AI Paper Atlas

Research map / Video / Video segmentation and tracking

Attend to Anything: Foundation Model for Unified Human Attention Modeling

Wenzhuo Zhao, ronghao xian, Keren Fu, Qijun Zhao

ICML 2026 · Video › Video segmentation and tracking · approach: Physics-inspired motion prediction · 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
use AAM instead of SUMSUM · MIT1003 (image)CC: 0.768 -> 0.831Improved
use AAM instead of SUMSUM · OSIE (image)CC: 0.861 -> 0.901Improved
use AAM instead of SUMSUM · U-EYE (image)CC: 0.731 -> 0.743Improved
use AAM instead of TAVDiffTAVDiff · Coutrot2 (audio-visual)CC: 0.798 -> 0.887Improved
use AAM instead of the best video baselineVSSM / MSFF-Net · DHF1K (video)CC: 0.534 -> 0.563Improved
use AAM instead of VSSMVSSM · UCF (video)NSS: 3.908 -> 3.892Hurt
use frame-wise FPD AAM instead of fixed-window video modelsTMFI-Net · Video inferenceFPS: 30 -> 111Improved
add joint training across image, video and audio-visual data (ablation)AAM · image/audio-visual/video ablation A-Caverage metricsImproved
add FPD temporal module instead of no module or standard self-attention (ablation)AAM · video ablation Eaverage metricsImproved
add hyperbolic loss and hyperbolic decoder (ablation)AAM · ablation Faverage metricsImproved
use larger DINOv3 backbone (ablation)AAM · backbone ablation Daverage metricsImproved
swap correct text condition for generic or wrong one (ablation)AAM · condition swapperformanceHurt

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