AI Paper Atlas

Research map / Detection and segmentation / Tracking

COVTrack: Continuous Open-Vocabulary Tracking via Adaptive Multi-Cue Fusion

Zekun Qian, Ruize Han, Zhixiang Wang, Junhui Hou, Wei Feng

ICCV 2025 · Detection and segmentation › Tracking · approach: Association cues for online MOT · 2 citations (OpenAlex)

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 changedWhereMeasuredEffect
add intra-frame semantic confidence (ablation)COVTrack · TAO validation (novel classes)AssocA: 40.6 -> 41.3Improved
add intra-frame location confidence (ablation)COVTrack · TAO validation (novel classes)AssocA: 37.7 -> 41.3Improved
add inter-frame location confidence (ablation)COVTrack · TAO validation (novel classes)AssocA: 37.3 -> 41.3Improved
add inter-frame semantic confidence (ablation)COVTrack · TAO validation (novel classes)AssocA: 39.1 -> 41.3Improved
add both intra-frame and inter-frame cue confidence (ablation)COVTrack · TAO validation (novel classes)AssocA: 35.7 -> 41.3Improved
add appearance features to intra-frame confidence learning (ablation)COVTrack · TAO validation (novel classes)AssocA: 36.5 -> 41.3Improved
add semantic and location features in fusion Eq. (4) (ablation)COVTrack · TAO validation (novel classes)AssocA: 39.7 -> 41.3Improved
add refinement with appearance feature in Eq. (5) (ablation)COVTrack · TAO validation (novel classes)AssocA: 39.1 -> 41.3Improved
use adaptive multi-cue fusion instead of SLAck direct addition (original TAO)COVTrack · TAO validation (novel, trained on original TAO)AssocA: 24.1 -> 34.8Improved
train on C-TAO instead of original TAOCOVTrack · TAO validation (novel)AssocA: 34.8 -> 41.3Improved
train on pairwise P-TAO instead of original TAOOVTrack · TAO validation (novel)AssocA: 25.6 -> 36.5Improved
train on full continuous C-TAO instead of pairwise P-TAOOVTrack · TAO validation (novel)AssocA: 36.5 -> 39.3Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most 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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy