AI Paper Atlas

Research map / Video / Action recognition

TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals

Jiyang Gao, Zhenheng Yang, Kan Chen, Chen Sun, Ram Nevatia

ICCV 2017 · Video › Action recognition · approach: Fully supervised temporal action detection · 503 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 unit size 16 instead of 32 for flow-feature TURN (ablation)TURN-FL · THUMOS-14 proposalsAR@F=1.0 (%): 42.4 -> 43.5 (FPS 260.6 -> 129.4)Improved
use flow CNN features instead of C3D features (ablation)TURN unit-16 · THUMOS-14 proposalsAR@F=1.0 (%): 39.3 -> 43.5 (FPS 880.8 -> 129.4)Improved
use flow CNN proposals instead of C3D proposals with SVM localizer (ablation)TURN-16 · THUMOS-14 localization (our SVM)mAP@tIoU=0.5 (%): 16.4 -> 17.8Improved
use flow CNN proposals instead of C3D proposals with S-CNN localizer (ablation)TURN-16 · THUMOS-14 localization (S-CNN localizer)mAP@tIoU=0.5 (%): 22.5 -> 25.6Improved
replace SCNN-prop proposals with TURN-FL-16 proposals in S-CNN localizerS-CNN localizer · THUMOS-14 localization (S-CNN localizer)mAP@tIoU=0.5 (%): 19.0 -> 25.6Improved
replace SCNN-prop proposals with TURN-FL-16 proposals in SVM localizerSVM localizer · THUMOS-14 localization (our SVM)mAP@tIoU=0.5 (%): 14.0 -> 17.8Improved
replace sliding windows with TURN-FL-16 proposals for ActivityNet Sports localizationSVM localizer with two-stream features · ActivityNet v1.1 SportsmAP@tIoU=0.5 (%): 27.3 -> 37.1Improved
replace sliding windows with TURN-FL-16 proposals for ActivityNet Work localizationSVM localizer with two-stream features · ActivityNet v1.1 WorkmAP@tIoU=0.5 (%): 29.6 -> 41.2Improved
train on ensemble of all four subsets instead of the subset alone (Arts test)TURN-C3D-16 · ActivityNet v1.3 ArtsAR@F=1.0 (%): 44.30 -> 45.30Improved
train on ensemble instead of Housework only (Housework test)TURN-C3D-16 · ActivityNet v1.3 HouseworkAR@F=1.0 (%): 44.30 -> 48.12Improved
train on ensemble instead of Vehicles only (Vehicles test)TURN-C3D-16 · ActivityNet v1.3 VehiclesAR@F=1.0 (%): 42.22 -> 42.33Improved
train on ensemble instead of Sports only (Sports test)TURN-C3D-16 · ActivityNet v1.3 SportsAR@F=1.0 (%): 46.62 -> 46.72Improved

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