paper-with-me

Papers

Proposal Relation Network for Temporal Action Detection

2021-06-20 · Xiang Wang, Zhiwu Qing, Ziyuan Huang, Yutong Feng, Shiwei Zhang, Jianwen Jiang, Mingqian Tang, Changxin Gao, Nong Sang

This technical report presents our solution for temporal action detection task in AcitivityNet Challenge 2021. The purpose of this task is to locate and identify actions of interest in long untrimmed videos. The crucial challenge of the task comes from that the temporal duration of action varies dramatically, and the target actions are typically embedded in a background of irrelevant activities. Our solution builds on BMN, and mainly contains three steps: 1) action classification and feature encoding by Slowfast, CSN and ViViT; 2) proposal generation. We improve BMN by embedding the proposed Proposal Relation Network (PRN), by which we can generate proposals of high quality; 3) action detection. We calculate the detection results by assigning the proposals with corresponding classification results. Finally, we ensemble the results under different settings and achieve 44.7% on the test set, which improves the champion result in ActivityNet 2020 by 1.9% in terms of average mAP.

📄 PDF Abstract BibTeX arXiv:2106.11812

Code (1)

wangxiang1230/SSTAP pytorch

Tasks

Action ClassificationAction DetectionRelationRelation NetworkTemporal Action Localization

Similar Papers 제목 키워드 기반

Complementary Boundary Generator with Scale-Invariant Relation Modeling for Temporal Action Localization: Submission to ActivityNet Challenge 2020

2020-07-20 · Haisheng Su, Jinyuan Feng, Hao Shao, Zhenyu Jiang 외

This technical report presents an overview of our solution used in the submission to ActivityNet Challenge 2020 Task 1 (\textbf{temporal action localization/detection}). Temporal action localization requires to not only …

Action LocalizationDiversityTemporal Action Localization

AEI: Actors-Environment Interaction with Adaptive Attention for Temporal Action Proposals Generation

2021-10-21 · Khoa Vo, Hyekang Joo, Kashu Yamazaki, Sang Truong 외

Humans typically perceive the establishment of an action in a video through the interaction between an actor and the surrounding environment. An action only starts when the main actor in the video begins to interact with…

Action DetectionTemporal Action Proposal Generation

Recurrent Tubelet Proposal and Recognition Networks for Action Detection

2018-09-01 · ECCV 2018 9 · Dong Li, Zhaofan Qiu, Qi Dai, Ting Yao 외

Detecting actions in videos is a challenging task as video is an information intensive media with complex variations. Existing approaches predominantly generate action proposals for each individual frame or fixed-length …

Action DetectionRegion Proposal

Boundary Content Graph Neural Network for Temporal Action Proposal Generation

2020-08-04 · ECCV 2020 8 · Yueran Bai, Yingying Wang, Yunhai Tong, Yang Yang 외

Temporal action proposal generation plays an important role in video action understanding, which requires localizing high-quality action content precisely. However, generating temporal proposals with both precise boundar…

Action DetectionAction UnderstandingGraph Neural NetworkTemporal Action Localization+1

What and When to Look?: Temporal Span Proposal Network for Video Relation Detection

2021-07-15 · Sangmin Woo, Junhyug Noh, Kangil Kim

Identifying relations between objects is central to understanding the scene. While several works have been proposed for relation modeling in the image domain, there have been many constraints in the video domain due to c…

RelationVideo Visual Relation DetectionVideo Visual Relation Tagging