This is the official website of the Visual Scene Understanding group of VIPL, ICT, CAS.

[CVPR2026]GEAR: GEometry-motion Alternating Refinement for Articulated Object Modeling with Gaussian Splatting[Paper]

[AAAI2026]Tell as You Want: Customizing Image Narrative with Knowledge and Thoughts[Paper]

[ICRA2026]RoboPCA: Pose-centered Affordance Learning from Human Demonstrations for Robot Manipulation[Paper]

[ICRA2026]Uni-Skill: Building Self-Evolving Skill Repository for Generalizable Robotic Manipulation[Paper]

[arXiv2025]VisKnow: Constructing Visual Knowledge Base for Object Understanding[Paper][Project]

[RAL2025]FreeMask3D: Zero-shot Point Cloud Instance Segmentation without 3D Training[Paper]

[BMVC2025]Catch Your Concepts: A Flexible Concept Locator for Interpretable Visual Recognition[Paper][Supp][Video][Code]

[PRL2025]Cross-Domain Few-Shot 3D Point Cloud Semantic Segmentation[Paper][Supp][Code]

[ICCV2025]OV3D-CG: Open-vocabulary 3D Instance Segmentation with Contextual Guidance[Paper][Supp][Code][Homepage]

[IROS2025]Robotic Programmer: Video Instructed Policy Code Generation for Robotic Manipulation (oral)[Paper][Homepage]

[RAL2025]Dynamic Behavior Cloning With Temporal Feature Prediction: Enhancing Robotic Arm Manipulation in Moving Object Tasks[Paper][Supp]

[CVPR2025]R2C: Mapping Room to Chessboard to Unlock LLM As Low-Level Action Planner[Paper][Supp][Code][Homepage]

[PRL2025]UniFa: A unified feature hallucination framework for any-shot object detection[Paper][Supp][Code]

[arXiv2024]M4U: Evaluating Multilingual Understanding and Reasoning for Large Multimodal Models[Paper][Code]

[ECCV2024]Think before Placement: Common Sense Enhanced Multi-modal Transformer for Object Placement[Paper][Code]

[ECCV2024]HiFi-Score: Fine-grained Image Description Evaluation with Hierarchical Parsing Graphs[Paper][Code]

[TIP2024]Event Graph Guided Compositional Spatial-Temporal Reasoning for Video Question Answering[Paper][Supp][Code]

[MM2024]Calibration for Long-tailed Scene Graph Generation[Paper][Code]

[PR2024]Introspective GAN: Learning to Grow a GAN for Incremental Generation and Classification[Paper][Code]

[WACV2024]Interpretable Object Recognition by Semantic Prototype Analysis[Paper][Supp][Code]

[PR2024]Hierarchical image-to-image translation with nested distributions modeling[Paper][Supp][Code]

[BMVC2024]Blocks as Probes: Dissecting Categorization Ability of Large Multimodal Models[Paper][Code][Homepage]

[AAAI2024]Point2Real: Bridging the Gap between Point Cloud and Realistic Image for Open-World 3D Recognition[Paper][Code]

[BMVC2024]Hierarchical Prompt Learning for Scene Graph Generation[Code]

[IJCV2023]Importance first: Generating scene graph of human interest[Paper][Supp][Code]

[NeurIPS2023]Glance and Focus: Memory Prompting for Multi-Event Video Question Answering[Paper][Code]

[WACV2023]Semantic Guided Latent Parts Embedding for Few-Shot Learning[Paper][Supp][Code]

[TPAMI2023]CRIC: A VQA Dataset for Compositional Reasoning on Vision and Commonsense[Paper][Supp][Homepage]

[WACV2022]SEGA: Semantic Guided Attention on Visual Prototype for Few-Shot Learning[Paper][Supp][Code]

[PRL2022]Rethinking Class Orders and Transferability in Class Incremental Learning[Paper][Supp][Code]

[IROS2022]Implicit-Part Based Context Aggregation for Point Cloud Instance Segmentation[Paper][Supp][Code]

[WACV2022]From Node to Graph: Joint Reasoning on Visual-Semantic Relational Graph for Zero-Shot Detection[Paper][Supp][Code]

[ICCV2021]Env-QA: A Video QA Dataset for Dynamic Environments Understanding[Paper][Supp][Homepage]

[PR2021]Deep Video Code for Efficient Face Video Retrieval[Paper][Supp][Code]

[CVPRW2021]A Tale of Two CILs: The Connections between Class Incremental Learning and Class Imbalanced Learning, and Beyond[Paper][Supp][Code]

[ECCV2020]Sketching Image Gist: Human-Mimetic Hierarchical Scene Graph Generation[Paper][Supp][Code]

[CVPR2016]Deep Supervised Hashing for Fast Image Retrieval[Paper][Code]