AI Paper Atlas

Research map / Detection and segmentation / Tracking

Detecting Attended Visual Targets in Video

Eunji Chong, Yongxin Wang, Nataniel Ruiz, James M. Rehg

CVPR 2020 · Detection and segmentation › Tracking · approach: Transformer-based video object tracking · 158 citations (OpenAlex)

Check 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 the head-position image (ablation)VideoAttentionTarget gaze model · VideoAttentionTargetAUC: 0.835 -> 0.860Improved
Add head feature maps to the head-conditioning pathway (ablation)VideoAttentionTarget gaze model · VideoAttentionTargetAUC: 0.758 -> 0.860Improved
Use a head-conditioned attention map to weight scene features (ablation)VideoAttentionTarget gaze model · VideoAttentionTargetAUC: 0.717 -> 0.860Improved
Fuse head features with scene features for encoding (ablation)VideoAttentionTarget gaze model · VideoAttentionTargetAUC: 0.853 -> 0.860Improved
Use ConvLSTM temporal modeling (ablation)VideoAttentionTarget gaze model · VideoAttentionTargetL² Dist.: 0.147 -> 0.134Improved
Add predicted attention heatmaps as an input channelResNet gaze-shift detector · Toddler gaze shift detectionPrecision: 0.541 -> 0.708Improved
Add predicted attention heatmaps as an input channelResNet gaze-shift detector · Toddler gaze shift detectionRecall: 0.567 -> 0.759Improved

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