CVPR Findings2026
B-MoE: A Body-Part-Aware Mixture-of-Experts “All Parts Matter” Approach to Micro-Action Recognition
Nishit Poddar, Aglind Reka, Diana-Laura Borza, Snehashis Majhi, Michal Balazia, Abhijit Das, François Brémond
Abstract
Micro-actions, fleeting and low-amplitude motions, such as glances, nods, or minor posture shifts, carry rich social meaning but remain difficult for current action recognition models to recognize due to their subtlety, short duration, and high inter-class ambiguity. In this paper, we introduce B-MoE, a Body-part-aware Mixture-of-Experts framework designed to explicitly model the structured nature of human motion. In B-MoE, each expert specializes in a distinct body region (head, body, upper limbs, lower limbs), and is based on the lightweight Macro-Micro Motion Encoder (M3E) that captures long-range contextual structure and fine-grained local motion. A cross-attention routing mechanism learns inter-region relationships and dynamically selects the most informative regions for each microaction. B-MoE uses a dual-stream encoder that fuses these region-specific semantic cues with global motion features to jointly capture spatially localized cues and temporally subtle variations that characterize micro-actions. Experiments on three challenging benchmarks (MA-52, SocialGesture, and MPII-GroupInteraction) show consistent state-of-theart gains, with improvements in ambiguous, underrepresented, and low-amplitude classes.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Is Space-Time Attention All You Need for Video Understanding? cites SlowFast Networks for Video Recognition
- Revisiting Skeleton-based Action Recognition cites SlowFast Networks for Video Recognition
- Video Swin Transformer cites Is Space-Time Attention All You Need for Video Understanding?
- Video Swin Transformer cites SlowFast Networks for Video Recognition
Builds on15
- SlowFast Networks for Video RecognitionChristoph Feichtenhofer, Haoqi Fan, Jitendra Malik, Kaiming HeICCV 2019 · 4,104 citations
- Is Space-Time Attention All You Need for Video Understanding?Gedas Bertasius, Heng Wang, Lorenzo TorresaniICML 2021 · 2,927 citations
- Video Swin TransformerZe Liu, Jia Ning, Yue Cao, Yixuan Wei et al.CVPR 2022 · 1,847 citations
- Revisiting Skeleton-based Action RecognitionHaodong Duan, Yue Zhao, Kai Chen, Dahua Lin et al.CVPR 2022 · 752 citations
- From Sparse to Soft Mixtures of ExpertsJoan Puigcerver, Carlos Riquelme Ruiz, Basil Mustafa, Neil HoulsbyICLR 2024 · 264 citations
Related papers
- MMAD: Multi-Label Micro-Action Detection in VideosKun Li, Pengyu Liu, Dan Guo, Fei Wang et al.ICCV 2025 · 21 citations
- Motion Matters: Motion-guided Modulation Network for Skeleton-based Micro-Action RecognitionJihao Gu, Kun Li, Fei Wang, Yanyan Wei et al.ACM MM 2025 · 23 citations
- Spatiotemporal-Untrammelled Mixture of Experts for Multi-Person Motion PredictionZheng Yin, Chengjian Li, Xiangbo Shu, Meiqi Cao et al.AAAI 2026
- MoEG-HOI: Mixture of Expert Groups for One-Stage Hand-Object Interaction Motion Generation with Hand-Finger-Joint Semantic GuidanceHang Xu, Yang Xiao, Changlong Jiang, Haohong Kuang et al.AAAI 2026
- MA-Bench: Towards Fine-grained Micro-Action UnderstandingKun Li, Jihao Gu, Fei Wang, Zhiliang Wu et al.CVPR 2026 · 12 citations
