cs.CVNov 10, 2026

The Target Is a Predicate: Predicate-State Grounding for Semantic-Level Video Reasoning Segmentation

Authors: Yuhuan Hong, Yiming Ren, Zhiqiang Lin, Feize Wu, Xingyun Liu, Yitong Xie, Lei Zhou, Lisheng Wu, 

Organizations: Tsinghua University · Peking University · Sun Yat-sen University · Yinwang intelligent Technology Co., Ltd

Abstract

In this paper, we introduce Predicate-State Video Reasoning Segmentation (PS-VRS), where a query defines a dynamic predicate P(o,t)P(o,t) over objects and time rather than a fixed object identity. Existing methods typically treat the target as permanently active once identified, leading to over-emission of masks during vacant intervals and failure to handle target switching. To address this, we construct PS-Bench, a large-scale benchmark with 2,077 videos and 16,250 queries annotated with explicit active/vacant predicate states, temporal intervals, and pixel masks. We further propose Predicate-State Grounding (PSG), a State-Bind-Emit pipeline that: (1) predicts [ACTIVE]/[VACANT] state tokens; (2) aligns them to video frames via dense cross-modal similarity; and (3) emits masks via SAM2 only for active states. Experiments show that PSG outperforms existing baselines by +9.32 J&F on PS-Bench and significantly reduces false-positive mask emissions. Our results demonstrate the effectiveness of explicit predicate-state modeling for video reasoning segmentation with dynamic visual witnesses.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Beyond Token Representations: Explicit Visual Object Grounding for Video Reasoning Segmentation

    Nov 3, 2026Jun Huang, Junyang Zhang, Zijie Yue +3Video ReasoningVideo Object Segmentation

  2. Learning to Reason with Persistent Object States for Video Instance Segmentation

    Sep 28, 2026Yongxue Xu, Boxue Yang, Ziqian Liu +3Video Object SegmentationInstance Segmentation

  3. Think Visually Across Space and Time: Grounded Reasoning for Video Segmentation

    Oct 18, 2026Junwei Wen, Deshui Miao, Guangming Lu +3Temporal Reasoning in VLMsVideo Object Segmentation