TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals
Citations Over TimeTop 1% of 2017 papers
Abstract
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 previous 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.
Related Papers
- Keeping Conflicts Latent: "Salient" versus "Non-Salient" Interpersonal Conflict Management Strategies of Japanese(2013)
- Intensive Margin and Extensive Margin Adjustments of Labor Market : Turkey versus United States(2013)
- Detecting Salient Regions Based on "What" and "Where" Pathways of Visual Systems(2006)
- → A Computational Method to Find Salient Features(2008)