AI Paper Atlas

Research map / Video / Video segmentation and tracking

Entry-Flipped Transformer for Inference and Prediction of Participant Behavior

Bo Hu, Tat-Jen Cham

ECCV 2022 · Video › Video segmentation and tracking · approach: Spatio-temporal predictive modeling · 10 citations (OpenAlex)

Read the paper

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 entry-flipped cross-attention in decoder (ablation)Transformer · Tennis (prediction)MAD Avg: 31.33 -> 28.44Improved
add entry-flipped cross-attention in decoderTransformer · Tennis (inference)FAD Avg: 49.34 -> 46.43Improved
flip with all past frames as query rather than limited query (ablation)EF-Transformer · Tennis (prediction)FAD Avg: 46.83 -> 51.71Hurt
use hybrid typical/EF decoders instead of pure EF (ablation)EF-Transformer · Tennis (prediction)MAD Avg: 28.44 -> 29.29Hurt
predict relative-to-first-frame uv^R instead of absolute uv (ablation)Sequential ST-encoder · Tennis (inference)MAD Avg: 48.89 -> 28.35Improved
predict cumulative frame differences instead of uv^R (ablation)Sequential ST-encoder · Tennis (inference)FAD Avg: 46.43 -> 54.93Hurt
use sequential ST-encoder instead of parallel S+T (ablation)EF-Transformer · Tennis (inference)MAD Avg: 28.93 -> 28.35Improved
add entry flipping under noise spike at t=9Transformer · Tennis noise spike at t=9FAD Avg: 157.81 -> 124.29Improved
add entry flipping under noise spike at t=3Transformer · Tennis noise spike at t=3FAD Avg: 99.67 -> 54.15Improved
add entry flipping in multi-task prediction with estimated actionsTransformer · Tennis multi-task predictionFAD Avg: 52.01 -> 45.45Improved
add entry flipping on dance prediction (1 target)Transformer · DanceMAD Avg: 12.35 -> 9.39Improved
add entry flipping on NBA predictionTransformer · NBAMAD Avg: 3.99 -> 3.89Improved

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