GMoT: Gated Motion-Aware Tokenization for Fine-Grained Micro-Gesture Video Reasoning with Multimodal LLMs

• URL: http://arxiv.org/abs/2607.16322v1
• Date: Wed, 15 Jul 2026 09:37:58 GMT
• Title: GMoT: Gated Motion-Aware Tokenization for Fine-Grained Micro-Gesture Video Reasoning with Multimodal LLMs
• Abstract summary: GMoT is a Gated Motion-Aware Tokenization module that distills sparse kinematic evidence into a compact sequence prior to temporal modeling.<n>To transition from simple classification to evidence-grounded reasoning, we introduce a progressive reward-guided policy refinement paradigm.<n>Our GMoT-augmented model improves in-domain accuracy, retains clear gains under label-preserving corruptions, and improves accuracy-oriented cross-domain transfer.
• Score: 38.593314566875755
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Micro-gesture recognition demands the detection of fleeting, spatially localized movements that are frequently overwhelmed by dominant static appearances and background noise. While Multimodal Large Language Models (MLLMs) excel at general video understanding, they inherently struggle with subtle kinematics and often rely on static posture priors. To this end, we propose GMoT, a Gated Motion-Aware Tokenization module that explicitly distills sparse kinematic evidence into a compact sequence prior to temporal modeling. GMoT dynamically spotlights action-relevant regions via spatially weighted pooling, extracts adjacent-frame temporal differencing to capture precise motion energy, and adaptively fuses these cues into the visual stream using a conservatively initialized semantic gate. To transition from simple classification to evidence-grounded reasoning, we further introduce a progressive reward-guided policy refinement paradigm, supported by a semi-supervised annotation pipeline that generates anatomically focused captions. Beyond achieving the best Top-1 accuracy among the compared methods on iMiGUE (67.32\%) and SMG (73.11\%), improving the Qwen3-VL-8B baseline by +6.80 and +3.11 points, our framework introduces Body-Region Grounding (BRG) Recall as an anatomical-grounding proxy conditioned on correct predictions, together with an overlapping-label cross-domain transfer protocol between iMiGUE and SMG. Extensive evaluations demonstrate that our GMoT-augmented model improves in-domain accuracy, retains clear gains under label-preserving corruptions, and improves accuracy-oriented cross-domain transfer under explicit small-split caveats while maintaining high anatomical grounding in its generated rationales.

Related papers

• Large-Small Model Collaboration for Zero-Shot Surgical Phase Recognition [45.191945465591374]
  Task-specific lightweight models for surgical phase recognition excel at capturing temporal dynamics but generalize poorly under domain shift.<n>We propose textbfLarge-textbfSmall textbfTemporal adaptation (textbfLaST), a novel large-small collaborative framework that enables zero-shot adaptation to unseen clinical domains.
  arXiv  Detail & Related papers  (2026-08-24T07:06:52Z)
• COMET: Contrastive Motion-Enhanced Temporal Reasoning for Video Multimodal Large Language Models [15.39037309359101]
  Video multimodal large language models have advanced significantly, yet fine-grained motion-temporal understanding remains fragile.<n>We propose COMET, a temporally grounded framework that systematically strengthens video MLLMs through explicit temporal representation.<n>For optimization, COMET combines temporal prior distillation with a forward-reverse TC-GRPO stage that turns temporal order into a direct learning signal.
  arXiv  Detail & Related papers  (2026-08-21T12:28:36Z)
• DyG$^2$T: Modeling Object Dynamics with 3D Gaussian Temporal-Spatial Particle Graph Transformer [86.4618122245946]
  DyG$2$T is a dynamics modeling framework that infers object motion trajectories by spatially completing and temporally discriminating Key Point representations.<n>Experiments on both synthetic and real-world datasets demonstrate that DyG$2$T achieves accurate dynamics modeling and reasoning.
  arXiv  Detail & Related papers  (2026-08-19T03:44:28Z)
• TVTA: Trajectory-Aware Viseme-Guided Temporal Aggregation for Event-Based Lip Reading [17.895146965920592]
  Event-based lip reading has emerged as a promising direction for visual speech recognition.<n>We propose a temporally enhanced framework for event-based lip reading.
  arXiv  Detail & Related papers  (2026-07-09T08:33:21Z)
• Partial Skeleton Visibility for Action Recognition: A Constrained Field-of-View Approach [60.596944437968524]
  PartialVisGraph is a novel framework for robust skeleton-based action recognition under constrained field-of-view.<n>It consistently achieves state-of-the-art accuracy under partial visibility, with gains of up to 68.8% on subsets with severe FoV restrictions.<n>Our approach offers a principled and practical pathway toward deployable skeleton-based action understanding in unconstrained environments.
  arXiv  Detail & Related papers  (2026-07-01T10:03:11Z)
• AnchorRefine: Synergy-Manipulation Based on Trajectory Anchor and Residual Refinement for Vision-Language-Action Models [60.04879435087352]
  Vision-language-action (VLA) policies generate actions within a single unified space.<n>We propose AnchorRefine, a hierarchical framework that factorizes VLA action modeling into trajectory anchor and residual refinement.<n> Experiments on LIBERO, CALVIN, and real-robot tasks demonstrate that AnchorRefine consistently improves both regression-based and diffusion-based VLA backbones.
  arXiv  Detail & Related papers  (2026-04-20T04:25:24Z)
• Thinking with Images as Continuous Actions: Numerical Visual Chain-of-Thought [55.65577137924979]
  We propose a framework that enables MLLMs to reason over images using continuous numerical coordinates.<n> NV-CoT expands the MLLM action space from discrete vocabulary tokens to a continuous Euclidean space.<n>Experiments on three benchmarks demonstrate that NV-CoT significantly improves localization precision and final answer accuracy.
  arXiv  Detail & Related papers  (2026-02-27T12:04:07Z)
• SGHA-Attack: Semantic-Guided Hierarchical Alignment for Transferable Targeted Attacks on Vision-Language Models [73.19044613922911]
  Large vision-language models (VLMs) are vulnerable to transfer-based adversarial perturbations.<n>We propose SGHA-Attack, a framework that adopts multiple target references and enforces intermediate-layer consistency.<n>Experiments on open-source and commercial black-box VLMs show that SGHA-Attack achieves stronger targeted transferability than prior methods.
  arXiv  Detail & Related papers  (2026-02-02T03:10:41Z)
• From Tokens to Nodes: Semantic-Guided Motion Control for Dynamic 3D Gaussian Splatting [26.57713792657793]
  We propose a motion-adaptive framework that aligns control density with motion complexity.<n>We show significant improvements in reconstruction quality and efficiency over existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-10-03T05:33:58Z)
• Dual Conditioned Motion Diffusion for Pose-Based Video Anomaly Detection [12.100563798908777]
  Video Anomaly Detection (VAD) is essential for computer vision research.<n>Existing VAD methods utilize either reconstruction-based or prediction-based frameworks.<n>We address pose-based video anomaly detection and introduce a novel framework called Dual Conditioned Motion Diffusion.
  arXiv  Detail & Related papers  (2024-12-23T01:31:39Z)
• Calibrating Undisciplined Over-Smoothing in Transformer for Weakly Supervised Semantic Segmentation [51.14107156747967]
  Weakly supervised semantic segmentation (WSSS) has attracted considerable attention because it requires fewer annotations than fully supervised approaches.<n>We propose an Adaptive Re-Activation Mechanism (AReAM) to control deep-level attention to undisciplined over-smoothing.<n>AReAM substantially improves segmentation performance compared with existing WSSS methods, reducing noise while sharpening focus on relevant semantic regions.
  arXiv  Detail & Related papers  (2023-05-04T19:11:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.