AI Paper Atlas

Research map / Video / Action recognition

Temporal Action Detection With Structured Segment Networks

Yue Zhao, Yuanjun Xiong, Limin Wang, Zhirong Wu, Xiaoou Tang, Dahua Lin

ICCV 2017 · Video › Action recognition · approach: Fully supervised temporal action detection · 942 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 structured temporal pyramid pooling with stage structure (A=1 instead of A=0) (ablation)SSN avg pool · ActivityNet v1.2average mAP (%): 4.34 -> 24.6Improved
use average pooling instead of max pooling (ablation)SSN (1,2)-1 · ActivityNet v1.2average mAP (%): 18.4 -> 24.6Improved
increase pyramid depth from (1) to (1,2) (ablation)SSN avg pool A=1 · ActivityNet v1.2average mAP (%): 24.3 -> 24.6Improved
add separate activity and completeness classifiers instead of single classifier (ablation)SSN · ActivityNet v1.2mAP (%): 17.9% -> 23.7%Improved
add location regression with multi-task learning (end-to-end) (ablation)SSN · ActivityNet v1.2mAP (%): 24.8 -> 25.9Improved
add location regression (stage-wise) (ablation)SSN · ActivityNet v1.2mAP (%): 24.6 -> 24.9Improved
train end-to-end instead of stage-wise (ablation)SSN · ActivityNet v1.2mAP (%): 24.9 -> 25.9Improved
use TAG proposals instead of sliding windows (ablation)SSN · ActivityNet v1.2mAP (%): 18.1 -> 24.9Improved
use TAG proposals instead of sliding windows (ablation)proposal generation · THUMOS14average recall (%): 21.2 -> 48.9Improved
use TAG proposals instead of sliding windows (ablation)proposal generation · ActivityNet v1.2average recall (%): 34.8 -> 71.7Improved
apply actionness classifier trained on ActivityNet v1.2 directly to THUMOS14TAG · THUMOS14average recall (%): 48.9 -> 39.6Hurt
add SSN structured detection compared with prior bestSSN · THUMOS14mAP@0.5 (%): 19.0 -> 29.1Improved

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