Spatial-Temporal Decoupled Adapter for Micro-gesture Online Recognition

• URL: http://arxiv.org/abs/2606.07355v1
• Date: Fri, 05 Jun 2026 15:03:38 GMT
• Title: Spatial-Temporal Decoupled Adapter for Micro-gesture Online Recognition
• Abstract summary: We propose a Spatial-Temporal Decoupled Adapter that decomposes video adaptation into independent temporal and spatial branches.<n>Our method achieves an F1 score of 0.43808, ranking 1st in Track 2 of the 4th EI-Mi-JCAI Challenge.
• Score: 23.516828286378836
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Micro-gesture online recognition aims to temporally localize and classify subtle gestures in untrimmed videos. Owing to their extremely short duration, low motion amplitude, and ambiguous visual cues, capturing discriminative spatiotemporal representations remains highly challenging. Existing parameter-efficient adapters typically employ a single branch to model spatial and temporal cues jointly, which may fail to capture the fine-grained patterns of micro-gestures. To address this limitation, we propose a Spatial-Temporal Decoupled Adapter that decomposes video adaptation into independent temporal and spatial branches via lightweight depthwise convolutions. In addition, to address the long-tail distribution problem in the benchmark dataset, we introduce Adaptive Soft Balanced Augmentation, which dynamically allocates augmentation intensity based on class rarity and learning difficulty, without manual thresholds. Our method achieves an F1 score of 0.43808, ranking 1st in Track 2 of the 4th EI-MiGA-IJCAI Challenge.

Related papers

• RhyMix: A Lightweight Adaptive Multi-Rhythm Network for Long-Term Time Series Forecasting [0.19116784879310025]
  We introduce RhyMix, a hybrid neural architecture designed around a parallel dual-path modeling paradigm with adaptive gating mechanisms.<n>RhyMix achieves state-of-the-art performance on 10 of 12 datasets for long-term forecasting.
  arXiv  Detail & Related papers  (2026-07-09T08:29:38Z)
• Motion Reinforces Appearance: RGB-Skeleton Gated Residual Fusion for Micro-Gesture Online Recognition [18.736764781779208]
  We propose DyFADet+, which extends DyFADet into a dual-stream RGB-skeleton framework.<n>On the SMG dataset, our method achieves an F1 score of 40.88, ranking 2nd in the Micro-gesture Online Recognition track.
  arXiv  Detail & Related papers  (2026-06-10T04:12:36Z)
• FlowLong: Inference-time Long Video Generation via Manifold-constrained Tweedie Matching [68.01498128172214]
  We propose a novel but simple inference-time approach for long video generation that is architecture-agnostic and requires no additional training.<n>Our method generates long videos via overlapping sliding windows, where predicted clean samples from adjacent windows are blended via emphTweedie matching to enforce both textbfmanifold constraint and temporal consistency across overlap regions.<n>Our method generates videos several times longer than the native window length while outperforming both training-free and autoregressive baselines in temporal consistency and visual quality, and further extends to audio-video joint generation and text-to-3DGS without any
  arXiv  Detail & Related papers  (2026-05-20T08:55:37Z)
• Local Spatiotemporal Convolutional Network for Robust Gait Recognition [7.0676119183443395]
  Gait recognition is a promising biometric technology that identifies individuals through their unique walking patterns.<n>Existing approaches rely on either static appearance features extracted from individual silhouette frames or employ complex sequential models.<n>We propose a Local Stemporal Convolutional Network (LSTCN), a structurally simple yet highly effective dual-branch architecture that endows standard two-dimensional convolutional networks with the capacity to extract temporal information.
  arXiv  Detail & Related papers  (2026-05-14T08:28:49Z)
• EchoTorrent: Towards Swift, Sustained, and Streaming Multi-Modal Video Generation [8.795438456031512]
  Multi-modal generation models have achieved high visual quality, but their prohibitive latency and limited temporal stability hinder real-time deployment.<n> Streaming inference exacerbates these issues, leading to pronounced multimodal ambiguities, such as blurring, temporal drift, and lip dechronization.<n>We propose EchoTorrent, a novel novel with a fourfold schema: Multi-Teacher Training fine-tunes a pre-trained model on distinct preference domains; Adaptive DMD (ACCDMD) calibrates the audio CFG degradation errors in phased via a schedule; Long Hybrid Tail, which enforces alignment exclusively on tail frames during long-horizon self-roll
  arXiv  Detail & Related papers  (2026-02-14T08:32:38Z)
• Lightweight Test-Time Adaptation for EMG-Based Gesture Recognition [2.414036142474149]
  We propose a lightweight framework for Test-Time Adaptation (TTA) using a Temporal Convolutional Network (TCN) backbone.<n>We introduce three deployment-ready strategies: causal adaptive batch normalization for real-time statistical alignment; (ii) a Gaussian Mixture Model (GMM) alignment with experience replay to prevent forgetting; and (iii) meta-learning for rapid, few-shot calibration.<n>Our results show that experience-replay updates yield superior stability under limited data, while meta-learning achieves competitive performance in one- and two-shot regimes.
  arXiv  Detail & Related papers  (2026-01-07T18:48:31Z)
• What You Have is What You Track: Adaptive and Robust Multimodal Tracking [72.92244578461869]
  We present the first comprehensive study on tracker performance with temporally incomplete multimodal data.<n>Our model achieves SOTA performance across 9 benchmarks, excelling in both conventional complete and missing modality settings.
  arXiv  Detail & Related papers  (2025-07-08T11:40:21Z)
• SampleAttention: Near-Lossless Acceleration of Long Context LLM Inference with Adaptive Structured Sparse Attention [53.4441894198495]
  Large language models (LLMs) now support extremely long context windows.<n>The quadratic complexity of vanilla attention results in significantly long Time-to-First-Token (TTFT) latency.<n>We propose SampleAttention, an adaptive structured and near-lossless sparse attention.
  arXiv  Detail & Related papers  (2024-06-17T11:05:15Z)
• D$^2$ST-Adapter: Disentangled-and-Deformable Spatio-Temporal Adapter for Few-shot Action Recognition [64.153799533257]
  D$2$ST-Adapter is structured with an internal dual-pathway architecture that enables built-in disentangled encoding of spatial and temporal features.<n>Our method is particularly well-suited to challenging scenarios where temporal dynamics are critical for action recognition.
  arXiv  Detail & Related papers  (2023-12-03T15:40:10Z)
• Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online Adaptation [87.85851771425325]
  We consider a new problem of adapting a human mesh reconstruction model to out-of-domain streaming videos. We tackle this problem through online adaptation, gradually correcting the model bias during testing. We propose the Dynamic Bilevel Online Adaptation algorithm (DynaBOA)
  arXiv  Detail & Related papers  (2021-11-07T07:23:24Z)
• Temporal-Spatial Neural Filter: Direction Informed End-to-End Multi-channel Target Speech Separation [66.46123655365113]
  Target speech separation refers to extracting the target speaker's speech from mixed signals. Two main challenges are the complex acoustic environment and the real-time processing requirement. We propose a temporal-spatial neural filter, which directly estimates the target speech waveform from multi-speaker mixture.
  arXiv  Detail & Related papers  (2020-01-02T11:12:50Z)

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.