AI Paper Atlas

Research map / Video / Action recognition

Learning From Video and Text via Large-Scale Discriminative Clustering

Antoine Miech, Jean-Baptiste Alayrac, Piotr Bojanowski, Ivan Laptev, Josef Sivic

ICCV 2017 · Video › Action recognition · approach: Temporal action segmentation · 37 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 the joint person-action constraint (ablation)Full setup · Action recognition (5 movies, 13 classes)mAP (%): 12.5 -> 16.4Improved
train on 66 movies instead of only the 5 evaluated movies (ablation)Full setup · Action recognition (5 movies, 13 classes)mAP (%): 12.4 -> 16.4Improved
use joint person-action constraint for interacting actions (Fight, Hand Shake, Hug, Kiss) (ablation)Full setup · Action recognition (5 movies, 13 classes)per-class AP: Fight 12.6 -> 5.9Hurt
add weak script supervision with discriminative clustering over fully supervised small set (ablation)Full setup · Action recognition (5 movies, 13 classes)mAP (%): 9.3 -> 16.4Improved
add background constraint alpha=0.3 instead of 0 (ablation)Our method · Casablanca person recognitionaccuracy (%): 58 -> 82Improved
raise background constraint alpha to 1.0 (ablation)Our method · Casablanca person recognitionaccuracy (%): 84 -> 55Hurt
add background constraint beta (ablation)Full setup · Action recognition (beta sweep)mAP (%): 15.0 -> 16.6No clear effect
use our discriminative-clustering person model over Parkhi et al. baselineOur method · Casablanca person recognitionaccuracy (%): 74% -> 83%Improved
use our model on Buffy episode 1Ours · Buffy season 5 episode 1AP (%): 99 -> 98Hurt
use our model on Buffy episode 3Ours · Buffy season 5 episode 3AP (%): 94 -> 98Improved

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