Latest

• From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models
• Learning by Correction: Efficient Tuning Task for Zero-Shot Generative Vision-Language Reasoning
• Two papers accepted by CVPR 2024!
• One papers accepted by TPAMI 2024!
• SGTR+: End-to-end Scene Graph Generation with Transformer
• Class-relation Knowledge Distillation for Novel Class Discovery
• Novel Class Discovery for Long-tailed Recognition
• Modeling Multimodal Aleatoric Uncertainty in Segmentation with Mixture of Stochastic Experts
• Two papers accepted by CVPR 2022!
• Weakly Supervised Nuclei Segmentation via Instance Learning
• Superpixel-guided Iterative Learning from Noisy Labels for Medical Image Segmentation
• An EM Framework for Online Incremental Learning of Semantic Segmentation
• Learning Implicit Temporal Alignment for Few-shot Video Classification
• Single Image 3D Object Estimation with Primitive Graph Networks
• One paper accepted by IJCAI 2021!
• One paper accepted by MICCAI 2021!
• Three papers accepted by ACM MM 2021!
• Three papers accepted by ACM MM 2021!
• Weakly Supervised Volumetric Segmentation via Self-taught Shape Denoising Model
• Distribution Alignment: A Unified Framework for Long-tail Visual Recognition
• DER: Dynamically Expandable Representation for Class Incremental Learning(Oral)
• One papers accepted by MIDL 2021!
• Relation-aware Instance Refinement for Weakly Supervised Visual Grounding
• Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation
• Confidence-aware Adversarial Learning for Self-supervised Semantic Matching
• One paper accepted by ECCV2020!
• Part-aware prototype Network for Few-shot Semantic Segmentation
• One paper accepted by MICCAI 2020!
• One paper accepted by PRCV 2020!
• Shape-aware Semi-supervised 3D Semantic Segmentation for Medical Images
• Learning Cross Modal Context Graph for Visual Grounding
• Learning Context-aware Task Reasoning for Efficient Meta-reinforcement Learning
• Four papers accepted by CVPR 2021!
• One paper accepted by AAAI 2020!
• One paper accepted by AAMAS 2020!
• Pose-aware Multi-level Feature Network for Human Object Interaction Detection
• Two papers accepted by ICCV 2019(One Oral & One Poster)!
• Dynamic Context Correspondence Network for Semantic Alignment
• LatentGNN: Learning Efficient Non-local Relations for Visual Recognition
• A Dual Attention Network With Semantic Embedding for Few-shot Learning
• 3D Object Structure Recovery via Semi-supervised Learning on Videos
• Geometry-aware Deep Network for Single-Image Novel View Synthesis
• One-shot Action Localization by Learning Sequence Matching Network
• SemStyle: Learning to Generate Stylised Image Captions using Unaligned Text
• Instance-aware Detailed Action Labeling in Videos
• 3D Box Proposals from a Single Monocular Image of an Indoor Scene
• Forest Change Detection in Incomplete Satellite Images With Deep Neural Networks
• Stacked Learning to Search for Scene Labeling
• Deep Free-Form Deformation Network for Object-Mask Registration
• Learning deep structured network for weakly supervised change detection
• Predicting Salient Face in Multiple-face Videos
• Boundary-aware Instance Segmentation
• Efficient Scene Layout Aware Object Detection for Traffic Surveillance
• Indoor Scene Parsing with Instance Segmentation, Semantic Labeling and Support Relationship Inference
• Learning Spatial Transforms for Refining Object Segment Proposals