Video Processing

MVAD: A Multiple Visual Artifact Detector for Video Streaming WACV 2025 Neural Video Compression with Context Modulation CVPR 2025 OccluGaussian: Occlusion-Aware Gaussian Splatting for Large Scene Reconstruction and Rendering ICCV 2025 ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos CVPR 2025 Omnidirectional Multi-Object Tracking CVPR 2025 One-Dimensional Object Detection for Streaming Text Segmentation of Meeting Dialogue ACL 2025 One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object Trajectory ICCV 2025 Online Dense Point Tracking with Streaming Memory ICCV 2025 On Quantizing Neural Representation for Variable-Rate Video Coding ICLR 2025 Optical Flow Estimation for Tiny Objects: New Problem, Specialized Benchmark, and Bioinspired Scheme IJCAI 2025 Overcoming both Domain Shift and Label Shift for Referring Video Segmentation NAACL 2025 PatchVSR: Breaking Video Diffusion Resolution Limits with Patch-wise Video Super-Resolution CVPR 2025 p-AVAS: Can Physics-Integrated Audio-Visual Modeling Boost Neural Acoustic Synthesis? ICCV 2025 Perceptual Video Compression with Neural Wrapping CVPR 2025 Plug-and-Play Versatile Compressed Video Enhancement CVPR 2025 PNVC: Towards Practical INR-based Video Compression AAAI 2025 PoseTraj: Pose-Aware Trajectory Control in Video Diffusion CVPR 2025 PostCast: Generalizable Postprocessing for Precipitation Nowcasting via Unsupervised Blurriness Modeling ICLR 2025 PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy ACL 2025 Principles of Visual Tokens for Efficient Video Understanding ICCV 2025 Pursuing Temporal-Consistent Video Virtual Try-On via Dynamic Pose Interaction CVPR 2025 PvNeXt: Rethinking Network Design and Temporal Motion for Point Cloud Video Recognition ICLR 2025 Query-centric Audio-Visual Cognition Network for Moment Retrieval, Segmentation and Step-Captioning AAAI 2025 RainyGS: Efficient Rain Synthesis with Physically-Based Gaussian Splatting CVPR 2025 RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Control ICCV 2025