Hugging Face Trending Papers

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

In this paper, we introduce Predicate-State Video Reasoning Segmentation (PS-VRS), where a query defines a dynamic predicate $P(o,t)$ 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.

arXiv Computer Vision
6d ago

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

arXiv:2611. 13785v1 Announce Type: new Abstract: In this paper, we introduce Predicate-State Video Reasoning Segmentation (PS-VRS), where a query defines a dynamic predicate $P(o,t)$ over objects and time rather than a fixed object identity.

By Yuhuan Hong, Yiming Ren, Zhiqiang Lin, Feize Wu, Xingyun Liu, Yitong Xie, Lei Zhou, Lisheng Wu, Junjie Wang, Yujiu Yang
Hugging Face Trending Papers
Aug 19

StateTrace: An Object-Centric Framework for Hidden-State Spatiotemporal Reasoning in Long Videos

StateTrace introduces an object‑centric framework that equips Video Language Models with a spatiotemporal state memory, enabling explicit reasoning about objects that become invisible in long videos. By organizing trajectories, inter‑object relations, and state‑transition events, the system retrieves relevant state‑evolution paths and converts them into concise reasoning cues. Experiments show that StateTrace consistently boosts performance on public benchmarks and the newly proposed HSR‑Bench, raising VideoLLaMA3’s score from 39.6 to 64.2.

arXiv Computer Vision
Aug 26

RT-NeuS: Towards Real-Time Neuro-Symbolic Video Understanding via Adaptive Temporal Verification

RT-NeuS is a neuro‑symbolic framework for long‑form video question answering that retains the accuracy and formal guarantees of temporal‑logic‑guided methods while dramatically reducing inference latency. It achieves this by using coarse‑to‑fine adaptive sampling to focus on query‑relevant frames and batched proposition detection with KV‑cache reuse, enabling all propositions to be evaluated in a single forward pass. Experiments on LongVideoBench, Video‑MME, and MLVU show up to a 13× speed‑up on an NVIDIA H200 GPU while matching or surpassing prior neuro‑symbolic accuracy.

By Shawn Liang, Sahil Shah, Chengwei Zhou, S P Sharan, Harsh Goel, Arnab Sanyal, Sandeep Chinchali, Gourav Datta
arXiv AI
Aug 25

VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting

VisionCoach is an input‑adaptive reinforcement learning framework that enhances spatio‑temporal grounding in video reasoning by using visual prompting during training. The system selectively applies visual prompts to challenging inputs, amplifying question‑relevant evidence and suppressing distractors, and then internalizes these improvements through self‑distillation so that inference can be performed on raw videos without prompts. Experiments on multiple benchmarks (V‑STAR, VideoMME, World‑Sense, VideoMMMU, PerceptionTest, and Charades‑STA) show that VisionCoach achieves state‑of‑the‑art performance while maintaining a single efficient inference pathway.

By Daeun Lee, Shoubin Yu, Yue Zhang, Mohit Bansal
arXiv Computer Vision
Sep 25

MoVISA: Multi-Token Reasoning for Video Object Segmentation

MoVISA introduces Multi-Token Reasoning for Video Object Segmentation, using multiple segmentation tokens (e.g., SEG0, SEG1) instead of a single token to better localize multiple objects over time. This approach enhances fine-grained alignment between language prompts and spatio-temporal mask predictions, leading to improved performance and interpretability. On benchmarks such as MeViS, DAVIS17, ReVOS, and Ref-Youtube-VOS, MoVISA achieves significant gains, notably a 13.2% J and F improvement on MeViS and an 8.4% J and F improvement on ReVOS.

By Ruining Zhao, Ho Kei Cheng, Alexander G Schwing
arXiv Computer Vision
Oct 26

SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction

SetCon reformulates open-ended referring segmentation as set-level concept prediction, using LVLM-generated natural-language concepts instead of segmentation-specific tokens. It employs a hierarchical semantic decomposition that first predicts a shared set-level concept and then refines it into fine-grained concept groups aligned with target subsets. The method, supported by a two-stage annotation pipeline adding hierarchical semantic supervision, achieves state-of-the-art results on multiple image and video benchmarks, with performance gains increasing as the number of referred targets grows.

By Zhixiong Zhang, Yizhuo Li, Shuangrui Ding, Yuhang Zang, Shengyuan Ding, Long Xing, Yibin Wang, Qiaosheng Zhang, Jiaqi Wang
arXiv Computer Vision
Sep 23

TEMPURA: Temporal Event Masked Prediction and Understanding for Reasoning in Action

arXiv:2505.01583v2 Announce Type: replace Abstract: Understanding causal event relationships and achieving fine-grained temporal grounding in videos remain challenging for vision-language models (VLM...

By Jen-Hao Cheng, Yi-Hao Peng, Huapeng Zhou, Vivian Wang, Huayu Wang, Hsiang-Wei Huang, Wenhao Chai, Hou-I Liu, Kuang-Ming Chen, Cheng-Yen Yang, Yi-Ling Chen, Vibhav Vineet, Qin Cai, Jenq-Neng Hwang