paper-with-me

홈 › Papers

SST: Single-Stream Temporal Action Proposals

2017-07-01 · CVPR 2017 7 · Shyamal Buch, Victor Escorcia, Chuanqi Shen, Bernard Ghanem, Juan Carlos Niebles

Our paper presents a new approach for temporal detection of human actions in long, untrimmed video sequences. We introduce Single-Stream Temporal Action Proposals (SST), a new effective and efficient deep architecture for the generation of temporal action proposals. Our network can run continuously in a single stream over very long input video sequences, without the need to divide input into short overlapping clips or temporal windows for batch processing. We demonstrate empirically that our model outperforms the state-of-the-art on the task of temporal action proposal generation, while achieving some of the fastest processing speeds in the literature. Finally, we demonstrate that using SST proposals in conjunction with existing action classifiers results in improved state-of-the-art temporal action detection performance.

📄 PDF Abstract BibTeX

Code (1)

shyamal-b/sst 공식 구현

Tasks

Action DetectionTemporal Action Proposal Generation

Similar Papers 제목 키워드 기반

Investigation on Combining 3D Convolution of Image Data and Optical Flow to Generate Temporal Action Proposals

2019-03-11 · Patrick Schlosser, David Münch, Michael Arens

In this paper, several variants of two-stream architectures for temporal action proposal generation in long, untrimmed videos are presented. Inspired by the recent advances in the field of human action recognition utiliz…

Action RecognitionOptical Flow EstimationTemporal Action LocalizationTemporal Action Proposal Generation

Temporally Object-based Video Co-Segmentation

2018-02-09 · Michael Ying Yang, Matthias Reso, Jun Tang, Wentong Liao 외

In this paper, we propose an unsupervised video object co-segmentation framework based on the primary object proposals to extract the common foreground object(s) from a given video set. In addition to the objectness attr…

ObjectSegmentation

Improving Action Localization by Progressive Cross-stream Cooperation

2019-05-28 · CVPR 2019 6 · Rui Su, Wanli Ouyang, Luping Zhou, Dong Xu

Spatio-temporal action localization consists of three levels of tasks: spatial localization, action classification, and temporal segmentation. In this work, we propose a new Progressive Cross-stream Cooperation (PCSC) fr…

Action ClassificationAction DetectionAction LocalizationSpatio-Temporal Action Localization+1

Fast Learning of Temporal Action Proposal via Dense Boundary Generator

2019-11-11 · Chuming Lin, Jian Li, Yabiao Wang, Ying Tai 외

Generating temporal action proposals remains a very challenging problem, where the main issue lies in predicting precise temporal proposal boundaries and reliable action confidence in long and untrimmed real-world videos…

General ClassificationOptical Flow EstimationregressionTemporal Action Localization

Decoupling Localization and Classification in Single Shot Temporal Action Detection

2019-04-16 · Yupan Huang, Qi Dai, Yutong Lu

Video temporal action detection aims to temporally localize and recognize the action in untrimmed videos. Existing one-stage approaches mostly focus on unifying two subtasks, i.e., localization of action proposals and cl…

Action DetectionClassificationGeneral ClassificationTemporal Action Localization