AI Paper Atlas

Research map / Video / Action recognition

Sports Video Analysis on Large-Scale Data

Dekun Wu, He Zhao, Xingce Bao, Richard P. Wildes

ECCV 2022 · Video › Action recognition · approach: Disentangled action recognition · 27 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
use a transformer decoder model instead of an LSTMvideo captioning model with S3D · NSVA test (captioning)CIDEr: 0.500 -> 0.572Improved
replace S3D with TimeSformer video features (ablation)UniVL · NSVA test (captioning)CIDEr: 0.717 -> 0.956Improved
add ball, basket, player-with-ball and position-aware features to S3D (ablation)UniVL (S3D) · NSVA test (captioning)CIDEr: 0.717 -> 0.986Improved
add all four finer features (BAL, BAS, PB, PA) to TimeSformer (ablation)Ours (T) · NSVA test (captioning)CIDEr: 0.956 -> 1.139Improved
add position-aware (court line) feature to TimeSformer (ablation)Ours (T) · NSVA test (captioning)CIDEr: 0.956 -> 1.064Improved
add player-with-ball feature to TimeSformer (ablation)Ours (T) · NSVA test (captioning)CIDEr: 0.956 -> 1.055Improved
add basket feature to TimeSformer (ablation)Ours (T) · NSVA test (captioning)CIDEr: 0.956 -> 1.023Improved
add ball feature to TimeSformer (ablation)Ours (T) · NSVA test (captioning)CIDEr: 0.956 -> 0.931Mixed
add basket and position-aware features to TimeSformer with player-with-ball (ablation)TimeSformer · NSVA action recognition (Action-C)accuracy: 58.13 -> 60.31Improved
add position-aware feature (ablation)TimeSformer+PB+BAL+BAS · NSVA action recognition (Action-C)accuracy: 60.79 -> 61.20Improved
add position-aware feature (ablation)TimeSformer+PB+BAL+BAS · NSVA action recognition (Action-E)accuracy: 42.29 -> 42.34No clear effect
use TimeSformer instead of S3D features (ablation)action recognition · NSVA action recognition (Action-F)accuracy: 48.81 -> 49.66Improved

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