AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Beyond F-Formations: Determining Social Involvement in Free Standing Conversing Groups From Static Images

Lu Zhang, Hayley Hung

CVPR 2016 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 40 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
Learn location-dependent frustum parameters instead of using global parametersF-formation detection · Idiap Poster Data, T=1F1: 0.83 -> 0.94Improved
Learn location-dependent frustum parameters instead of using global parametersF-formation detection · Idiap Poster Data, T=2/3F1: 0.94 vs 0.94No clear effect
Model associates with social-prior featuresAssociate detection · Idiap Poster DataF1: 0.44 -> 0.71Improved
Use associate detections to remove false-positive F-formation membersF-formation detection · Idiap Poster Data, full-agreement formationsF1: 0.86 -> 0.91Improved
Add associate-detection feedback to global-FF-formation detection · Idiap Poster Data, full-agreement formationsF1: 0.83 -> 0.88Improved
Use proximity and orientation features without group-size features (ablation)social-A · Idiap Poster Data, associate detectionF1: 0.71 -> 0.70No clear effect
Use proximity and group-size features without orientation features (ablation)social-A · Idiap Poster Data, associate detectionF1: 0.71 -> 0.67Hurt
Use orientation and group-size features without proximity features (ablation)social-A · Idiap Poster Data, associate detectionF1: 0.71 -> 0.69No clear effect
Use proximity features only (ablation)social-A · Idiap Poster Data, associate detectionF1: 0.71 -> 0.69Hurt
Use orientation features only (ablation)social-A · Idiap Poster Data, associate detectionF1: 0.71 -> 0.69Hurt
Use group-size features only (ablation)social-A · Idiap Poster Data, associate detectionF1: 0.71 -> 0.63Hurt
Extract social-prior features with global-F rather than spatial-F (ablation)Associate detection · Idiap Poster DataF1: 0.71 vs 0.71No 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