AI Paper Atlas

Research map / 3D vision / Human pose estimation

Gaze Target Estimation Anywhere with Concepts

Xu Cao, Houze Yang, Vipin Gunda, Zhongyi Zhou, Tianyu Xu, Adarsh Kowdle, Inki Kim, James M. Rehg

CVPR 2026 · 3D vision › Human pose estimation · approach: Heatmap and coordinate pose encoding · 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 text/visual subject prompt (ablation)GazeAnywhere-DINOv3-L · GazeFollow-ConceptAvg L2: 0.144 -> 0.099Improved
use full text prompt (all four categories) instead of appearance only (ablation)GazeAnywhere-DINOv3-L · GazeFollow-ConceptAvg L2: 0.113 -> 0.099Improved
add head box loss (ablation)GazeAnywhere-DINOv3-L · VAT-ConceptL2: 0.136 -> 0.123Improved
add presence loss on top of head loss (ablation)GazeAnywhere-DINOv3-L · GazeFollow-ConceptAvg L2: 0.099 -> 0.099No clear effect
add presence loss (ablation)GazeAnywhere-DINOv3-L · VAT-ConceptAP: 0.863 -> 0.879Improved
keep image and text encoders frozen (ablation)GazeAnywhere-DINOv3-L · GazeFollow-ConceptAvg L2: 0.150 -> 0.099Improved
replace CLIP-B with DINOv3-L encoder (ablation)GazeAnywhere · GazeFollow-ConceptAvg L2: 0.123 -> 0.099Improved
replace MetaCLIP2-H (1.9B) with DINOv3-L (870M) (ablation)GazeAnywhere · VAT-ConceptL2: 0.150 -> 0.123Improved
increase detector dimension D from 64 to 128 (ablation)GazeAnywhere-DINOv3-L · GazeFollow-ConceptAvg L2: 0.115 -> 0.100Improved
increase detector dimension D from 256 to 512 (ablation)GazeAnywhere-DINOv3-L · VAT-ConceptAUC: 0.928 -> 0.917No clear effect
increase detector layers from 1 to 3 (ablation)GazeAnywhere-DINOv3-L · GazeFollow-ConceptAvg L2: 0.126 -> 0.099Improved
increase detector layers from 3 to 5 (ablation)GazeAnywhere-DINOv3-L · GazeFollow-ConceptAvg L2: 0.099 -> 0.095No clear effect

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