Scene Understanding

CoSpace: Benchmarking Continuous Space Perception Ability for Vision-Language Models CVPR 2025 Counterfactual Thinking Driven Emotion Regulation for Image Sentiment Recognition IJCAI 2025 Crab: A Unified Audio-Visual Scene Understanding Model with Explicit Cooperation CVPR 2025 CrossOver: 3D Scene Cross-Modal Alignment CVPR 2025 Cross-Task Affinity Learning for Multitask Dense Scene Predictions WACV 2025 CrowdMAC: Masked Crowd Density Completion for Robust Crowd Density Forecasting WACV 2025 CSV-Occ: Fusing Multi-frame Alignment for Occupancy Prediction with Temporal Cross State Space Model and Central Voting Mechanism ICML 2025 CUET-NLP_Big_O@DravidianLangTech 2025: A Multimodal Fusion-based Approach for Identifying Misogyny Memes NAACL 2025 DDS: Decoupled Dynamic Scene-Graph Generation Network WACV 2025 Decoding Alzheimer’s: Interpretable Visual and Logical Attention in Picture Description Tasks Interspeech 2025 DepR: Depth Guided Single-view Scene Reconstruction with Instance-level Diffusion ICCV 2025 DeRainGS: Gaussian Splatting for Enhanced Scene Reconstruction in Rainy Environments AAAI 2025 DiffSim: Taming Diffusion Models for Evaluating Visual Similarity ICCV 2025 DiffVsgg: Diffusion-Driven Online Video Scene Graph Generation CVPR 2025 Diorama: Unleashing Zero-shot Single-view 3D Indoor Scene Modeling ICCV 2025 DIP: Unsupervised Dense In-Context Post-training of Visual Representations ICCV 2025 DiscoSG: Towards Discourse-Level Text Scene Graph Parsing through Iterative Graph Refinement EMNLP 2025 DiskVPS: Vanishing Point Detector via Hough Transform in a Disk Region CVPR 2025 DIV-FF: Dynamic Image-Video Feature Fields For Environment Understanding in Egocentric Videos CVPR 2025 DocTTT: Test-Time Training for Handwritten Document Recognition using Meta-Auxiliary Learning WACV 2025 Do It Yourself: Learning Semantic Correspondence from Pseudo-Labels ICCV 2025 Do Visual Imaginations Improve Vision-and-Language Navigation Agents? CVPR 2025 DSPNet: Dual-vision Scene Perception for Robust 3D Question Answering CVPR 2025 DWIM: Towards Tool-aware Visual Reasoning via Discrepancy-aware Workflow Generation & Instruct-Masking Tuning ICCV 2025 DyFo: A Training-Free Dynamic Focus Visual Search for Enhancing LMMs in Fine-Grained Visual Understanding CVPR 2025