Research map / Detection and segmentation / Tracking
Object Tracking by Jointly Exploiting Frame and Event Domain
Jiqing Zhang, Xin Yang, Yingkai Fu, Xiaopeng Wei, Baocai Yin, Bo Dong
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 event input to frame input by concatenation (Event to Frame) (ablation) | Frame-only tracker · FE108 (ALL) | RSR: 45.6 -> 55.5 | Improved |
| add Edge Attention Block to the event branch (ablation) | Full tracker · FE108 (ALL) | RSR: 60.7 -> 63.4 | Improved |
| add CDMS fusion block (ablation) | Full tracker · FE108 (ALL) | RSR: 59.8 -> 63.4 | Improved |
| add self-attention inside CDMS (ablation) | Full tracker · FE108 (ALL) | RSR: 62.6 -> 63.4 | Improved |
| add cross-attention inside CDMS (ablation) | Full tracker · FE108 (ALL) | RSR: 61.9 -> 63.4 | Improved |
| add adaptive weighting inside CDMS (ablation) | Full tracker · FE108 (ALL) | RSR: 60.9 -> 63.4 | Improved |
| use learned slice weights instead of fixing all weights to 1 (ablation) | Full tracker · FE108 (ALL) | RSR: 61.3 -> 63.4 | Improved |
| use proposed latest-timestamp aggregation instead of TSLTD (ablation) | Full tracker · FE108 (ALL) | RSR: 60.4 -> 63.4 | Improved |
| use proposed aggregation instead of Event Frame (ablation) | Full tracker · FE108 (ALL) | RSR: 59.0 -> 63.4 | Improved |
| increase event slices n from 1 to 3 (ablation) | Full tracker · FE108 (ALL) | RSR: 60.2 -> 63.4 | Improved |
| increase event slices n from 3 to 6 (ablation) | Full tracker · FE108 (ALL) | RSR: 63.4 -> 63.9; FPS 30.1 -> 22.7 | Mixed |
| add event aggregated frames to ATOM by concatenation | ATOM · FE108 (ALL) | RSR: 46.5 -> 55.5 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- CLNet — CLNet: A Compact Latent Network for Fast Adjusting Siamese Trackers (ECCV 2020) · better on 2 of 2 shared results
- ATOM — ATOM: Accurate Tracking by Overlap Maximization (CVPR 2019) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel Baseline (CVPR 2024 · similarity 0.88)
- Fully Spiking Neural Networks for Unified Frame-Event Object Tracking (NeurIPS 2025 · similarity 0.86)
- ETAP: Event-based Tracking of Any Point (CVPR 2025 · similarity 0.86)
- TimeTracker: Event-based Continuous Point Tracking for Video Frame Interpolation with Non-linear Motion (CVPR 2025 · similarity 0.85)
- FlexEvent: Towards Flexible Event-Frame Object Detection at Varying Operational Frequencies (NeurIPS 2025 · similarity 0.85)
- Single-Model and Any-Modality for Video Object Tracking (CVPR 2024 · similarity 0.85)
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.
