Research map / Video / Action recognition
DailyDVS-200: A Comprehensive Benchmark Dataset for Event-Based Action Recognition
Qi Wang, Zhou Xu, Yuming Lin, Jingtao Ye, Hongsheng Li, Guangming Zhu, Syed Afaq Ali Shah, Mohammed Bennamoun, Liang Zhang
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 |
|---|---|---|---|
| use a shorter frame time step (0.5s to 0.125s) for event frames, gap 0 (ablation) | SlowFast · DailyDVS-200 | top-1 accuracy (%): 41.49 -> 64.09 | Improved |
| increase frame gap from 0 to 4 (0.5s step) (ablation) | SlowFast · DailyDVS-200 | top-1 accuracy (%): 41.49 -> 24.55 | Hurt |
| use moving camera instead of static camera in test group | Swin-T · DailyDVS-200 camera motion groups | top-1 accuracy (%): 58.05 -> 27.84 | Hurt |
| micro-action range instead of full-body range in test group | Swin-T · DailyDVS-200 action range groups | top-1 accuracy (%): 59.24 -> 34.59 | Hurt |
| front lighting instead of side lighting in test group | Swin-T · DailyDVS-200 illumination groups | top-1 accuracy (%): 53.39 -> 39.11 | Hurt |
| increase proportion of dynamic-camera data in training (ablation) | TSM · DailyDVS-200 moving and static groups | accuracy | Hurt |
| use token-based Swin-T instead of frame-based SlowFast under camera motion | Event action recognition · DailyDVS-200 moving camera group | top-1 accuracy (%): 21.05 -> 27.84 | Improved |
| use token-based Swin-T instead of best frame-based method | Event action recognition · DailyDVS-200 cross-subject | top-1 accuracy (%): 41.49 -> 48.06 | Improved |
Closest papers by meaning
- Action Recognition and Benchmark Using Event Cameras (TPAMI 2023 · similarity 0.90)
- EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Vision (AAAI 2025 · similarity 0.90)
- HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors (AAAI 2024 · similarity 0.88)
- PASS: Path-selective State Space Model for Event-based Recognition (NeurIPS 2025 · similarity 0.88)
- SpikePoint: An Efficient Point-based Spiking Neural Network for Event Cameras Action Recognition (ICLR 2024 · similarity 0.88)
- ExACT: Language-guided Conceptual Reasoning and Uncertainty Estimation for Event-based Action Recognition and More (CVPR 2024 · similarity 0.86)
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.
