Yang Liu

Demystifying Deep Learning in Predictive Spatio-Temporal Analytics: An Information-Theoretic Framework

Sep 17, 2020
Qi Tan, Yang Liu, Jiming Liu

* 35 pages, 8 figures

Access Model/Code and Paper

Fairness Matters -- A Data-Driven Framework Towards Fair and High Performing Facial Recognition Systems

Sep 16, 2020
Yushi Cao, David Berend, Palina Tolmach, Moshe Levy, Guy Amit, Asaf Shabtai, Yuval Elovici, Yang Liu

* 32 pages, 10 Figures, pre-print, adjusted title

Access Model/Code and Paper

Information Bottleneck Constrained Latent Bidirectional Embedding for Zero-Shot Learning

Sep 16, 2020
Yang Liu, Lei Zhou, Xiao Bai, Lin Gu, Tatsuya Harada, Jun Zhou

* 10 pages, 7 figures, 4 tables

Access Model/Code and Paper

Noisy Self-Knowledge Distillation for Text Summarization

Sep 15, 2020
Yang Liu, Sheng Shen, Mirella Lapata

Access Model/Code and Paper

Light Can Hack Your Face! Black-box Backdoor Attack on Face Recognition Systems

Sep 15, 2020
Haoliang Li, Yufei Wang, Xiaofei Xie, Yang Liu, Shiqi Wang, Renjie Wan, Lap-Pui Chau, Alex C. Kot

* First two authors contributed equally

Access Model/Code and Paper

Are Deep Neural Architectures Losing Information? Invertibility Is Indispensable

Sep 07, 2020
Yang Liu, Zhenyue Qin, Saeed Anwar, Sabrina Caldwell, Tom Gedeon

* ICONIP 2020

Access Model/Code and Paper

Physics-based Shading Reconstruction for Intrinsic Image Decomposition

Sep 03, 2020
Anil S. Baslamisli, Yang Liu, Sezer Karaoglu, Theo Gevers

* Submitted to Computer Vision and Image Understanding (CVIU)

Access Model/Code and Paper

Semantics-aware Adaptive Knowledge Distillation for Sensor-to-Vision Action Recognition

Sep 02, 2020
Yang Liu, Guanbin Li, Liang Lin

* This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible. This paper focuses on the sensor-to-vision heterogenous action recognition problem. Codes is available in https://github.com/YangLiu9208/SAKDN

Access Model/Code and Paper

CORAL: COde RepresentAtion Learning with Weakly-Supervised Transformers for Analyzing Data Analysis

Aug 28, 2020
Ge Zhang, Mike A. Merrill, Yang Liu, Jeffrey Heer, Tim Althoff

Access Model/Code and Paper

FedMVT: Semi-supervised Vertical Federated Learning with MultiView Training

Aug 25, 2020
Yan Kang, Yang Liu, Tianjian Chen

* International Workshop on Federated Learning for User Privacy and Data Confidentiality in Conjunction with IJCAI 2020 (FL-IJCAI'20)

Access Model/Code and Paper

Are Neural Open-Domain Dialog Systems Robust to Speech Recognition Errors in the Dialog History? An Empirical Study

Aug 18, 2020
Karthik Gopalakrishnan, Behnam Hedayatnia, Longshaokan Wang, Yang Liu, Dilek Hakkani-Tur

* Accepted at INTERSPEECH 2020. For dataset, see https://github.com/alexa/Topical-Chat/tree/master/TopicalChatASR/

Access Model/Code and Paper

Unsupervised 3D Learning for Shape Analysis via Multiresolution Instance Discrimination

Aug 03, 2020
Peng-Shuai Wang, Yu-Qi Yang, Qian-Fang Zou, Zhirong Wu, Yang Liu, Xin Tong

Access Model/Code and Paper

The End-of-End-to-End: A Video Understanding Pentathlon Challenge (2020)

Aug 03, 2020
Samuel Albanie, Yang Liu, Arsha Nagrani, Antoine Miech, Ernesto Coto, Ivan Laptev, Rahul Sukthankar, Bernard Ghanem, Andrew Zisserman, Valentin Gabeur, Chen Sun, Karteek Alahari, Cordelia Schmid, Shizhe Chen, Yida Zhao, Qin Jin, Kaixu Cui, Hui Liu, Chen Wang, Yudong Jiang, Xiaoshuai Hao

* Individual reports, dataset information, rules, and released source code can be found at the competition webpage (https://www.robots.ox.ac.uk/~vgg/challenges/video-pentathlon)

Access Model/Code and Paper

FedML: A Research Library and Benchmark for Federated Machine Learning

Jul 27, 2020
Chaoyang He, Songze Li, Jinhyun So, Mi Zhang, Hongyi Wang, Xiaoyang Wang, Praneeth Vepakomma, Abhishek Singh, Hang Qiu, Li Shen, Peilin Zhao, Yan Kang, Yang Liu, Ramesh Raskar, Qiang Yang, Murali Annavaram, Salman Avestimehr

* We maintain the source code, documents, and user community at https://fedml.ai

Access Model/Code and Paper

Incentives for Federated Learning: a Hypothesis Elicitation Approach

Jul 21, 2020
Yang Liu, Jiaheng Wei

Access Model/Code and Paper

Pasadena: Perceptually Aware and Stealthy Adversarial Denoise Attack

Jul 14, 2020
Yupeng Cheng, Qing Guo, Felix Juefei-Xu, Xiaofei Xie, Shang-Wei Lin, Weisi Lin, Wei Feng, Yang Liu

Access Model/Code and Paper

Modeling Voting for System Combination in Machine Translation

Jul 14, 2020
Xuancheng Huang, Jiacheng Zhang, Zhixing Tan, Derek F. Wong, Huanbo Luan, Jingfang Xu, Maosong Sun, Yang Liu

* Accepted by main track of IJCAI2020;SOLE copyright holder is IJCAI (international Joint Conferences on Artificial Intelligence), all rights reserved. https://www.ijcai.org/Proceedings/2020/511

Access Model/Code and Paper

Contextualized Code Representation Learning for Commit Message Generation

Jul 14, 2020
Lun Yiu Nie, Cuiyun Gao, Zhicong Zhong, Wai Lam, Yang Liu, Zenglin Xu

Access Model/Code and Paper

Backdoor attacks and defenses in feature-partitioned collaborative learning

Jul 07, 2020
Yang Liu, Zhihao Yi, Tianjian Chen

* to be published in FL-ICML 2020 workshop

Access Model/Code and Paper

Interpolation between Residual and Non-Residual Networks

Jun 26, 2020
Zonghan Yang, Yang Liu, Chenglong Bao, Zuoqiang Shi

* Accepted at ICML 2020. Code available at https://github.com/minicheshire/InResNet

Access Model/Code and Paper

Does Non-COVID19 Lung Lesion Help? Investigating Transferability in COVID-19 CT Image Segmentation

Jun 23, 2020
Yixin Wang, Yao Zhang, Yang Liu, Jiang Tian, Cheng Zhong, Zhongchao Shi, Yang Zhang, Zhiqiang He

* 9 pages

Access Model/Code and Paper

Distributional Individual Fairness in Clustering

Jun 22, 2020
Nihesh Anderson, Suman K. Bera, Syamantak Das, Yang Liu

Access Model/Code and Paper

AMALGUM -- A Free, Balanced, Multilayer English Web Corpus

Jun 18, 2020
Luke Gessler, Siyao Peng, Yang Liu, Yilun Zhu, Shabnam Behzad, Amir Zeldes

* In Proceedings of The 12th Language Resources and Evaluation Conference (pp. 5267-5275), 2020
* Accepted at LREC 2020. See https://www.aclweb.org/anthology/2020.lrec-1.648/ (note: ACL Anthology's title is currently out of date)

Access Model/Code and Paper

Yang Liu

Demystifying Deep Learning in Predictive Spatio-Temporal Analytics: An Information-Theoretic Framework

Fairness Matters -- A Data-Driven Framework Towards Fair and High Performing Facial Recognition Systems

Information Bottleneck Constrained Latent Bidirectional Embedding for Zero-Shot Learning

Noisy Self-Knowledge Distillation for Text Summarization

Light Can Hack Your Face! Black-box Backdoor Attack on Face Recognition Systems

Are Deep Neural Architectures Losing Information? Invertibility Is Indispensable

Physics-based Shading Reconstruction for Intrinsic Image Decomposition

Semantics-aware Adaptive Knowledge Distillation for Sensor-to-Vision Action Recognition

CORAL: COde RepresentAtion Learning with Weakly-Supervised Transformers for Analyzing Data Analysis

FedMVT: Semi-supervised Vertical Federated Learning with MultiView Training

Are Neural Open-Domain Dialog Systems Robust to Speech Recognition Errors in the Dialog History? An Empirical Study

Unsupervised 3D Learning for Shape Analysis via Multiresolution Instance Discrimination

The End-of-End-to-End: A Video Understanding Pentathlon Challenge (2020)

FedML: A Research Library and Benchmark for Federated Machine Learning

Incentives for Federated Learning: a Hypothesis Elicitation Approach

Pasadena: Perceptually Aware and Stealthy Adversarial Denoise Attack

Modeling Voting for System Combination in Machine Translation

Contextualized Code Representation Learning for Commit Message Generation

Backdoor attacks and defenses in feature-partitioned collaborative learning

Interpolation between Residual and Non-Residual Networks

Does Non-COVID19 Lung Lesion Help? Investigating Transferability in COVID-19 CT Image Segmentation

Distributional Individual Fairness in Clustering

AMALGUM -- A Free, Balanced, Multilayer English Web Corpus

Privacy-Preserving Technology to Help Millions of People: Federated Prediction Model for Stroke Prevention

Differentially Private Decentralized Learning

DeepRhythm: Exposing DeepFakes with Attentional Visual Heartbeat Rhythms

FakePolisher: Making DeepFakes More Detection-Evasive by Shallow Reconstruction

Physics informed deep learning for computational elastodynamics without labeled data