AI Paper Atlas

Research map / Video / Video segmentation and tracking

Deep Future Gaze: Gaze Anticipation on Egocentric Videos Using Adversarial Networks

Mengmi Zhang, Keng Teck Ma, Joo Hwee Lim, Qi Zhao, Jiashi Feng

CVPR 2017 · Video › Video segmentation and tracking · approach: Stochastic video prediction · 111 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
Use DFG for gaze anticipationGTEA · GTEAAUC: 0.878 -> 0.883Improved
Use DFG for gaze anticipationGTEA · GTEAAAE: 8.4 -> 10.5Hurt
Use DFG for gaze anticipationGTEAplus · GTEAplusAUC: 0.867 -> 0.952Improved
Use DFG for gaze anticipationGTEAplus · GTEAplusAAE: 7.9 -> 6.6Improved
Use DFG for gaze anticipationOST · OSTAUC: 0.850 -> 0.854Improved
Use DFG for gaze anticipationOST · OSTAAE: 13.3 -> 10.6Improved
Integrate anticipated gaze locations into C3DC3D on GTEAplus · GTEAplusactivity recognition rate: 26.9% -> 28.5%Improved
Add a moving-background stream via the two-stream 3D-CNN generator (ablation)DFG on GTEA · GTEAAAE: 12.3, 11.9, 12.2, 12.1; Our Best: 11.0, 11.3, 11.3, 11.5Improved
Train GP end-to-end on generated frames rather than only real frames (ablation)DFG on GTEA · GTEAAAE: 12.8, 13.3, 13.9, 13.9; Our Best: 11.0, 11.3, 11.3, 11.5Improved
Add the discriminator to provide realism feedback during frame generation (ablation)DFG on GTEA · GTEAAAE: 11.3, 11.8, 12.3, 12.4; Our Best: 11.0, 11.3, 11.3, 11.5Improved
Add the two-stream 3D-CNN generator instead of the static-background variant (ablation)DFG on GTEA · GTEAAUC: 0.86, 0.85, 0.85, 0.85; Our Best: 0.88, 0.86, 0.85, 0.84Mixed
Train GP end-to-end on generated frames rather than only real frames (ablation)DFG on GTEA · GTEAAUC: 0.84, 0.82, 0.80, 0.81; Our Best: 0.88, 0.86, 0.85, 0.84Improved

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