AI Paper Atlas

Research map / 3D vision / Human pose estimation

Identifying First-Person Camera Wearers in Third-Person Videos

Chenyou Fan, Jangwon Lee, Mingze Xu, Krishna Kumar Singh, Yong Jae Lee, David J. Crandall, Michael S. Ryoo

CVPR 2017 · 3D vision › Human pose estimation · approach: Temporal video pose estimation · 53 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 semi-Siamese branches with specialized early layers instead of fully shared layers (ablation)two-stream correspondence network · First-/third-person correspondenceBinary AP: 0.453 -> 0.585Improved
use semi-Siamese branches instead of fully shared layers (ablation)spatial correspondence network · First-/third-person correspondenceBinary AP: 0.481 -> 0.528Improved
use semi-Siamese branches instead of fully shared layers (ablation)temporal correspondence network · First-/third-person correspondenceBinary AP: 0.337 -> 0.389Improved
replace contrastive loss with triplet loss (ablation)two-stream semi-Siamese network · First-/third-person correspondenceBinary AP: 0.585 -> 0.621Improved
replace contrastive loss with triplet loss (ablation)spatial semi-Siamese network · First-/third-person correspondenceBinary AP: 0.528 -> 0.549Improved
replace contrastive loss with triplet loss (ablation)temporal semi-Siamese network · First-/third-person correspondenceBinary AP: 0.389 -> 0.452Improved
combine spatial and motion cues in a two-stream network (ablation)semi-Siamese correspondence network · First-/third-person correspondenceBinary AP: 0.528 and 0.389 -> 0.585Improved
use spatial rather than temporal features (ablation)triplet semi-Siamese network · First-/third-person correspondenceBinary AP: 0.456 -> 0.549Improved
remove all layer sharing between the two branches (ablation)two-stream correspondence network · First-/third-person correspondenceBinary AP: 0.476 -> 0.585Hurt
add gaze estimates to guide the spatial network (ablation)spatial correspondence network · First-/third-person correspondencematching abilityHurt
use triplet loss rather than contrastive loss (ablation)temporal semi-Siamese network · Multiple wearable camerasBinary AP: 0.412 -> 0.386Hurt

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