Research map / Architectures and efficiency / Spiking networks
OmniEvent: Unified Event Representation Learning
Weiqi Yan, Chenlu Lin, Youbiao Wang, Zhipeng Cai, Xiuhong Lin, Yangyang Shi, Weiquan Liu, Yu Zang
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 |
|---|---|---|---|
| remove one or more components (SFCA branches, STA, statistical features) (ablation) | OmniEvent · CIFAR10-DVS | top-1 accuracy (%): 74.7 to 82.0 when ablated -> 85.2 full | Improved |
| use decoupled spatial, temporal and spatio-temporal branches instead of EP2T weighted fusion | EP2T · CIFAR10-DVS | top-1 accuracy (%): 79.6 -> 85.2 | Improved |
| use space-filling-curve aggregation instead of KNN | EP2T · CIFAR10-DVS | GPU memory (MB): 4650 -> 3146 | Improved |
| use space-filling-curve aggregation instead of KNN | EP2T · CIFAR10-DVS | inference time (ms): 42.8 -> 36.6 | Improved |
| use OmniEvent instead of EST | EST · CIFAR10-DVS | inference time (ms): 6.3 -> 36.6 | Hurt |
| use OmniEvent representation for event-to-point-cloud registration | EP2T · MVSEC E2P | RE (deg): 3.606 -> 1.146 | Improved |
| use OmniEvent on VECtor registration translation error | TORE · VECtor E2P | TE (m): 7.254 -> 7.201 | No clear effect |
| use OmniEvent in optical flow on flying3 | M-LSTM+EVFlowNet · MVSEC indoor flying3 | AEE: 1.08 -> 1.15 | Hurt |
Closest papers by meaning
- EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Vision (AAAI 2025 · similarity 0.88)
- End-to-End Learning of Representations for Asynchronous Event-Based Data (ICCV 2019 · similarity 0.88)
- Rethinking Efficient and Effective Point-Based Networks for Event Camera Classification and Regression (TPAMI 2025 · similarity 0.88)
- Efficient Event Camera Data Pretraining with Adaptive Prompt Fusion (ICCV 2025 · similarity 0.87)
- PASS: Path-selective State Space Model for Event-based Recognition (NeurIPS 2025 · similarity 0.87)
- E2HQV: High-Quality Video Generation from Event Camera via Theory-Inspired Model-Aided Deep Learning (AAAI 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.
