AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

LG-Gaze: Learning Geometry-aware Continuous Prompts for Language-Guided Gaze Estimation

Pengwei Yin, Jingjing Wang, Guanzhong Zeng, Di Xie, Jiang Zhu

ECCV 2024 · Vision-language and multimodal › CLIP and zero-shot · approach: Test-time adaptation of VLMs · 11 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 MCR loss with language guidance to the gaze loss (ablation)ResNet-18 gaze model · Four cross-domain tasksaverage angular error (deg): 8.65 -> 7.01Improved
add geometry loss on anchor embeddings (ablation)LG-Gaze · Four cross-domain tasksaverage angular error (deg): 7.01 -> 6.84Improved
use geometry-aware spherical interpolation instead of global linear interpolation (ablation)LG-Gaze · Four cross-domain tasksaverage angular error (deg): 7.34 -> 6.84Improved
use spherical interpolation instead of bilinear interpolation (ablation)LG-Gaze · Four cross-domain tasksaverage angular error (deg): 6.98 -> 6.84Improved
add 256 global negative samples (ablation)MCR loss · Four cross-domain tasksaverage angular error (deg): 7.21 -> 6.84Improved
increase global negatives from 256 to 1024 (ablation)MCR loss · Four cross-domain tasksaverage angular error (deg): 6.84 -> 6.81No clear effect
use MCR instead of CDG, RNC or MoCo contrastive losses (ablation)LG-Gaze · Four cross-domain tasksaverage angular error (deg): 6.96 -> 6.84Improved
apply CoOp text prompt tuning to gazeCLIP · Four cross-domain tasksaverage angular error (deg): 8.65 -> 11.07Hurt
use zero-shot Vanilla CLIP for gaze predictionCLIP · Four cross-domain tasksaverage angular error (deg): 8.65 -> 81.04Hurt
use LG-Gaze versus CLIP-Gaze on ETH-XGaze->MPIIFaceGazeLG-Gaze · ETH-XGaze -> MPIIFaceGazeangular error (deg): 6.41 -> 6.45No clear effect

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