Research map / Vision-language and multimodal / CLIP and zero-shot
EventBind: Learning a Unified Representation to Bind Them All for Event-based Open-world Understanding
jiazhou zhou, Xu Zheng, Yuanhuiyi Lyu, Lin Wang
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 HTCA module (ablation) | EventBind · N-Caltech101 | top-1 accuracy (%): 50.40 -> 92.54 | Improved |
| add hybrid text prompts (ablation) | EventBind · N-Caltech101 | top-1 accuracy (%): 92.54 -> 93.40 | Improved |
| add proposed event encoder (ablation) | EventBind · N-Caltech101 | top-1 accuracy (%): 93.40 -> 94.08 | Improved |
| add event prompts and cross-frame temporal modeling (ablation) | event encoder · N-Caltech101 | top-1 accuracy (%): 90.40 -> 94.08 | Improved |
| add semantic consistency loss when image input available (ablation) | HTCA · N-Caltech101 | top-1 accuracy (%): 93.11 -> 94.08 | Improved |
| fine-tune CLIP image encoder rather than freezing it (ablation) | event encoder · N-Caltech101 | top-1 accuracy (%): 86.69 -> 94.08 | Improved |
| use RGB event frames instead of gray-scale (ablation) | event representation · N-Caltech101 | top-1 accuracy (%): 92.18 -> 94.08 | Improved |
| add image and event content prompts (ablation) | text encoder · N-Caltech101 | top-1 accuracy (%): 91.96 -> 94.08 | Improved |
| increase event prompt length from 4 to 16 (ablation) | event encoder · N-Caltech101 | top-1 accuracy (%): 93.27 -> 94.08 | Improved |
| use EventBind (ViT-L-14) on N-ImageNet fine-tuning vs smaller backbones | EventBind · N-ImageNet fine-tuning | top-1 accuracy (%): 42.94 (ViT-B-32) -> 63.54 (ViT-L-14) | Improved |
| use EventBind ViT-B-16 instead of EventCLIP ViT-L-14 on N-Caltech101 for efficiency | EventBind · N-Caltech101 | top-1 accuracy (%): 93.57 -> 94.08 with 635MB vs 890MB | Improved |
Closest papers by meaning
- EventGPT: Event Stream Understanding with Multimodal Large Language Models (CVPR 2025 · similarity 0.90)
- OpenESS: Event-based Semantic Scene Understanding with Open Vocabularies (CVPR 2024 · similarity 0.88)
- EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Vision (AAAI 2025 · similarity 0.87)
- LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos (CVPR 2025 · similarity 0.87)
- RE-VLM: Event-Augmented Vision-Language Model for Scene Understanding (CVPR 2026 · similarity 0.87)
- EventLens: Event-Structure Reinforcement Learning for Video Understanding (NeurIPS 2026 · 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.
