paper-with-me

홈 › Papers

Qiniu Submission to ActivityNet Challenge 2018

2018-06-12 · Xiaoteng Zhang, Yixin Bao, Feiyun Zhang, Kai Hu, Yicheng Wang, Liang Zhu, Qinzhu He, Yining Lin, Jie Shao, Yao Peng

In this paper, we introduce our submissions for the tasks of trimmed activity recognition (Kinetics) and trimmed event recognition (Moments in Time) for Activitynet Challenge 2018. In the two tasks, non-local neural networks and temporal segment networks are implemented as our base models. Multi-modal cues such as RGB image, optical flow and acoustic signal have also been used in our method. We also propose new non-local-based models for further improvement on the recognition accuracy. The final submissions after ensembling the models achieve 83.5% top-1 accuracy and 96.8% top-5 accuracy on the Kinetics validation set, 35.81% top-1 accuracy and 62.59% top-5 accuracy on the MIT validation set.

📄 PDF Abstract BibTeX arXiv:1806.04391

Code (0)

등록된 구현이 없습니다.

Tasks

Activity RecognitionOptical Flow Estimation

Similar Papers 제목 키워드 기반

Dense-Captioning Events in Videos: SYSU Submission to ActivityNet Challenge 2020

2020-06-21 · Teng Wang, Huicheng Zheng, Mingjing Yu

This technical report presents a brief description of our submission to the dense video captioning task of ActivityNet Challenge 2020. Our approach follows a two-stage pipeline: first, we extract a set of temporal event …

Dense CaptioningDense Video CaptioningVideo Captioning

Temporal Convolution Based Action Proposal: Submission to ActivityNet 2017

2017-07-21 · Tianwei Lin, Xu Zhao, Zheng Shou

In this notebook paper, we describe our approach in the submission to the temporal action proposal (task 3) and temporal action localization (task 4) of ActivityNet Challenge hosted at CVPR 2017. Since the accuracy in ac…

Action ClassificationAction LocalizationGeneral ClassificationTemporal Action Localization

Naver at ActivityNet Challenge 2019 -- Task B Active Speaker Detection (AVA)

2019-06-25 · Joon Son Chung

This report describes our submission to the ActivityNet Challenge at CVPR 2019. We use a 3D convolutional neural network (CNN) based front-end and an ensemble of temporal convolution and LSTM classifiers to predict wheth…

Active Speaker DetectionAudio-Visual Active Speaker Detection

iqiyi Submission to ActivityNet Challenge 2019 Kinetics-700 challenge: Hierarchical Group-wise Attention

2020-02-07 · Qian Liu, Dongyang Cai, Jie Liu, Nan Ding 외

In this report, the method for the iqiyi submission to the task of ActivityNet 2019 Kinetics-700 challenge is described. Three models are involved in the model ensemble stage: TSN, HG-NL and StNet. We propose the hierarc…

General ClassificationVideo Classification

CUHK & ETHZ & SIAT Submission to ActivityNet Challenge 2016

2016-08-02 · Yuanjun Xiong, Li-Min Wang, Zhe Wang, Bo-Wen Zhang 외

This paper presents the method that underlies our submission to the untrimmed video classification task of ActivityNet Challenge 2016. We follow the basic pipeline of temporal segment networks and further raise the perfo…

General ClassificationVideo Classification