Research map / Image generation / Text-to-image diffusion
CiteTracker: Correlating Image and Text for Visual Tracking
Xin Li, Yuqing Huang, Zhenyu He, Yaowei Wang, Huchuan Lu, Ming-Hsuan Yang
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 prompt-tuned CLIP image-text conversion (vs original CLIP) (ablation) | CiteTracker · GOT-10k | AO: 71.4 -> 74.7 | Improved |
| add prompt-tuned CLIP image-text conversion (vs original CLIP) (ablation) | CiteTracker · TNL2K | SUC: 56.1 -> 57.7 | Improved |
| add attribute descriptions (color, material, texture) (ablation) | CiteTracker · OTB2015 | precision: 90.6 -> 92.2 | Improved |
| add attribute descriptions (ablation) | CiteTracker · TNL2K | precision: 59.1 -> 59.6 | Improved |
| add dynamic text-feature generation (ablation) | CiteTracker · OTB2015 | AUC: 69.3 -> 69.6 | Improved |
| add dynamic text-feature generation (ablation) | CiteTracker · GOT-10k | AO: 74.5 -> 74.7 | Improved |
| add dynamic text-feature generation (ablation) | CiteTracker · TNL2K | SUC: 57.6 -> 57.7 | Improved |
| correlate manually annotated text features with visual features (ablation) | Base model · TNL2K | SUC: 55.9 -> 57.1 | Improved |
| correlate manually annotated text features with visual features (ablation) | Base model · OTB2015 | AUC: 67.5 -> 68.1 | Improved |
| replace manual descriptions with generated text (CiteTracker vs LangTracker) | CiteTracker · TNL2K | SUC: 57.1 -> 57.7 | Improved |
| add text correlation (CiteTracker vs OSTrack) for initialization robustness | OSTrack · OTB2015 | TRE-worst AUC: 57.5 -> 61.1 | Improved |
| add text correlation (CiteTracker vs OSTrack) | OSTrack · OTB2015 | TRE AUC: 69.3 -> 70.2 | Improved |
Closest papers by meaning
- ChatTracker: Enhancing Visual Tracking via LLM-Driven Iterative Description Refinement (TPAMI 2026 · similarity 0.89)
- Leveraging Text-to-Image Diffusion Models for Unsupervised Visual Object Tracking (TPAMI 2026 · similarity 0.88)
- Joint Visual Grounding and Tracking With Natural Language Specification (CVPR 2023 · similarity 0.87)
- HFF-Tracker: A Hierarchical Fine-grained Fusion Tracker for Referring Multi-Object Tracking (AAAI 2025 · similarity 0.87)
- GoMatching: A Simple Baseline for Video Text Spotting via Long and Short Term Matching (NeurIPS 2024 · similarity 0.86)
- ChatTracker: Enhancing Visual Tracking Performance via Chatting with Multimodal Large Language Model (NeurIPS 2024 · 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.
