Research map / Detection and segmentation / Open-set and few-shot detection
Segment Any Event Streams via Weighted Adaptation of Pivotal Tokens
Zhiwen Chen, Zhiyu Zhu, Yifan Zhang, Junhui Hou, Guangming Shi, Jinjian Wu
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Adapts the Segment Anything Model to event camera streams by weighted adaptation of pivotal tokens, enabling universal event-based object segmentation.
Problem
Segment Anything Models are designed for RGB images and do not transfer directly to event data; event-derived embeddings must be aligned with SAM's embedding space for robust universal event segmentation.
Approach
Adapt SAM to event streams by aligning and calibrating event-derived embeddings through weighted adaptation of a small set of pivotal tokens, rather than fine-tuning the full model.
Experimental setup
Baselines: SAM
Builds on: Segment Anything Model
Closest papers by meaning
- SAM 2: Segment Anything in Images and Videos (ICLR 2025 · similarity 0.85)
- Efficient Event-Based Semantic Segmentation via Exploiting Frame-Event Fusion: A Hybrid Neural Network Approach (AAAI 2025 · similarity 0.85)
- Event-assisted Low-Light Video Object Segmentation (CVPR 2024 · similarity 0.85)
- OpenESS: Event-based Semantic Scene Understanding with Open Vocabularies (CVPR 2024 · similarity 0.85)
- EZSR: Event-based Zero-Shot Recognition (CVPR 2025 · similarity 0.85)
- EventPillars: Pillar-based Efficient Representations for Event Data (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.
