TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals

ICCV 2017 Jiyang GaoZhenheng YangChen SunKan ChenRam Nevatia

Temporal Action Proposal (TAP) generation is an important problem, as fast and accurate extraction of semantically important (e.g. human actions) segments from untrimmed videos is an important step for large-scale video analysis. We propose a novel Temporal Unit Regression Network (TURN) model... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Action Recognition In Videos THUMOS’14 TURN [email protected] 46.3 # 6
[email protected] 35.3 # 7
[email protected] 24.5 # 9
Temporal Action Localization THUMOS’14 TURN-FL-16 + S-CNN mAP [email protected] 25.6 # 11
mAP [email protected] 54 # 7
mAP [email protected] 50.9 # 6
mAP [email protected] 44.1 # 9
mAP [email protected] 34.9 # 7