Update ICCV2021.md

ICCV2021.md

@@ -187,7 +187,10 @@
 
 <a name="IOD"/> 
 
-### 图像目标检测(2D Object Detection)
+### 2D目标检测(2D Object Detection)
+
+[6] SimROD: A Simple Adaptation Method for Robust Object Detection<br>
+[paper](https://arxiv.org/abs/2107.13389)<br><br>
 
 [5] Active Learning for Deep Object Detection via Probabilistic Modeling<br>
 [paper](https://arxiv.org/abs/2103.16130)<br><br>
@@ -212,6 +215,14 @@
 [paper](https://arxiv.org/pdf/2107.11355.pdf)<br><br>
 
 
+<a name="ADI"/> 
+
+### 图像异常检测(Anomally Detection in Image)
+
+[1] Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detection<br>
+[paper](https://arxiv.org/abs/2107.13118)<br><br>
+
+
 <br>
 <a name="Segmentation"/> 
 
@@ -301,12 +312,22 @@
 [1] HRegNet: A Hierarchical Network for Large-scale Outdoor LiDAR Point Cloud Registration<br>
 [paper](https://arxiv.org/abs/2107.11992) | [project](https://ispc-group.github.io/hregnet)<br><br> 
 
+<a name="3DReconstruction"/> 
+
+### 三维重建(3D Reconstruction)
+
+[1] PlaneTR: Structure-Guided Transformers for 3D Plane Recovery<br>
+[paper](https://arxiv.org/abs/2107.13108) | [code](https://git.io/PlaneTR)<br><br>
+
 <br>
 
 <a name="NNS"/> 
 
 ## 神经网络设计与优化(Neural Network Structure Design & Optimization)
 
+[1] Energy-Based Open-World Uncertainty Modeling for Confidence Calibration(置信度校准)<br>
+[paper](https://arxiv.org/abs/2107.12628)<br><br>
+
 <a name="CNN"/>
 
 [2] Learning to Resize Images for Computer Vision Tasks<br>
@@ -452,6 +473,13 @@
 [1] HuMoR: 3D Human Motion Model for Robust Pose Estimation(Oral)<br>
 [paper](https://geometry.stanford.edu/projects/humor/docs/humor.pdf) | [video](https://youtu.be/5VWirxUHG0Y) | [project](https://geometry.stanford.edu/projects/humor/)<br><br>
 
+<a name="DepthEstimation"/> 
+
+### 深度估计(Depth Estimation)
+
+[1] MonoIndoor: Towards Good Practice of Self-Supervised Monocular Depth Estimation for Indoor Environments<br>
+[paper](https://arxiv.org/abs/2107.12429)<br><br>
+
 <br>
 <a name="ImageRetrieval"/> 
 
@@ -467,6 +495,9 @@
 
 ### 行为识别/行为识别/动作识别/检测/分割(Action/Activity Recognition)
 
+[2] Enriching Local and Global Contexts for Temporal Action Localization<br>
+[paper](https://arxiv.org/abs/2107.12960)<br><br>
+
 [1] Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition<br>
 [paper](https://arxiv.org/abs/2107.12213) | [code](https://github.com/Uason-Chen/CTR-GCN)<br><br>
 
@@ -488,6 +519,9 @@
 
 ## 视觉定位(Visual Localization)
 
+[3] Normalization Matters in Weakly Supervised Object Localization<br>
+[paper](https://arxiv.org/abs/2107.13221)<br><br>
+
 [2] TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization<br>
 [paper](https://arxiv.org/abs/2103.14862) | [code](https://github.com/vasgaowei/TS-CAM)<br><br>
 
@@ -540,6 +574,9 @@
 
 ## 文本检测/识别(Text Detection/Recognition)
 
+[4] Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection<br>
+[paper](https://arxiv.org/abs/2107.12664)<br><br>
+
 [3] Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognition<br>
 [paper](https://arxiv.org/abs/2107.12090)<br><br>
 
@@ -622,6 +659,12 @@
 
 ### 图像聚类(Image Clustering)
 
+[3] Graph Constrained Data Representation Learning for Human Motion Segmentation(人体运动分割)<br>
+[paper](https://arxiv.org/abs/2107.13362)<br><br>
+
+[2] Improve Unsupervised Pretraining for Few-label Transfer<br>
+[paper](https://arxiv.org/abs/2107.12369)<br><br>
+
 [1] Clustering by Maximizing Mutual Information Across Views<br>
 [paper](https://arxiv.org/abs/2107.11635)<br><br>
 
@@ -631,6 +674,15 @@
 
 ## 迁移学习/domain/自适应(Transfer Learning/Domain Adaptation)
 
+[6] Adversarial Unsupervised Domain Adaptation with Conditional and Label Shift: Infer, Align and Iterate<br>
+[paper](https://arxiv.org/abs/2107.13469)<br><br>
+
+[5] Recursively Conditional Gaussian for Ordinal Unsupervised Domain Adaptation(Oral)<br>
+[paper](https://arxiv.org/abs/2107.13467)<br><br>
+
+[4] Improve Unsupervised Pretraining for Few-label Transfer<br>
+[paper](https://arxiv.org/abs/2107.12369)<br><br>
+
 [3] Generalized Source-free Domain Adaptation<br>
 [homepage](https://sites.google.com/view/g-sfda/g-sfda) | [code](https://www.google.com/url?q=https%3A%2F%2Fgithub.com%2FAlbert0147%2FG-SFDA&sa=D&sntz=1&usg=AFQjCNGLrqNbPGLbA6USJ8N3xM7eb-RzYw)<br><br>
 
@@ -684,11 +736,13 @@
 [paper](https://arxiv.org/abs/2103.16130)<br><br>
 
 <br>
-
 <a name="VisualReasoning"/> 
 
 ## 视觉推理/视觉问答(Visual Reasoning/VQA)
 
+[3] Greedy Gradient Ensemble for Robust Visual Question Answering<br>
+[paper](https://arxiv.org/abs/2107.12651) | [code](https://github.com/GeraldHan/GGE)<br><br>
+
 [2] On the hidden treasure of dialog in video question answering<br>
 [paper](https://arxiv.org/abs/2103.14517)<br><br>
 
@@ -720,6 +774,15 @@
 
 ## 暂无分类
 
+Spatial Uncertainty-Aware Semi-Supervised Crowd Counting(人群计数)<br>
+[paper](https://arxiv.org/abs/2107.13271)<br><br>
+
+Rethinking Counting and Localization in Crowds: A Purely Point-Based Framework(Oral)(人群计数)<br>
+[paper](https://arxiv.org/abs/2107.12746) | [code](https://github.com/TencentYoutuResearch/CrowdCounting-P2PNet)<br><br>
+
+Uniformity in Heterogeneity:Diving Deep into Count Interval Partition for Crowd Counting(人群计数)<br>
+[paper](https://arxiv.org/abs/2107.12619) | [code](https://github.com/TencentYoutuResearch/CrowdCounting-UEPNet)<br><br>
+
 Self-Conditioned Probabilistic Learning of Video Rescaling(视频压缩)<br>
 [paper](https://arxiv.org/abs/2107.11639)<br><br>
 
@@ -750,6 +813,12 @@ KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs<br>
 
 # 2. ICCV2021 Oral（更新中）
 
+[18] Recursively Conditional Gaussian for Ordinal Unsupervised Domain Adaptation(Oral)<br>
+[paper](https://arxiv.org/abs/2107.13467)<br><br>
+
+[17] Rethinking Counting and Localization in Crowds: A Purely Point-Based Framework(Oral)(人群计数)<br>
+[paper](https://arxiv.org/abs/2107.12746) | [code](https://github.com/TencentYoutuResearch/CrowdCounting-P2PNet)<br><br>
+
 [16] Rank & Sort Loss for Object Detection and Instance Segmentation(Oral)<br>
 [paper](https://arxiv.org/abs/2107.11669) | [code](https://github.com/kemaloksuz/RankSortLoss)<br><br>