AI Paper Atlas

Research map / Video / Action recognition

Hierarchical Relational Networks for Group Activity Recognition and Retrieval

Mostafa S. Ibrahim, Greg Mori

ECCV 2018 · Video › Action recognition · approach: Disentangled action recognition · 146 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 a relational layer (all-pairs) in place of the shared dense layer (ablation)B1-NoRelations · Volleyball group activity (single frame)accuracy: 85.1 -> 86.5Improved
fine-tune VGG19 on person boxes (ablation)RCRG-1R-1C · Volleyball group activity (single frame)accuracy: 75.4 -> 86.5Improved
split first layer into 2 team cliques instead of all-people clique (ablation)RCRG-2R · Volleyball group activity (single frame)accuracy: 86.1 -> 87.2Improved
stack a third relational layer (4,2,1 cliques) over 2 layers (ablation)RCRG-2R-21C · Volleyball group activity (single frame)accuracy: 87.2 -> 86.4Hurt
use concatenation pooling instead of max-pooling (ablation)RCRG-2R-11C · Volleyball group activity (single frame)accuracy: 86.1 -> 88.3Improved
use concatenation pooling instead of max-pooling (ablation)RCRG-2R-21C · Volleyball group activity (single frame)accuracy: 87.2 -> 86.7Hurt
use concatenation pooling instead of max-pooling (ablation)RCRG-3R-421C · Volleyball group activity (single frame)accuracy: 86.4 -> 87.3Improved
use relational autoencoder instead of per-person compact autoencoderB1-Compact128 · Volleyball scene retrievalHit@1: 49.4 -> 57.4Improved
use relational autoencoder (128-d) instead of raw VGG19 features (4096-d)B2-VGG19 · Volleyball scene retrievalHit@1: 55.0 -> 57.4Improved
use 4 layers with 2 team cliques instead of 2 layers with 1 clique (ablation)RAER · Volleyball scene retrieval (model variants)Hit@1: 56.8 -> 57.4Improved
use hierarchical cliques (4,2,2,4) instead of uniform 2 cliques (ablation)RAER-4L · Volleyball scene retrieval (model variants)Hit@1: 57.4 -> 55.8Hurt
use relational autoencoder instead of VGG19 when 50% of people are missingB2-VGG19-D · Volleyball scene retrieval (denoising, 50% people dropped)Hit@1: 34.0 -> 43.0Improved

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