Zero-MELO: Test-Time Evidence Calibration with Multimodal LLMs for Zero-Shot Micro-Gesture Recognition

[2608.14854] Zero-MELO: Test-Time Evidence Calibration with Multimodal LLMs for Zero-Shot Micro-Gesture Recognition 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:2608.14854 (cs) [Submitted on 14 Aug 2026] Title: Zero-MELO: Test-Time Evidence Calibration with Multimodal LLMs for Zero-Shot Micro-Gesture Recognition Authors: Chengyan Wang , Hanliang Xie , Yueyi Yang , Haoyu Chen View a PDF of the paper titled Zero-MELO: Test-Time Evidence Calibration with Multimodal LLMs for Zero-Shot Micro-Gesture Recognition, by Chengyan Wang and Hanliang Xie and Yueyi Yang and Haoyu Chen View PDF HTML (experimental) Abstract: While Multimodal Large Language Models (MLLMs) excel in general video understanding, their capability in fine-grained and motion-centric tasks remains limited. This limitation is particularly critical in micro-gesture recognition (MGR), where micro-gestures (MGs) - subtle, short-duration, and spatially localized human movements - serve as key discriminative signals for implicit affective analysis, yet are easily neglected following common prompting practices. Although MGR has been intensively studied by many discriminative approaches, the use of MLLMs for MGR is underexplored, with notably poor performance. We hypothesize that the motion-sensitive representation ability of MLLMs is constrained by their inherent single-pass forward inference, which can be substantially enhanced through carefully designed test-time guidance. Motivated by this, building on our prior findings regarding temporal insensitivity in Video LLMs, we diagnose zero-shot MGR errors in the Negative Log-Likelihood (NLL) space. We observe that MLLMs suffer from two bottlenecks: 1) insufficient localized evidence and 2) severe score biases driven by language and motion-agnostic appearances. Thus, we propose a novel test-time evidence calibration framework that improves both reasoning details and prediction reliability. Specifically, we introduce a tree search mechanism to progressively acquire localized, fine-grained visual evidence, coupled with a test-time calibration module to mitigate score biases. The multi-cue fusion module then integrates evidence from multiple cues without relying on a single cue for final prediction. Our framework achieves mean-class accuracies of 26.84\% on iMiGUE and 22.10\% on MA-52, significantly outperforming the Qwen2.5-VL baseline, which produces 16.15\% and 10.20\%, respectively. The code will be available at this https URL . Comments: Accepted by ACM MM 2026 Subjects: Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2608.14854 [cs.CV] (or arXiv:2608.14854v1 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2608.14854 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Haoyu Chen [ view email ] [v1] Fri, 14 Aug 2026 19:50:31 UTC (20,617 KB) Full-text links: Access Paper: View a PDF of the paper titled Zero-MELO: Test-Time Evidence Calibration with Multimodal LLMs for Zero-Shot Micro-Gesture Recognition, by Chengyan Wang and Hanliang Xie and Yueyi Yang and Haoyu Chen View PDF HTML (experimental) TeX Source view license Current browse context: cs.CV < prev | next > new | recent | 2026-08 Change to browse by: cs 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

• MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios#617829
• RAVEL: Asynchronous Rolling Inference for Flow-Based Vision-Language-Action Models#1119243
• EMGBlend: Heterogeneity-Aware Self-Supervised Pretraining for Gesture and Force Decoding#1061220
• LEVERAGING FOUNDATION MODELS FOR CONTINUOUS SIGN LANGUAGE RECOGNITION#191222
• Attention-Steered Vision-Language Models for Sign Language Translation#1013642