AI Paper Atlas

Research map / Video / Action recognition

SBGAR: Semantics Based Group Activity Recognition

Xin Li, Mooi Choo Chuah

ICCV 2017 · Video › Action recognition · approach: Disentangled action recognition · 121 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 optical flow images to RGB frames (ablation)SBGAR · Collective Activity Datasetaccuracy (%): 83.7 -> 86.1Improved
add optical flow images to RGB frames (ablation)SBGAR · Volleyball Datasetaccuracy (%): 54.3 -> 66.9Improved
add RGB frames to optical flow images (ablation)SBGAR · Collective Activity Datasetaccuracy (%): 70.1 -> 86.1Improved
add RGB frames to optical flow images (ablation)SBGAR · Volleyball Datasetaccuracy (%): 38.7 -> 66.9Improved
use a temporal LSTM over multiple frames instead of single-frame classificationInception-v3 image features · Collective Activity Datasetaccuracy (%): 67.2 -> 68.5Improved
use a temporal LSTM over multiple frames instead of single-frame classificationInception-v3 image features · Volleyball Datasetaccuracy (%): 41.9 -> 44.3Improved
use caption-based semantic LSTM instead of direct image features LSTMtemporal model · Volleyball Datasetaccuracy (%): 44.3 -> 66.9Improved
use frames both before and after the current frame instead of before only (Before(10) to Before(10)After(10)) (ablation)SBGAR · Collective Activity Datasetaccuracy (%): 85.7 -> 86.4Improved
use frames both before and after the current frame instead of before only (Before(10) to Before(10)After(10)) (ablation)SBGAR · Volleyball Datasetaccuracy (%): 64.7 -> 67.7Improved
use only past frames Before(10) versus only future frames After(10) (ablation)SBGAR · Collective Activity vs Volleyballaccuracy (%): 85.7 vs 84.7 on Collective; 64.7 vs 65.1 on VolleyballMixed
train LSTM1 for more epochs (stable beyond 500) (ablation)SBGAR · Collective and VolleyballaccuracyImproved
train LSTM2 for more epochs (stable after 200) (ablation)SBGAR · Collective and VolleyballaccuracyImproved

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