AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

DECK: Discovering Event Composition Knowledge from Web Images for Zero-Shot Event Detection and Recounting in Videos

AAAI 2017 · Detection and segmentation › Open-set and few-shot detection · approach: Zero-shot segmentation and detection · 16 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
select concepts with DECK web-image knowledge instead of word2vec (image + video concepts) (ablation)ZeroMED · ZeroMED MEDTest 2014mAP (%): 12.4 -> 16.3Helped
select image concepts with DECK instead of word2vec (ablation)ZeroMED · ZeroMED MEDTest 2014mAP (%): 5.4 -> 9.1Helped
add video-based concepts to DECK image concepts (ablation)DECK · ZeroMED MEDTest 2014mAP (%): 9.1 -> 16.3Helped
use DECK concept discovery instead of training event classifiers on the web images (ablation)ZeroMED · ZeroMED MEDTest 2014mAP (%): 6.4 -> 16.3Helped
add diversity term to recounting (ablation)DECK · MED-Recounting (MED14)mean RQ: 0.535 -> 0.642Helped
select concepts with DECK instead of word2vec (ablation)ZeroMER · MED-Recounting (MED14)mean RQ: 0.534 -> 0.648Helped
add diversity term in human evaluation (ablation)DECK · MED-Recounting (MED14)human preference: 71.5% better, 18.5% worseMixed

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