AI Paper Atlas

Research map / Video / Action recognition

Temporal Aggregate Representations for Long-Range Video Understanding

Fadime Sener, Dipika Singhania, Angela Yao

ECCV 2020 · Video › Action recognition · approach: Fully supervised temporal action detection · 149 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 max-pooling instead of frame sampling for snippets (ablation)Temporal Aggregate model · Breakfast next action anticipationaccuracy: 32.1 -> 40.1Improved
use max-pooling instead of GRU (ablation)Temporal Aggregate model · Breakfast next action anticipationaccuracy: 37.9 -> 40.1Improved
use max-pooling instead of mean-pooling (ablation)Temporal Aggregate model · Breakfast next action anticipationaccuracy: 36.6 -> 40.1Improved
use non-local blocks instead of concatenation + linear layer (ablation)Temporal Aggregate model · Breakfast next action anticipationaccuracy: 33.7 -> 40.1Improved
couple recent and spanning features in coupling blocks instead of only spanning or only recent (ablation)Temporal Aggregate model · Breakfast next action anticipationaccuracy: 35.1 -> 40.1Improved
add Temporal Aggregation Blocks on top of a single coupling block (ablation)Temporal Aggregate model · Breakfast next action anticipationaccuracy: 32.1 -> 40.1Improved
ensemble of recent starting points instead of single start (ablation)Temporal Aggregate model · Breakfast next action anticipationaccuracy: 37.7 -> 40.1Improved
ensemble of three spanning scales instead of single scale (ablation)Temporal Aggregate model · Breakfast next action anticipationaccuracy: 38.0 -> 40.1Improved
add fourth spanning scale (5,10,15,20) (ablation)Temporal Aggregate model · Breakfast next action anticipationaccuracy: 40.1 -> 40.2No clear effect
use recent scale K_R=5 instead of 10 (ablation)Temporal Aggregate model · Breakfast next action anticipationaccuracy: 38.6 -> 40.1Improved
add auxiliary complex activity prediction (ablation)Temporal Aggregate model · Breakfast next action anticipationaccuracy: 1.1%Improved
max over spanning outputs instead of concatenation + linear (ablation)Temporal Aggregate model · Breakfast next action anticipationaccuracy: 37.4 -> 40.1Improved

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