8 papers
GeoWeaver: Grounding Visual Tokens with Geometric Evidence before Scene Reasoning
Deshui Miao, Xingsen Huang, Yameng Gu +3
Spatio-temporal reasoning in vision-language models requires visual representations that preserve physical geometry rather than merely semantic appearance. Recent multimodal models…
RCoT-Seg: Reinforced Chain-of-Thought for Video Reasoning and Segmentation
Junwei Wen, Deshui Miao, Guangming Lu +2
Video Reasoning Segmentation (VRS) aims to segment target objects in videos based on implicit instructions that convey human intent and temporal logic. Existing MLLM-based methods…
Report of the 5th PVUW Challenge: Towards More Diverse Modalities in Pixel-Level Understanding
Chang Liu, Henghui Ding, Nikhila Ravi +40
This report summarizes the objectives, datasets, and top-performing methodologies of the 2026 Pixel-level Video Understanding in the Wild (PVUW) Challenge, hosted at CVPR 2026, whi…
OAMVOS:2nd Report for 5th PVUW MOSE Track
Deshui Miao, Xingsen Huang, Yameng Gu +3
SAM-based dense trackers provide strong short-term mask propagation but remain fragile under long occlusion, fast motion, viewpoint change, and distractors. The problem is especial…
AgentRVOS for MeViS-Text Track of 5th PVUW Challenge: 3rd Method
Deshui Miao, Chao Yang, Chao Tian +4
This report describes a Ref-VOS pipeline centered on Sa2VA and organized with explicit agent roles. The key idea is that Sa2VA should provide the first dense semantic hypothesis, w…
APRVOS: 1st Place Winner of 5th PVUW MeViS-Audio Track
Deshui Miao, Yameng Gu, Chao Yang +3
This report presents an Audio-aware Referring Video Object Segmentation (Ref-VOS) pipeline tailored to the MEVIS\_Audio setting, where the referring expression is provided in spoke…