Chunhua Shen

Research interests

Publications

• BiSeNet V2: Bilateral Network with Guided Aggregation for Real-Time Semantic Segmentation

  International Journal of Computer Vision · 2021 · https://doi.org/10.1007/s11263-021-01515-2

• End-to-End Video Instance Segmentation with Transformers

  · 2021 · 10.1109/cvpr46437.2021.00863

• CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentation

  Lecture notes in computer science · 2021 · 10.1007/978-3-030-87199-4_16

• Dense Contrastive Learning for Self-Supervised Visual Pre-Training

  · 2021 · 10.1109/cvpr46437.2021.00304

• Twins: Revisiting the Design of Spatial Attention in Vision Transformers

  arXiv (Cornell University) · 2021 · 10.48550/arxiv.2104.13840

• SOLO: Segmenting Objects by Locations

  Lecture notes in computer science · 2020 · 10.1007/978-3-030-58523-5_38

• Conditional Convolutions for Instance Segmentation

  Lecture notes in computer science · 2020 · 10.1007/978-3-030-58452-8_17

• Deep Learning for Anomaly Detection: A Review

  Singapore Management University Institutional Knowledge (InK) (Singapore Management University) · 2020 · https://doi.org/10.48550/arxiv.2007.02500

• BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation

  · 2020 · 10.1109/cvpr42600.2020.00860

• DeepEMD: Few-Shot Image Classification With Differentiable Earth Mover’s Distance and Structured Classifiers

  · 2020 · 10.1109/cvpr42600.2020.01222

• FCOS: A Simple and Strong Anchor-free Object Detector

  IEEE Transactions on Pattern Analysis and Machine Intelligence · 2020 · 10.1109/tpami.2020.3032166

• PolarMask: Single Shot Instance Segmentation With Polar Representation

  · 2020 · 10.1109/cvpr42600.2020.01221

• FCOS: Fully Convolutional One-Stage Object Detection

  Journal · 2019 · https://doi.org/10.1109/iccv.2019.00972

• CANet: Class-Agnostic Segmentation Networks With Iterative Refinement and Attentive Few-Shot Learning

  · 2019 · 10.1109/cvpr.2019.00536

• Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation

  Journal · 2019 · https://doi.org/10.1109/cvpr.2019.00050

• RefineNet: Multi-Path Refinement Networks for Dense Prediction

  IEEE Transactions on Pattern Analysis and Machine Intelligence · 2019 · https://doi.org/10.1109/tpami.2019.2893630

• Efficient and Accurate Arbitrary-Shaped Text Detection With Pixel Aggregation Network

  · 2019 · 10.1109/iccv.2019.00853

• Hyperspectral Classification Based on Lightweight 3-D-CNN With Transfer Learning

  IEEE Transactions on Geoscience and Remote Sensing · 2019 · https://doi.org/10.1109/tgrs.2019.2902568

• Attention-Guided Network for Ghost-Free High Dynamic Range Imaging

  Journal · 2019 · https://doi.org/10.1109/cvpr.2019.00185

• Unsupervised Scale-consistent Depth and Ego-motion Learning from\n Monocular Video

  arXiv (Cornell University) · 2019 · https://doi.org/10.48550/arxiv.1908.10553

• Wider or Deeper: Revisiting the ResNet Model for Visual Recognition

  Pattern Recognition · 2019 · https://doi.org/10.1016/j.patcog.2019.01.006

• Repulsion Loss: Detecting Pedestrians in a Crowd

  · 2018 · 10.1109/cvpr.2018.00811

• Towards Effective Low-Bitwidth Convolutional Neural Networks

  Journal · 2018 · https://doi.org/10.1109/cvpr.2018.00826

• RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation

  Journal · 2017 · https://doi.org/10.1109/cvpr.2017.549

• Towards Context-Aware Interaction Recognition for Visual Relationship Detection

  Journal · 2017 · https://doi.org/10.1109/iccv.2017.71

• Deep learning features at scale for visual place recognition

  Journal · 2017 · https://doi.org/10.1109/icra.2017.7989366

• From Motion Blur to Motion Flow: A Deep Learning Solution for Removing Heterogeneous Motion Blur

  Journal · 2017 · https://doi.org/10.1109/cvpr.2017.405

• Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections

  arXiv (Cornell University) · 2016 · 10.48550/arxiv.1603.09056

• Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation

  · 2016 · 10.1109/cvpr.2016.348

• Depth and surface normal estimation from monocular images using regression on deep features and hierarchical CRFs

  · 2015 · 10.1109/cvpr.2015.7298715

• Supervised Discrete Hashing

  · 2015 · 10.1109/cvpr.2015.7298598

• Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields

  IEEE Transactions on Pattern Analysis and Machine Intelligence · 2015 · 10.1109/tpami.2015.2505283

• A survey of appearance models in visual object tracking

  ACM Transactions on Intelligent Systems and Technology · 2013 · 10.1145/2508037.2508039

Current projects

No projects listed.