Oral 1.2: Deep Network and Learning

All date and time in the Technical Program is based on Hong Kong Standard Time (GMT+8) I

 

Date: December 2, 2020 (Wednesday)
Time: 10:30-12:30
Chairs: xxx, University of Science and Technology of China
xxx, Hong Kong Polytechnic University
O1.2.1 HDR Image Compression with Convolutional Autoencoder
Author11, Author21, Author32, Author41, Author51
1Faculty of Information Technology, Beijing University of Technology, China, 2Institute of Digital Media, Peking University, China
O1.2.2 Mining Larger Class Activation Map with Common Attribute Labels
Author1, Author2
School of Information and Communication Engineering, University of Electronic Science and Technology of China, China
O1.2.3 Orthogonal Features Fusion Network for Anomaly Detection
Author11, Author22, Author33, Author43,4, Author51
1Department of Computer Science and Engineering, University at Buffalo, USA; 2Beijing University of Posts and Telecommunications, China; 3School of Automation and Electrical Engineering, Beihang University, China; 4Shenzhen Academy of Aerospace Technology, China
O1.2.4 Network Update Compression for Federated Learning
Author11, Author21, Author31, Author42, Author53
1University of Missouri-Kansas City, USA; 2Peking University, China; 3Tencent America, USA
O1.2.5 Efficient Light Deep Network for Street Scene Parsing
ZheHui Wang1, Sanyuan Zhao1, Jianbing Shen1, Zhengchao Lei2
1Beijing Institute of Technology, China; 2Coordination Center of China, China
O1.2.6 Compressing Facial Makeup Transfer Networks by Collaborative Distillation and Kernel Decomposition
Author11, Author22, Author32, Author42, Author52
1Chu Kochen Honors College, Zhejiang University, China; 2College of Information Science and Electronic Engineering, Zhejiang University, China


O1.2.1: HDR Image Compression with Convolutional Autoencoder
Author11, Author21, Author32, Author41, Author51
1Faculty of Information Technology, Beijing University of Technology, China, 2Institute of Digital Media, Peking University, China

Presenter: xxx

Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.

 

Abstract

Sed ut perspiciatis unde omnis iste natus error sit voluptatem accusantium doloremque laudantium, totam rem aperiam, eaque ipsa quae ab illo inventore veritatis et quasi architecto beatae vitae dicta sunt explicabo. Nemo enim ipsam voluptatem quia voluptas sit aspernatur aut odit aut fugit, sed quia consequuntur magni dolores eos qui ratione voluptatem sequi nesciunt. Neque porro quisquam est, qui dolorem ipsum quia dolor sit amet, consectetur, adipisci velit, sed quia non numquam eius modi tempora incidunt ut labore et dolore magnam aliquam quaerat voluptatem.

 


O1.2.2: Mining Larger Class Activation Map with Common Attribute Labels
Author1, Author2
School of Information and Communication Engineering, University of Electronic Science and Technology of China, China

Presenter: xxx

Ut enim ad minima veniam, quis nostrum exercitationem ullam corporis suscipit laboriosam, nisi ut aliquid ex ea commodi consequatur? Quis autem vel eum iure reprehenderit qui in ea voluptate velit esse quam nihil molestiae consequatur, vel illum qui dolorem eum fugiat quo voluptas nulla pariatur.

 

Abstract

At vero eos et accusamus et iusto odio dignissimos ducimus qui blanditiis praesentium voluptatum deleniti atque corrupti quos dolores et quas molestias excepturi sint occaecati cupiditate non provident, similique sunt in culpa qui officia deserunt mollitia animi, id est laborum et dolorum fuga. Et harum quidem rerum facilis est et expedita distinctio. Nam libero tempore, cum soluta nobis est eligendi optio cumque nihil impedit quo minus id quod maxime placeat facere possimus, omnis voluptas assumenda est, omnis dolor repellendus. Temporibus autem quibusdam et aut officiis debitis aut rerum necessitatibus saepe eveniet ut et voluptates repudiandae sint et molestiae non recusandae.

 


O1.2.3: Orthogonal Features Fusion Network for Anomaly Detection
Author11, Author22, Author33, Author43,4, Author51
1Department of Computer Science and Engineering, University at Buffalo, USA; 2Beijing University of Posts and Telecommunications, China; 3School of Automation and Electrical Engineering, Beihang University, China; 4Shenzhen Academy of Aerospace Technology, China

Presenter: xxx

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Suspendisse pretium pellentesque est, ut consequat neque dapibus id. Integer commodo pellentesque sapien posuere pulvinar. Sed sit amet maximus nulla. Cras a sagittis ante. Etiam tristique gravida porttitor. Nam rutrum ornare diam, vitae sollicitudin metus tristique et. Pellentesque urna massa, rhoncus non vestibulum in, hendrerit eu mauris. Proin consequat scelerisque nibh sit amet pretium. Praesent at dapibus lorem, nec faucibus leo.

Abstract

Cras a mauris lectus. Sed imperdiet pulvinar nisi, ut rutrum orci mollis sed. Etiam eleifend at tortor ut aliquet. Vivamus sem orci, vulputate vel leo vitae, facilisis interdum magna. Pellentesque finibus pretium erat ac posuere. Aenean varius congue mauris, et vehicula tortor. Mauris dapibus semper massa, sed dignissim diam molestie sit amet. Vestibulum ante ipsum primis in faucibus orci luctus et ultrices posuere cubilia curae.

 


O1.2.4: Network Update Compression for Federated Learning
Author11, Author21, Author31, Author42, Author53
1University of Missouri-Kansas City, USA; 2Peking University, China; 3Tencent America, USA

Presenter: xxx

Maecenas molestie enim ut congue consequat. Ut sollicitudin, est sit amet egestas vestibulum, mi eros venenatis ex, a feugiat arcu nulla eu urna. Donec aliquet, massa nec iaculis dapibus, mi quam scelerisque purus, sit amet vulputate risus tortor quis leo. Pellentesque non accumsan mi, facilisis porta lacus. Vestibulum luctus nec augue ut dictum. Duis rhoncus tellus in quam condimentum, eget convallis arcu pretium.

 

Abstract

Morbi tincidunt laoreet urna sed volutpat. Vestibulum et finibus urna, sed faucibus metus. Sed scelerisque erat erat, sed varius neque consectetur quis. Suspendisse vulputate urna urna. Morbi eleifend tristique accumsan. Ut vulputate molestie ex ac porta. Phasellus in tellus orci. Nulla sed mi vel arcu congue tincidunt. In feugiat diam et nibh accumsan aliquam. Morbi a hendrerit neque, vitae accumsan lorem. Ut ullamcorper vulputate urna, id sodales massa convallis nec. Pellentesque rhoncus tempus mattis.

 


O1.2.5: Efficient Light Deep Network for Street Scene Parsing
Author11, Author21, Author31, Author42
1Beijing Institute of Technology, China; 2Coordination Center of China, China

Presenter: xxx

Nunc nec nibh dui. Pellentesque ac mollis ante. Praesent porttitor libero tellus, a aliquet est maximus at. Fusce sollicitudin consectetur pellentesque. Morbi massa erat, rutrum non sodales quis, ullamcorper in arcu. Curabitur fringilla lectus ut neque tristique posuere. Donec eu finibus nibh. Nam enim nulla, dictum sed enim id, facilisis luctus turpis. Quisque nisi mauris, blandit quis interdum et, pellentesque eu nisi.

 

Abstract

Duis a nisi mattis, vestibulum lacus eu, volutpat libero. Suspendisse tincidunt imperdiet bibendum. Mauris quis mattis turpis. Suspendisse posuere vehicula nibh, nec porta magna egestas sed. Praesent fermentum auctor sapien, in tristique libero ultrices ac. Suspendisse vulputate at lorem at egestas.

 


O1.2.6: Compressing Facial Makeup Transfer Networks by Collaborative Distillation and Kernel Decomposition
Author11, Author22, Author32, Author42, Author52
1Chu Kochen Honors College, Zhejiang University, China; 2College of Information Science and Electronic Engineering, Zhejiang University, China

Presenter: xxx

Vivamus lobortis augue felis, a rutrum metus consectetur vel. Aliquam vitae felis ut urna facilisis aliquam non eget quam. Quisque ullamcorper nulla dui, in sollicitudin tellus luctus in. Duis dictum nunc sit amet ultrices feugiat. Maecenas id pharetra sapien. Nam semper rhoncus sem vitae tempus.

 

Abstract

Sed accumsan felis eu ultrices iaculis. Suspendisse iaculis lacus semper nisl molestie, quis iaculis dui eleifend. Maecenas accumsan purus ut dolor auctor, a tempus nunc iaculis. Quisque aliquam erat sit amet augue pharetra, vel cursus felis bibendum. Curabitur suscipit, nibh sit amet pretium tempor, ex libero rhoncus enim, vitae laoreet elit nisi ac lectus. In at nulla mattis, congue nisi quis, fermentum augue. Donec consectetur accumsan justo, ac mattis tortor vehicula ac.