Research map / Detection and segmentation / CNN features
Rethinking Scale-Aware Temporal Encoding for Event-based Object Detection
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Studies scale-aware temporal encoding for event-camera object detection, targeting temporal modeling at early feature stages rather than only high-level features.
Problem
Event-based object detection struggles to model the temporal dynamics of event streams; most existing methods apply temporal modules only to high-level features, limiting early-stage temporal modeling.
Approach
Rethinks temporal encoding for event detection so that temporal modeling is scale-aware and applied across feature scales, including early stages; the abstract is truncated so the specific mechanism is not stated.
Closest papers by meaning
- FlexEvent: Towards Flexible Event-Frame Object Detection at Varying Operational Frequencies (NeurIPS 2025 · similarity 0.90)
- Efficient Event-Based Object Detection: A Hybrid Neural Network with Spatial and Temporal Attention (CVPR 2025 · similarity 0.89)
- PASS: Path-selective State Space Model for Event-based Recognition (NeurIPS 2025 · similarity 0.89)
- EGSST: Event-based Graph Spatiotemporal Sensitive Transformer for Object Detection (NeurIPS 2024 · similarity 0.88)
- LEOD: Label-Efficient Object Detection for Event Cameras (CVPR 2024 · similarity 0.87)
- Object Detection using Event Camera: A MoE Heat Conduction based Detector and A New Benchmark Dataset (CVPR 2025 · similarity 0.87)
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.