AI Paper Atlas

Research map / Video / Action recognition

SCSampler: Sampling Salient Clips From Video for Efficient Action Recognition

Bruno Korbar, Du Tran, Lorenzo Torresani

ICCV 2019 · Video › Action recognition · approach: Disentangled action recognition · 235 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
select K=10 clips with SCSampler instead of dense evaluationir-CSN-152 · Sports1Mvideo accuracy (%): 77.0 -> 84.0Improved
select clips with SCSampler instead of uniform selectionMC3-18 · Sports1Mvideo accuracy (%): 64.8 -> 72.8Improved
select clips with SCSampler instead of dense evaluationir-CSN-152 · Sports1Mruntime (days): 14.0 -> 0.9Improved
select clips with SCSampler instead of dense evaluationir-CSN-152 · Kineticsvideo accuracy (%): 78.8 -> 80.2Improved
use fully-convolutional spatial testing with SCSamplerir-CSN-152 · Kineticsvideo accuracy (%): 80.2 -> 81.1Improved
train visual sampler with AC loss instead of SAL-RANK (ablation)Visual sampler · miniSportsvideo accuracy (%): 64.8 -> 73.1Improved
train audio sampler with SAL-RANK loss instead of AC (ablation)Audio sampler · miniSportsvideo accuracy (%): 66.4 -> 67.8Improved
add I-frame features to MD+RGB-R (ablation)Visual sampler ResNet-18 · miniSportsvideo accuracy (%): 73.1 -> 74.9Improved
use ResNet-18 instead of ShuffleNet-26 (ablation)Visual sampler MD+RGB-R · miniSportsvideo accuracy (%): 67.9 -> 73.1Improved
combine MD and RGB-R features instead of MD alone (ablation)Visual sampler ResNet-18 · miniSportsvideo accuracy (%): 63.5 -> 73.1Improved
add audio sampler via AV-union-list to visual sampler (ablation)SCSampler · miniSportsvideo accuracy (%): 73.1 -> 76.0Improved
replace AV-union-list with joint training of both samplers (ablation)SCSampler · miniSportsvideo accuracy (%): 76.0 -> 75.5No clear effect

Later papers that compared with this method

8 later accepted papers report SCSampler as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.

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