Overview

Temporal video grounding studies how to identify when a described action, event, or state occurs in a video, often returning one or more time intervals. Methods range from proposal-based models and cross-modal alignment to zero-shot video-language models, query-guided frame selection, and agents that search long videos in stages. Training commonly uses temporal annotations and benchmarks such as QVHighlights, Charades-STA, and ActivityNet-Captions, while newer work explores weak supervision, reinforcement learning, and open-world queries. A central challenge is that fluent answers and broad event recognition do not guarantee precise, faithful evidence localization, especially in long videos or when queries are ambiguous or match multiple moments.

Latest papers

CardsList

180 papers16 papers in the last four weeks, down 33% on the four weeks before. 0.1% of all new papers.

  1. CineMME: From Dialogue Grounding to Narrative Reasoning in Multimodal Video Understanding

    Nov 11, 2026Jin Liu, Dawei Du, Yexiang Liu +7Video-Language Model EvaluationAudio-Visual Understanding

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

    Nov 10, 2026Yuhuan Hong, Yiming Ren, Zhiqiang Lin +7Reasoning SegmentationTemporal Video Grounding

  3. AgenticConflictLens: From Long Traffic Videos to Verifiable Conflict Evidence

    Nov 10, 2026Boshra Khalili, Sonia Moshfeghi, Jinwoo Jang +1Intelligent Transportation SystemsProactive Video Understanding

  4. ABRR: Transforming Temporal Sentence Grounding with Wasserstein-Adaptive Refinement and Precision Ranking

    Nov 9, 2026Xiang Fang, Wanlong Fang, Junhao Dong +1Temporal Video Grounding

  5. Grounding in the Dark: Text-Only Training for Zero-Shot Video Temporal Localization

    Nov 4, 2026Divyanshu Mishra, Sabine Sternig, Rakshith Shetty +1Temporal Video GroundingModality Gap in VLMs

  6. EP-LVMQA: Evidence-Preserving Coarse-to-Fine Localization for Low-Quality Long Video Moment Question Answering

    Nov 3, 2026Guoning Chen, Zhexun Hu, Yifan Wei +3Video Question AnsweringLong-Video QA

  7. FinishStrong: Learning to End Well after Imperfect Start in Video Temporal Grounding

    Nov 1, 2026Yuda Zou, Boxiang Zhou, Xin Zhou +5Temporal Video Grounding

  8. Hierarchical Step Decomposition for Training-free Online Video Step Grounding

    Oct 29, 2026Long Zhou, Luca Zanella, Paolo Rota +2Temporal Video GroundingStreaming Video Understanding

  9. DTP-OPSD: Reinforcement Learning with Distractor-Aware Temporal-Privilege On-Policy Self-Distillation for Temporal Video Grounding

    Oct 29, 2026Zhaoyu Chen, Yongwei NieTemporal Video GroundingRL for Video Reasoning

  10. Tempo-Zero: Recursive Self-Play in Executable Worlds for Video Reasoning

    Oct 23, 2026Jingmin Zhu, Yanyan Zou, Xiuyu Li +10Video ReasoningSelf-Play RL

  11. Organizing Temporal Evidence in Hyperbolic Space for Video Moment Retrieval

    Oct 23, 2026Mengnan Liu, Sanping Zhou, Kun Xia +3Video Moment RetrievalTemporal Video Grounding

  12. RVG-Bench: A Benchmark for Reasoning-Driven Audio-Visual Temporal Grounding

    Oct 23, 2026Yue Feng, Boshen Xu, Zihao Yue +5Temporal Video GroundingMultimodal Grounding

  13. EvaOmni: An Evidence-Grounded Benchmark for Audio-Visual Reasoning

    Oct 20, 2026Xiaoxing Hu, Wenxi Yao, Chaoyuan Shi +17Audio-Visual UnderstandingAudio-Visual QA

  14. OmniGround: Strengthening Omni-Modal Temporal Grounding via Attention-Consistency Training

    Oct 19, 2026Zixuan Chen, Depeng Wang, Hao Lin +5Temporal Video GroundingMultimodal Grounding

  15. DiffGround: Semantic Difference-Guided Zero-Shot Video Question Grounding

    Oct 18, 2026Cheng-Han Lee, Amir Salimi, Hsiang-Wei Huang +3Temporal Video GroundingVideo Question Answering

  16. SuperClip Pyramid for Video Temporal Grounding

    Oct 17, 2026Sanghyeok Lee, Juyeon Ko, Joonmyung Choi +4Temporal Video GroundingVideo Moment Retrieval

  17. HAPACT: A Benchmark For Human-Centric Physical Impact Localization in Movies

    Oct 16, 2026Youngrae Kim, Yejin Jang, Eunho Kim +4Physical Reasoning in VideoTemporal Video Grounding

  18. Event-STVG: Spatio-Temporal Video Grounding for Long-Form Event Reasoning

    Oct 15, 2026Yizhe Zhang, Xujia Wang, Songqi Tang +10Video ReasoningTemporal Video Grounding

  19. Where, How, and When: Query-Guided Grounding for Video Understanding

    Oct 15, 2026Yogesh KumarVideo Moment RetrievalTemporal Video Grounding

  20. OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding

    Oct 13, 2026Xuyang Liu, Shihao Wang, Xinyu Wei +5Video-Language Model EvaluationMultimodal Grounding

  21. VideoSlate: Stateful Commit Control for Temporally Grounded Agentic Video Reasoning

    Oct 12, 2026Shuo Zheng, Yuanjie Dang, Peng Chen +4Temporal Video GroundingVideo Question Answering

  22. EventLens: Event-Structure Reinforcement Learning for Video Understanding

    Oct 12, 2026Guowen Zhang, Boshen Xu, Zihao Yue +6Video UnderstandingTemporal Video Understanding