Chain-of-Evidence Multimodal Reasoning for Few-shot Temporal Action Localization

[2504.13460] Chain-of-Evidence Multimodal Reasoning for Few-shot Temporal Action Localization Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computer Vision and Pattern Recognition arXiv:2504.13460 (cs) [Submitted on 18 Apr 2025 ( v1 ), last revised 14 Aug 2026 (this version, v6)] Title: Chain-of-Evidence Multimodal Reasoning for Few-shot Temporal Action Localization Authors: Mengshi Qi , Hongwei Ji , Wulian Yun , Xianlin Zhang , Huadong Ma View a PDF of the paper titled Chain-of-Evidence Multimodal Reasoning for Few-shot Temporal Action Localization, by Mengshi Qi and 4 other authors View PDF HTML (experimental) Abstract: Traditional temporal action localization (TAL) methods rely on large amounts of detailed annotated data, whereas few-shot TAL reduces this dependence by using only a few training samples to identify unseen action categories. However, existing few-shot TAL methods typically focus solely on video-level information, neglecting textual information, which can provide valuable semantic support for the action localization task. To address these issues, in this work, we propose a new few-shot temporal action localization method by Chain-of-Evidence multimodal reasoning to improve localization performance. Specifically, we design a novel few-shot learning framework to capture action commonalities and variations, which includes a semantic-aware text-visual alignment module designed to align the query and support videos at different levels. Meanwhile, to better express the temporal dependencies and causal relationships between actions at the textual level, we design a Chain-of-Evidence (CoE) reasoning method that progressively guides the Vision Language Model (VLM) and Large Language Model (LLM) to generate CoE text descriptions for videos. The generated texts can capture more variance of action than visual features. We conduct extensive experiments on the publicly available ActivityNet1.3, THUMOS14 and our newly collected Human-related Anomaly Localization Dataset. The experimental results demonstrate that our proposed method significantly outperforms existing methods in single-instance and multi-instance scenarios. Our source code and data are available at this https URL . Comments: Accepted by TIP2026 Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2504.13460 [cs.CV] (or arXiv:2504.13460v6 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2504.13460 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Hongwei Ji [ view email ] [v1] Fri, 18 Apr 2025 04:35:35 UTC (2,800 KB) [v2] Wed, 23 Apr 2025 10:12:52 UTC (2,801 KB) [v3] Tue, 6 May 2025 05:00:15 UTC (2,802 KB) [v4] Wed, 17 Dec 2025 10:11:29 UTC (28,559 KB) [v5] Thu, 25 Dec 2025 06:57:15 UTC (28,559 KB) [v6] Fri, 14 Aug 2026 18:21:51 UTC (33,459 KB) Full-text links: Access Paper: View a PDF of the paper titled Chain-of-Evidence Multimodal Reasoning for Few-shot Temporal Action Localization, by Mengshi Qi and 4 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CV < prev | next > new | recent | 2025-04 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• GHR-VLM: Making Zero-Shot Transit Video Analytics Realizable with Grounded Hybrid Reasoning#684536
• GHR-VLM: Making Zero-Shot Transit Video Analytics Realizable with Grounded Hybrid Reasoning#682761
• Action100M: A Large-scale Video Action Dataset#288041
• Beyond Token Importance: Preserving Spatial Scaffolds for Efficient Vision-Language-Action Inference#1132168
• EgoSIS: From Factorized Visual Ego-Transitions to Motion-Canonical Spatial Evidence for UAV Reasoning#987931