Scene Understanding

Situational Scene Graph for Structured Human-Centric Situation Understanding WACV 2025 SkipPool: Improved Sparse Hierarchical Graph Pooling with Differentiable Exploration AAAI 2025 SOVGaussian: Sparse-View 3D Gaussian Splatting for Open-Vocabulary Scene Understanding AAAI 2025 SPADE: Spatial-Aware Denoising Network for Open-vocabulary Panoptic Scene Graph Generation with Long- and Local-range Context Reasoning ICCV 2025 SpaRE: Enhancing Spatial Reasoning in Vision-Language Models with Synthetic Data ACL 2025 Spatial457: A Diagnostic Benchmark for 6D Spatial Reasoning of Large Mutimodal Models CVPR 2025 SpatialSplat: Efficient Semantic 3D from Sparse Unposed Images ICCV 2025 SPHERE: Unveiling Spatial Blind Spots in Vision-Language Models Through Hierarchical Evaluation ACL 2025 SplatTalk: 3D VQA with Gaussian Splatting ICCV 2025 Statistical Confidence Rescoring for Robust 3D Scene Graph Generation from Multi-View Images ICCV 2025 Storynizor: Consistent Story Generation via Inter-Frame Synchronized and Shuffled ID Injection AAAI 2025 SUM: Saliency Unification through Mamba for Visual Attention Modeling WACV 2025 Supercharging Floorplan Localization with Semantic Rays ICCV 2025 SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition ICCV 2025 Synthetic Visual Genome CVPR 2025 T2SG: Traffic Topology Scene Graph for Topology Reasoning in Autonomous Driving CVPR 2025 TaiwanVQA: A Benchmark for Visual Question Answering for Taiwanese Daily Life COLING 2025 TB-HSU: Hierarchical 3D Scene Understanding with Contextual Affordances AAAI 2025 Temporally Consistent Object-Centric Learning by Contrasting Slots CVPR 2025 Textured Mesh Saliency: Bridging Geometry and Texture for Human Perception in 3D Graphics AAAI 2025 The Confidence Paradox: Can LLM Know When It’s Wrong? IJCNLP 2025 The Photographer's Eye: Teaching Multimodal Large Language Models to See, and Critique Like Photographers CVPR 2025 Thermal Polarimetric Multi-view Stereo ICCV 2025 TimeFormer: Capturing Temporal Relationships of Deformable 3D Gaussians for Robust Reconstruction ICCV 2025 TLSD: Breaking the Limit of Topological Lane Mapping with Graph Knowledge and Distance Awareness ACML 2025