AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

ATCTrack: Aligning Target-Context Cues with Dynamic Target States for Robust Vision-Language Tracking

Xiaokun Feng, Shiyu Hu, Xuchen Li, Dailing Zhang, Meiqi Wu, Jing Zhang, Xiaotang Chen, Kaiqi Huang

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: VLM capability analysis · 4 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 textual target-context guidance (ablation)ATCTrack-B naive · TNL2KAUC: 65.5 -> 66.5Improved
add visual target-context guidance (ablation)ATCTrack-B naive · TNL2KAUC: 65.5 -> 66.7Improved
combine textual and visual target-context guidance (ablation)ATCTrack-B naive · LaSOTAUC: 72.5 -> 74.7Improved
add target words awareness to textual modeling (ablation)naive text fusion · TNL2KAUC: 65.5 -> 65.9Improved
add context words calibration (ablation)ATCTrack-B with target words awareness · TNL2KAUC: 65.9 -> 66.5Improved
use dual-type textual features (initial and calibrated) instead of calibrated only (ablation)ATCTrack-B textual guidance · LaSOTAUC: 73.2 -> 73.6Improved
use RoI local region of predicted box for visual context (ablation)naive visual baseline · LaSOTAUC: 72.5 -> 71.1Hurt
use search region with cropped local mask for visual context (ablation)naive visual baseline · LaSOTAUC: 72.5 -> 71.9Hurt
use search region with global mask instead of crop mask (ablation)visual target-context module · LaSOTAUC: 71.9 -> 73.7Improved
use HiViT backbone instead of ViT (ablation)ATCTrack-B · TNL2KAUC: 65.8 -> 67.5Improved
add dynamic template (ablation)ATCTrack-B · LaSOTAUC: 73.2 -> 74.7Improved
add target word supervision labels (BCE loss) (ablation)ATCTrack-B · TNL2KAUC: 67.0 -> 67.5Improved

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