: Learning a Symmetry Three-Player GAN for Identity-Preserving Face Synthesis
881. Deep Learning of Graph Matching
882. Neural Baby Talk
883. Efficient Video Object Segmentation via Network Modulation
884. Regularizing Deep Networks by Modeling and Predicting Label Structure
885. Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation
886. Face Detector Adaptation without Negative Transfer or Catastrophic Forgetting
887. Motion-Appearance Co-Memory Networks for Video Question Answering
888. Compare and Contrast: Learning Prominent Visual Differences
889. Tangent Convolutions for Dense Prediction in 3D
890. Single-Shot Object Detection with Enriched Semantics
891. Generating Synthetic X-ray Images of a Person from the Surface Geometry
892. Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering
893. Edit Probability for Scene Text Recognition
894. MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features
895. Weakly-Supervised Action Segmentation with Iterative Soft Boundary Assignment
896. Texture Mapping for 3D Reconstruction with RGB-D Sensor
897. Multi-Agent Diverse Generative Adversarial Networks
898. Towards Universal Representation for Unseen Action Recognition
899. Zero-Shot Kernel Learning.
900. DOTA: A Large-scale Dataset for Object Detection in Aerial Images
901. Multi-Frame Quality Enhancement for Compressed Video
902. From Lifestyle VLOGs to Everyday Interactions
903. Occluded Pedestrian Detection through Guided Attention in CNNs
904. Decoupled Networks
905. Deep Cocktail Networks: Multi-source Unsupervised Domain Adaptation with Category Shift
906. Partially Shared Multi-Task Convolutional Neural Network with Local Constraint for Face Attribute Learning
907. Joint Pose and Expression Modeling for Facial Expression Recognition
908. Unsupervised Textual Grounding: Linking Words to Image Concepts
909. Interleaved Structured Sparse Convolutional Neural Networks
910. Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models
911. ROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban Scenes
912. Image to Image Translation for Domain Adaptation
913. A Face to Face Neural Conversation Model
914. Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification
915. FSRNet: End-to-End Learning Face Super-Resolution with Facial Priors
916. SO-Net: Self-Organizing Network for Point Cloud Analysis
917. MoNet: Moments Embedding Network
918. Coupled End-to-end Transfer Learning with Generalized Fisher Information
919. Inferring Light Fields from Shadows
920. LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Image
921. Multi-Level Fusion based 3D Object Detection from Monocular Images
922. Single-Image Depth Estimation Based on Fourier Domain Analysis
923. Flow Guided Recurrent Neural Encoder for Video Salient Object Detection
924. Super-Resolving Very Low-Resolution Face Images with Supplementary Attributes
925. Seeing Voices and Hearing Faces: Cross-modal biometric matching
926. Feature Mapping for Learning Fast and Accurate 3D Pose Inference from Synthetic Images
927. Fast and Accurate Single Image Super-Resolution via Information Distillation Network
928. Learning and Using the Arrow of Time
929. Rethinking the Faster R-CNN Architecture for Temporal Action Localization
930. Deeply Learned Filter Response Functions for Hyperspectral Reconstruction
931. Fusing Crowd Density Maps and Visual Object Trackers for People Tracking in Crowd Scenes
932. Intrinsic Image Transformation via Scale Space Decomposition
933. Deep Ordinal Regression Network for Monocular Depth Estimation
934. Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation
935. Functional Map of the World
936. CSGNet: Neural Shape Parser for Constructive Solid Geometry
937. Instance Embedding Transfer to Unsupervised Video Object Segmentation
938. Statistical Tomography of Microscopic Life
939. Point-wise Convolutional Neural Networks
940. Pixar: Real-time 3D Object Detection from Point Clouds
941. HydraNets: Specialized Dynamic Architectures for Efficient Inference
942. Deep Depth Completion of a Single RGB-D Image
943. Learning to Extract a Video Sequence from a Single Motion-Blurred Image
944. A Fast Resection-Intersection Method for the Known Rotation Problem
945. iVQA: Inverse Visual Question Answering
946. Crowd Counting via Adversarial Cross-Scale Consistency Pursuit
947. Trust your Model: Light Field Depth Estimation with inline Occlusion Handling
948. PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition
949. A Memory Network Approach for Story-based Temporal Summarization of 360° Videos
950. Tags2Parts: Discovering Semantic Regions from Shape Tags
951. Jerk-Aware Video Acceleration Magnification
952. A Robust Method for Strong Rolling Shutter Effects Correction Using Lines with Automatic Feature Selection
953. Mobile Video Object Detection with Temporally-Aware Feature Maps
954. VirtualHome: Simulating Household Activities via Programs
955. MoNet: Deep Motion Exploitation for Video Object Segmentation
956. Detect globally, refine locally: A novel approach to saliency detection
957. EPINET: A Fully-Convolutional Neural Network for Light Field Depth Estimation by Using Epipolar Geometry
958. Learning Face Age Progression: A Pyramid Architecture of GANs
959. Normalized Cut Loss for Weakly Supervised CNN Segmentation
960. Reconstructing Thin Structures of Manifold Surfaces by Integrating Spatial Curves
961. Dynamic Few-Shot Visual Learning without Forgetting
962. Camera Style Adaptation for Person Re-identification
963. In-Place Activated BatchNorm for Memory-Optimized Training of DNNs
964. NeuralNetwork-Viterbi: A Framework for Weakly Supervised Video Learning
965. Resource Aware Person Re-identification across Multiple Resolutions
966. Zero-Shot Super-Resolution using Deep Internal Learning
967. Analysis of Hand Segmentation in the Wild
968. Who's Better? Who's Best? Pairwise Deep Ranking for Skill Determination
969. Face Aging with Identity-Preserved Conditional Generative Adversarial Networks
970. Deep Extreme Cut: From Extreme Points to Object Segmentation
971. Person Re-identification with Cascaded Pairwise Convolutions
972. Distributable Consistent Multi-Graph Matching
973. A Twofold Siamese Network for Real-Time Object Tracking
974. AON: Towards Arbitrarily-Oriented Text Recognition
975. Deep Cauchy Hashing for Hamming Space Retrieval
976. Non-blind Deblurring: Handling Kernel Uncertainty with CNNs
977. Referring Image Segmentation via Recurrent Refinement Networks
978. Deep Density Clustering of Unconstrained Faces
979. A Constrained Deep Neural Network for Ordinal Regression