Research map / Video / Video-language understanding
Tracking by Natural Language Specification
Zhenyang Li, Ran Tao, Efstratios Gavves, Cees G. M. Snoek, Arnold W.M. Smeulders
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 |
|---|---|---|---|
| Use dynamic filters generated from the language query for target localization | Lingual specification network · ReferIt test | overall IoU: 48.0 -> 54.3 | Improved |
| Track with language and visual specification jointly rather than language specification only (ablation) | Tracking by natural language specification · Lingual OTB99 | AUC | Improved |
| Use language-only tracking instead of visual tracking initialized from the language-predicted location (ablation) | Tracking by natural language specification · Lingual OTB99, when initial target identification is poor | tracking accuracy | Improved |
| Add lingual tracking to visual tracking initialized by a predicted target location (ablation) | Model II tracking · Lingual OTB99 | tracking accuracy | Improved |
| Use language-only tracking instead of language-plus-visual tracking (ablation) | Tracking by natural language specification · Lingual ImageNet Videos | AUC: 23.4 -> 26.3 | Improved |
| Add language specification to box-based tracking | Visual tracking with a user-provided box · Lingual OTB99 | AUC: 56.1 -> 57.8 | Improved |
| Add language specification to box-based tracking | Visual tracking with a user-provided box · Lingual ImageNet | AUC: 47.9 -> 49.4 | Improved |
Closest papers by meaning
- Towards More Flexible and Accurate Object Tracking With Natural Language: Algorithms and Benchmark (CVPR 2021 · similarity 0.93)
- Tracking by Natural Language Specification with Long Short-term Context Decoupling (ICCV 2023 · similarity 0.90)
- Beyond Explicit Language: Plug-and-Play Visual-to-Linguistic Modeling Toward General Object Tracking (CVPR 2026 · similarity 0.90)
- Learning to Track Instance from Single Nature Language Description (CVPR 2026 · similarity 0.89)
- ChatTracker: Enhancing Visual Tracking Performance via Chatting with Multimodal Large Language Model (NeurIPS 2024 · similarity 0.88)
- Unifying Visual and Vision-Language Tracking via Contrastive Learning (AAAI 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.
