Research map / Detection and segmentation / Tracking
TCTrack: Temporal Contexts for Aerial Tracking
Ziang Cao, Ziyuan Huang, Liang Pan, Shiwei Zhang, Ziwei Liu, Changhong Fu
Check 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 temporal information filtering to the temporal transformer (ablation) | AT-Trans · UAV123 | success: 0.550 -> 0.573 | Improved |
| Add temporal information filtering to the temporal transformer (ablation) | AT-Trans · UAV123 | precision: 0.750 -> 0.765 | Improved |
| Use multi-frame rather than single-frame training (ablation) | AT-Trans without TIF, convolutional initialization · UAV123 | success: 0.550 -> 0.508 | Hurt |
| Use convolutional rather than random temporal-prior initialization (ablation) | AT-Trans with TIF and multi-frame training · UAV123 | success: 0.586 -> 0.604 | Improved |
| Use the previous temporal prior rather than the current similarity map as encoder query (ablation) | AT-Trans with TIF, multi-frame training, and convolutional initialization · UAV123 | success: 0.580 -> 0.604 | Improved |
| Add temporal context filtering and the full AT-Trans configuration rather than using the unfiltered Transformer (ablation) | AT-Trans · UAV123 | success: 0.550 -> 0.604 | Improved |
| Increase TAdaConv sequence length from 1 to 2 (ablation) | TAdaConv · UAV123 | success: 0.561 -> 0.573 | Improved |
| Increase TAdaConv sequence length from 2 to 3 (ablation) | TAdaConv · UAV123 | success: 0.573 -> 0.580 | Improved |
| Increase TAdaConv sequence length from 1 to 3 (ablation) | TAdaConv · UAV123 | precision: 0.749 -> 0.776 | Improved |
| Use the full TCTrack framework rather than the SiamRPN++ baseline | UAVTrack112_L · UAVTrack112_L | success: 0.559 -> 0.582 | Improved |
| Use the full TCTrack framework rather than the SiamRPN++ baseline | UAVTrack112_L · UAVTrack112_L | precision: 0.773 -> 0.786 | Improved |
| Add temporal context to feature extraction and similarity-map refinement (ablation) | TCTrack compared with Transformer · UAV123 | success: 9.8% | Improved |
Later papers that compared with this method
2 later accepted papers report TCTrack as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Towards Real-World Visual Tracking With Temporal Contexts (TPAMI 2023 · better on 6 of 6 shared results)
- BioDrone: A Bionic Drone-Based Single Object Tracking Benchmark for Robust Vision (IJCV 2023 · better on 1 of 1 shared result)
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
- Learning Adaptive and View-Invariant Vision Transformer for Real-Time UAV Tracking (ICML 2024 · similarity 0.88)
- Similarity-Guided Layer-Adaptive Vision Transformer for UAV Tracking (CVPR 2025 · similarity 0.86)
- Learning Occlusion-Robust Vision Transformers for Real-Time UAV Tracking (CVPR 2025 · similarity 0.85)
- LVPTrack: High Performance Domain Adaptive UAV Tracking with Label Aligned Visual Prompt Tuning (AAAI 2025 · similarity 0.85)
- Dynamic Semantic-Aware Correlation Modeling for UAV Tracking (NeurIPS 2025 · similarity 0.85)
- Temporal Adaptive RGBT Tracking with Modality Prompt (AAAI 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.
