AI Paper Atlas

Research map / Video / Video-language understanding

Leveraging Weak Semantic Relevance for Complex Video Event Classification

Chao Li, Jiewei Cao, Zi Huang, Lei Zhu, Heng Tao Shen

ICCV 2017 · Video › Video-language understanding · approach: Dense video captioning · 11 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 weak semantic relevance guidance to the attention model (lambda_a > 0) (ablation)BiLSTM attention model · ActivityNetmAP: 55.1% -> 61.6%Improved
add weak semantic relevance guidance to the attention model (lambda_a > 0) (ablation)BiLSTM attention model · FCVIDmAP: 73.2% -> 77.8%Improved
add weak semantic relevance guidance to the attention model (lambda_a > 0) (ablation)BiLSTM attention model · MEDTest14mAP: 29.1% -> 36.3%Improved
use relevance as weak guidance in a learned attention model instead of directly weighting shot features (SVM-WA)video event classifier · ActivityNetmAP: 50.8% -> 61.6%Improved
use relevance as weak guidance in a learned attention model instead of directly weighting shot features (SVM-WA)video event classifier · FCVIDmAP: 69.9% -> 77.8%Improved
use relevance as weak guidance in a learned attention model instead of directly weighting shot features (SVM-WA)video event classifier · MEDTest14mAP: 28.1% -> 36.3%Improved
use attention guidance plus bidirectional LSTM instead of NISVM isotonic orderingvideo event classifier · MEDTest14mAP: 34.4% -> 36.3%Improved
increase lambda_a above 0.4 (ablation)full model · ActivityNetmAPHurt
set lambda_a to 0.3 on FCVID (best value) (ablation)full model · FCVIDmAPImproved
add guided attention with LSTM on static-scene events (events 11 to 14)full model · MEDTest14 events 11-14APHurt

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