Scene Understanding

Multiple Feature Refining Network for Visual Emotion Distribution Learning AAAI 2025 Multi-Sourced Compositional Generalization in Visual Question Answering IJCAI 2025 MultiVerse: A Multi-Turn Conversation Benchmark for Evaluating Large Vision and Language Models ICCV 2025 Multi-View Pedestrian Occupancy Prediction with a Novel Synthetic Dataset AAAI 2025 Multi-View Pose-Agnostic Change Localization with Zero Labels CVPR 2025 Near, far: Patch-ordering enhances vision foundation models' scene understanding ICLR 2025 NoiseController: Towards Consistent Multi-view Video Generation via Noise Decomposition and Collaboration ICCV 2025 No More Sibling Rivalry: Debiasing Human-Object Interaction Detection ICCV 2025 NTSEBENCH: Cognitive Reasoning Benchmark for Vision Language Models NAACL 2025 NuiScene: Exploring Efficient Generation of Unbounded Outdoor Scenes ICCV 2025 OccProphet: Pushing the Efficiency Frontier of Camera-Only 4D Occupancy Forecasting with an Observer-Forecaster-Refiner Framework ICLR 2025 Omni-Chart-600K: A Comprehensive Dataset of Chart Types for Chart Understanding NAACL 2025 On the Perception Bottleneck of VLMs for Chart Understanding EMNLP 2025 Open-Vocabulary Octree-Graph for 3D Scene Understanding ICCV 2025 Open-World Amodal Appearance Completion CVPR 2025 OURO: A Self-Bootstrapped Framework for Enhancing Multimodal Scene Understanding ICCV 2025 Out of Length Text Recognition with Sub-String Matching AAAI 2025 PanoGS: Gaussian-based Panoptic Segmentation for 3D Open Vocabulary Scene Understanding CVPR 2025 PanSt3R: Multi-view Consistent Panoptic Segmentation ICCV 2025 Pareiduo: A Human–LLM Dialogue in Sand NeurIPS 2025 Perspective-Aware Reasoning in Vision-Language Models via Mental Imagery Simulation ICCV 2025 PhysGen3D: Crafting a Miniature Interactive World from a Single Image CVPR 2025 Physics Context Builders: A Modular Framework for Physical Reasoning in Vision-Language Models ICCV 2025 Planar Affine Rectification from Local Change of Scale and Orientation ICCV 2025 PlanarSplatting: Accurate Planar Surface Reconstruction in 3 Minutes CVPR 2025