AI Paper Atlas

Research map / Video / Action recognition

Temporal Segment Networks for Action Recognition in Videos

Limin Wang, Yuanjun Xiong, Zhe Wang, Yu Qiao, Dahua Lin, Xiaoou Tang, Luc Van Gool

TPAMI 2018 · Video › Action recognition · approach: Spatiotemporal CNNs for action recognition · 967 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 cross modality pre-training of the temporal stream (ablation)two-stream ConvNets · UCF101 split 1accuracy: 90.0% -> 91.5%Improved
add partial BN with dropout (ablation)two-stream ConvNets · UCF101 split 1accuracy: 91.5% -> 92.0%Improved
train from scratch instead of ImageNet pre-training of the spatial stream (ablation)two-stream ConvNets · UCF101 split 1accuracy: 90.0% -> 82.9%Hurt
add temporal segment network (K=7) samplingtwo-stream RGB+Flow · UCF101accuracy: 92.4% -> 94.9%Improved
add TSN to RGB+RGB Diff.RGB+RGB Diff. · UCF101accuracy: 86.8% -> 91.0%Improved
add warped optical flow as a third modality (ablation)TSN RGB+Flow · UCF101accuracy: 94.9% -> 95.0%No clear effect
increase segment number K from 3 to 7 (ablation)TSN · UCF101accuracy: 94.2% -> 94.9%Improved
increase segment number K from 7 to 9 (ablation)TSN · UCF101accuracy: 94.9% -> 94.9%No clear effect
replace average pooling with max pooling as consensus (ablation)TSN K=7 · UCF101accuracy: 94.9% -> 92.4%Hurt
replace average pooling with top-K pooling as consensus (ablation)TSN K=7 · ActivityNetaccuracy: 87.8% -> 88.1%Improved
replace BN-Inception two-stream with TSN (K=7)BN-Inception · ActivityNet v1.3 valmAP: 78.9% -> 84.7%Improved
use Inception V3 instead of BN-Inception in TSN (ablation)TSN · ActivityNet v1.3 valmAP: 84.7% -> 87.7%Improved

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