AI Paper Atlas

Research map / Video / Video segmentation and tracking

What Will Happen Next? Forecasting Player Moves in Sports Videos

Panna Felsen, Pulkit Agrawal, Jitendra Malik

ICCV 2017 · Video › Video segmentation and tracking · approach: Physics-inspired motion prediction · 79 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 nearest-defender position and distance features to the player features (F[3..9] vs F[8..9]) (ablation)Random forest on overhead view · Water polo next-possessor (test, detected heads)accuracy (%): 35.2 -> 44.1Improved
add ball possessor coordinates F[1,2] to the features (F[1..9] vs F[3..9]) (ablation)Random forest on overhead view · Water polo next-possessor (test, ground truth heads)accuracy (%): 48.8 -> 47.1No clear effect
use estimated detections instead of ground truth heads (ablation)Random forest F[1..9] · Water polo next-possessor (test)accuracy (%): 47.1 -> 45.5No clear effect
make the FCN also output player locations in addition to the next possessor (ablation)FCN on raw images · Water polo next-possessor (test)accuracy (%): 10% to 38.1%Improved
use overhead-view random forest instead of FCN on raw imagesWater polo next-possessor · Water polo next-possessor (test, detected heads)accuracy (%): 35.2 -> 45.5Improved
use early fusion of 5 past frames instead of CNN + LSTM late fusion (ablation)Basketball ball position CNN · Basketball ball position 1s aheadmean distance error (% court length): 11.4 -> 10.8Improved
use early fusion of 5 past frames instead of CNN + LSTM late fusion (ablation)Basketball ball position CNN · Basketball ball position 2s aheadmean distance error (% court length): 17.1 -> 16.8Improved
use overhead-view CNN with hand features instead of raw-image CNNBasketball event forecasting · Basketball event forecasting 1s ahead (full test split A)mAP (%): 11.9 -> 22.6Improved
use random forest on 92 hand-designed features instead of Overhead CNNBasketball event forecasting · Basketball event forecasting 1s ahead (full test split A)mAP (%): 22.6 -> 26.4Improved
use random forest instead of Overhead CNN at 2s horizonBasketball event forecasting · Basketball event forecasting 2s ahead (full test split A)mAP (%): 13.7 -> 18.7Improved
train random forest on basketball and test on water polo (transfer)Random forest F[1..9] · Water polo next-possessor (test)accuracy (%): 45.5 -> 36.8Hurt

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