Research map / Video / Action recognition
Seeing Motion Through Polarity for Event-based Action Recognition
Meiqi Cao, Jiachao Zhang, Xin Jiang, Rui Yan, Yazhou Yao, Zechao Li, Xiangbo Shu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add POKER (PMC + PMR) to EventBind with stacked frames | EventBind · SeAct | top-1 accuracy (%): 67.24 -> 69.82 | Improved |
| add POKER to EventBind with reconstructed frames | EventBind · THUE-ACT-50-CHL | top-1 accuracy (%): 61.14 -> 63.72 | Improved |
| add POKER to EventBind with reconstructed frames on DVS Action | EventBind · DVS Action | top-1 accuracy (%): 98.24 -> 99.60 | Improved |
| add Polarity Motion Capturer (PMC) (ablation) | EventBind · SeAct | top-1 accuracy (%): 74.13 -> 75.00 | Improved |
| add Polarity Motion Capturer (PMC) (ablation) | EventBind · THUE-ACT-50-CHL | top-1 accuracy (%): 61.14 -> 62.24 | Improved |
| add Polarity Motion Reasoner (PMR) on top of PMC (ablation) | EventBind + PMC · SeAct | top-1 accuracy (%): 75.00 -> 76.72 | Improved |
| add PMR on top of PMC (ablation) | EventBind + PMC · THUE-ACT-50-CHL | top-1 accuracy (%): 62.24 -> 63.72 | Improved |
| use learnable router fusion instead of concatenation in PMC (ablation) | PMC · THUE-ACT-50-CHL | accuracy (%): 61.51 -> 63.72 | Improved |
| use learnable router fusion instead of element-wise addition (ablation) | PMC · THUE-ACT-50-CHL | accuracy (%): 63.35 -> 63.72 | Improved |
| use polarity alignment loss instead of standard contrastive loss (ablation) | POKER · THUE-ACT-50-CHL | accuracy (%): 62.62 -> 63.72 | Improved |
| use Gemini-2.5-pro rather than Qwen3-VL-30B as MLLM in PMR (ablation) | PMR · SeAct | top-1 accuracy (%): 75.00 -> 76.72 | Improved |
| use general-purpose MLLMs zero-shot instead of polarity-guided pipeline (ablation) | MLLMs · DVS Action zero-shot | top-1 accuracy (%): 99.6 vs 51.7 (GPT-4o-mini) | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- EventMamba — EventMamba: Enhancing Spatio-Temporal Locality with State Space Models for Event-Based Video Reconstruction (AAAI 2025) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- ExACT: Language-guided Conceptual Reasoning and Uncertainty Estimation for Event-based Action Recognition and More (CVPR 2024 · similarity 0.85)
- Disentangled Concepts Speak Louder Than Words: Explainable Video Action Recognition (NeurIPS 2025 · similarity 0.85)
- EventPrune: Cascaded Event-Assisted Token Pruning for Efficient First-Person Dynamic Spatial Reasoning (NeurIPS 2026 · similarity 0.84)
- HuMoCon: Concept Discovery for Human Motion Understanding (CVPR 2025 · similarity 0.84)
- Talk2Event: Grounded Understanding of Dynamic Scenes from Event Cameras (NeurIPS 2025 · similarity 0.84)
- Building a Multi-modal Spatiotemporal Expert for Zero-shot Action Recognition with CLIP (AAAI 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
