NAS

• Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours
  • paper
  • code

Multiple Tasks

• Attentive Single-Tasking of Multiple Tasks
  • paper
  • code

Deformable Convolution

• Deformable Convolutional Networks
  • paper
  • code
• Deformable ConvNets v2: More Deformable, Better Results
  • paper

Pose estimation

• GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond
  • paper
  • code
• High-Resolution Representations for Labeling Pixels and Regions
  • paper
  • code

human pose estimation

2019

• Deep High-Resolution Representation Learning for Human Pose Estimation
  • paper
  • code

semantics segmentation

2019

• Segmenting the Future
  • paper
  • code
• Dual Attention Network for Scene Segmentation
  • paper
  • code
• Residual pyramid learning for single-shot semantic segmentation
  • paper
• Scale-Adaptive Neural Dense Features:Learning via Hierarchical Context Aggregation
  • paper
  • code

• Structured Knowledge Distillation for Semantic Segmentation
  • paper

• In Defense of Pre-trained ImageNet Architectures for Real-time Semantic Segmentation of Road-driving Images
  • paper
  • code
• FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation
  • paper
  • code
  • webpage

VSOD

• Shifting More Attention to Video Salient Object Detection
  • paper
  • code
  • projectpage

Salient-Object-Detection

2019

• On guiding video object segmentation
  • paper
• Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection
  • paper
  • code
• A Simple Pooling-Based Design for Real-Time Salient Object Detection
  • paper
  • code
  • adaptiveavgpool2d
• SAC-Net: Spatial Attenuation Context for Salient Object Detection
  • paper
  • webpage

2018

• Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection
  • paper
  • code
• PiCANet: Learning Pixel-wise Contextual Attention for Saliency Detection
  • paper
  • code
• PAGRN: Progressive Attention Guided Recurrent Network for Salient Object Detection. (CVPR)
  • paper
  • code

• Direction-aware Spatial Context Features for Shadow Detection
  • paper
  • code
  • webpage
• R³Net: Recurrent Residual Refinement Network for Saliency Detection (IJCAI2018)
  • paper
  • code
• A Bi-Directional Message Passing Model for Salient Object Detection. (CVPR)
  • paper
  • code
• Progressive Attention Guided Recurrent Network for Salient Object Detection. (CVPR)
  • paper

2017

• Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection. (ICCV)
  • paper
  • code