TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals

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. There are two salient aspects of TURN: (1) TURN jointly predicts action proposals and refines the temporal boundaries by temporal coordinate regression; (2) Fast computation is enabled by unit feature reuse: a long untrimmed video is decomposed into video units, which are reused as basic building blocks of temporal proposals. TURN outperforms the state-of-the-art methods under average recall (AR) by a large margin on THUMOS-14 and ActivityNet datasets, and runs at over 880 frames per second (FPS) on a TITAN X GPU. We further apply TURN as a proposal generation stage for existing temporal action localization pipelines, it outperforms state-of-the-art performance on THUMOS-14 and ActivityNet.

PDF Abstract ICCV 2017 PDF ICCV 2017 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Action Recognition THUMOS’14 TURN mAP@0.3 46.3 # 7
mAP@0.4 35.3 # 7
mAP@0.5 24.5 # 8
Temporal Action Localization THUMOS’14 TURN-FL-16 + S-CNN mAP IOU@0.5 25.6 # 34
mAP IOU@0.1 54 # 9
mAP IOU@0.2 50.9 # 8
mAP IOU@0.3 44.1 # 32
mAP IOU@0.4 34.9 # 31

Methods


No methods listed for this paper. Add relevant methods here