AI Paper Atlas

Research map / Video / Action recognition

Real-Time Online Video Detection with Temporal Smoothing Transformers

Yue Zhao, Philipp Krähenbühl

ECCV 2022 · Video › Action recognition · approach: Spatiotemporal CNNs for action recognition · 96 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 Laplace kernel (ES) instead of box kernel (ablation)TeSTra · EK100 anticipation (RGB)overall action recall: 16.14 -> 16.95Improved
exponential smoothing lambda=0 instead of FIFO for box kernel (ablation)TeSTra with box kernel · EK100 anticipation (RGB)unseen and tail action recall: 12.64 -> 12.22Hurt
stream-mode ES instead of batch-mode for Laplace kernel (ablation)TeSTra · EK100 anticipation (RGB)overall action recall: 16.95 -> 16.94No clear effect
add temporal PE to long-term memory (ablation)TeSTra · EK100 anticipation (RGB)overall action recall: 17.0 -> 16.8No clear effect
add temporal PE to short-term memory (ablation)TeSTra · EK100 anticipation (RGB)overall action recall: 15.7 -> 17.0Improved
add MixClip augmentation (rate 0.5) (ablation)TeSTra · EK100 anticipation (RGB)overall action recall: 15.5 -> 17.0Improved
MixClip rate 0.8 instead of 0.5 (ablation)TeSTra · EK100 anticipation (RGB)overall action recall: 17.0 -> 16.2Hurt
fuse short-term memory with compressed memory instead of no fuse (ablation)TeSTra · EK100 anticipation (RGB)overall action recall: 15.9 -> 17.0Improved
attach short-term memory to long memory instead of no fuse (ablation)TeSTra · EK100 anticipation (RGB)overall action recall: 15.9 -> 16.0No clear effect
add long memory without fusing short memory (ablation)TeSTra · EK100 anticipation (RGB)overall action recall: 16.1 -> 15.9Hurt
use TeSTra instead of LSTR (K400 features)TeSTra · THUMOS'14 anticipationaverage mAP: 52.6 -> 56.8Improved
NVOFA optical flow instead of TV-L1TeSTra · THUMOS'14 online detectionmAP: 71.2 -> 67.3Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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