AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

AVTrack: Audio-Visual Tracking in Human-centric Complex Scenes

Yaoting Wang, Yun Zhou, Zipei Zhang, Henghui Ding

ICML 2026 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual source localization · 0 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 speech separation with MossFormer2 (ablation)AVTracker · AVTrackHOTA: 28.85 -> 29.08Improved
add speech separation with SepFormer (ablation)AVTracker · AVTrackHOTA: 28.85 -> 28.41Hurt
use larger speech processor (Whisper-large-v3-turbo vs Whisper-small) (ablation)AVTracker · AVTrackHOTA: 25.19 -> 28.85Improved
use larger VLM (Qwen3-VL-8B vs 4B) (ablation)AVTracker · AVTrackHOTA: 24.47 -> 28.85Improved
use VLM global reasoner instead of face detection features for tracklet grouping (ablation)AVTracker · AVTrackHOTA: 23.62 -> 24.01Improved
add local chunk compression (ablation)AVTracker · AVTrackHOTA: 16.88 -> 24.01Improved
add dynamic windowing (ablation)AVTracker · AVTrackHOTA: 27.45 -> 28.85Improved
add audio information in AVIS methods compared with VIS-only methodsAVTrack baselines · AVTrackHOTA: 11.46 -> 20.84Improved
use AVTracker modular pipeline instead of strongest AVIS baseline AVTrackFormerAVTrack · AVTrackHOTA: 21.47 -> 29.08Improved

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