Self-Supervised Marine Video Analysis via Siamese Network

被引：0
作者：
Liang, Ju [1 ]
Song, Jihan [1 ,2 ]
Li, Qianqian [1 ]
Shi, Zhensheng [1 ,3 ]
Gu, Zhaorui [1 ]
Zheng, Haiyong [1 ]
Zheng, Bing [1 ,4 ]
机构：
[1] Ocean Univ China, Underwater Vis Lab Ouc Ai, Qingdao, Peoples R China
[2] Ocean Univ China, Coll Informat Sci & Engn, Qingdao, Peoples R China
[3] Ocean Univ China, Frontiers Sci Ctr Deep Ocean Multispheres & Earth, Qingdao, Peoples R China
[4] Ocean Univ China, Sanya Oceanog Inst, Qingdao, Peoples R China
来源：
OCEANS 2021: SAN DIEGO - PORTO | 2021年
基金：
中国国家自然科学基金;
关键词：
Self-supervised learning; Marine video analysis; Siamese network; Marine organism detection; Marine scene recognition; Marine organism action recognition; SCENE;
D O I：
暂无
中图分类号：
U6 [水路运输]; P75 [海洋工程];
学科分类号：
0814 ; 081505 ; 0824 ; 082401 ;
摘要：
At present, advanced equipment has provided strong data support for marine scientific research. However, it is unrealistic to rely on manpower analysis to analyze the huge amount of data. Therefore, it is an effective and good method to use computer vision method to automatically identify and analyze marine video. In this paper, a self-supervised learning method based on siamese network is designed to learn the effective visual representation in marine unlabeled video, and the model is transferred to three downstream tasks: marine organism action recognition, marine organism detection, and marine scene recognition. We are on the latest dataset to experiment to evaluation the effectiveness of our method. Experimental results show that our method has certain competitiveness and effectiveness in the three downstream tasks.
引用
收藏
页数：7
相关论文
共 42 条
[31]   MULTISENSOR INTEGRATION FOR UNDERWATER SCENE CLASSIFICATION [J].
NANDHAKUMAR, N ;
MALIK, S .
APPLIED INTELLIGENCE, 1995, 5 (03) :207-216
[32]   Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles [J].
Noroozi, Mehdi ;
Favaro, Paolo .
COMPUTER VISION - ECCV 2016, PT VI, 2016, 9910 :69-84
[33]   Modeling the shape of the scene: A holistic representation of the spatial envelope [J].
Oliva, A ;
Torralba, A .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2001, 42 (03) :145-175
[34]  
Redmon J., 2015, YOU ONLY LOOK ONCE U, DOI [10.1109/CVPR.2016.91, DOI 10.1109/CVPR.2016.91]
[35]   Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks [J].
Ren, Shaoqing ;
He, Kaiming ;
Girshick, Ross ;
Sun, Jian .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2017, 39 (06) :1137-1149
[36]  
Shrivakshan G., 2012, International Journal of Computer Science Issues, V9, P269
[37]  
Soori U., 2009, UNDERWATER CROWD FLO
[38]  
Spampinato C., 2010, P 1 ACM INT WORKSH A, P45
[39]  
Spampinato C, 2008, VISAPP 2008: PROCEEDINGS OF THE THIRD INTERNATIONAL CONFERENCE ON COMPUTER VISION THEORY AND APPLICATIONS, VOL 2, P514
[40]  
Sung M, 2017, OCEANS-IEEE
12345