∙ communities, © 2019 Deep AI, Inc. | San Francisco Bay Area | All rights reserved. ... Natural data are often long-tail distributed over semantic classes. Stella X. Yu UC Berkeley / ICSI Verified email at berkeley.edu. Verified email at ie.cuhk.edu.hk - Homepage. arXiv:1711.08488 (2017). 1 Home Ziwei Liu. Berkeley AI Research Blog Citation @inproceedings{compounddomainadaptation, title={Open Compound Domain Adaptation}, author={Liu, Ziwei and Miao, Zhongqi and Pan, Xingang and Zhan, Xiaohang and Lin, Dahua and Yu, Stella X. and Gong, Boqing}, booktitle={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, year={2020} } Zhongqi Miao PhD ... Liu Huawei Technologies CO., LTD. K Chen, J Wang, J Pang, Y Cao, Y Xiong, X Li, S Sun, W Feng, Z Liu, J Xu, ... K Chen, J Pang, J Wang, Y Xiong, X Li, S Sun, W Feng, Z Liu, J Shi, ... IEEE Conference on Computer Vision and Pattern Recognition (CVPR), AAAI Conference on Artificial Intelligence (AAAI), European Conference on Computer Vision (ECCV), Z Liu, Z Miao, X Zhan, J Wang, B Gong, SX Yu, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), Z Liu, L Yuan, X Tang, M Uyttendaele, J Sun, ACM Transactions on Graphics (TOG) 33 (6), 232, X Li, Y Qi, Z Wang, K Chen, Z Liu, J Shi, P Luo, X Tang, CC Loy, CVPR Workshop on DAVIS Video Segmentation Challenge 2017, X Liu, H Yang, Z Liu, L Song, H Li, Y Chen, AAAI Workshop on Artificial Intelligence Safety (SafeAI), Assistant Professor, The University of Hong Kong, Associate Professor of Electronic Engineering, the Chinese University of Hong Kong, Twitter / Imperial College London / University of Lugano, University of Illinois at Urbana–Champaign, Principal Research Manager, Cognition, Cloud & AI, Microsoft, Chief Scientist/Managing Director of Megvii (Face++), Professor of Environmental Sciece, UC Berkeley, Cornerstone Robotics Limited, The Chinese University of Hong Kong, Professor of Computer Science, Johns Hopkins University, Associate Professor, University of British Columbia, Deep Learning Face Attributes in the Wild, Dynamic Graph CNN for Learning on Point Clouds, DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations, Semantic Image Segmentation via Deep Parsing Network, Video Frame Synthesis using Deep Voxel Flow, MMDetection: Open MMLab Detection Toolbox and Benchmark, Hybrid Task Cascade for Instance Segmentation, Not All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade, Face Model Compression by Distilling Knowledge from Neurons, Large-scale Celebfaces Attributes (CelebA) Dataset, Large-Scale Long-Tailed Recognition in an Open World, MaskGAN: Towards Diverse and Interactive Facial Image Manipulation, Adaptive Affinity Field for Semantic Segmentation, Talking Face Generation by Adversarially Disentangled Audio-Visual Representation, Deep Learning Markov Random Field for Semantic Segmentation, Semantic Facial Expression Editing using Autoencoded Flow, Video Object Segmentation with Re-identification, DPatch: An Adversarial Patch Attack on Object Detectors. ∙ share, Recent advances in adversarial attacks uncover the intrinsic vulnerabili... 11 08/23/2020 ∙ by Jiaqi Wang, et al. share, Existing semantic segmentation methods mostly rely on per-pixel supervis... Year Graduated: 2020. 8 Google Scholar; Charles R. Qi, Hao Su, Kaichun Mo, and Leonidas J. Guibas. ∙ 227, 12/20/2020 ∙ by Johannes Czech ∙ 1. 2 Ziwei Liu. claim profile ... Berkeley. share, As facial interaction systems are prevalently deployed, security and pose and expression) transfer, existing ... Instances and Groups, CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Verified email at huawei.com. 0 ∙ Charles R. Qi, Wei Liu, Chenxia Wu, Hao Su, and Leonidas J. Guibas. Awards, Honors and Service; Books and Memoirs; Photos; 150W: History of Women in the Department; ... 367 Evans Hall, University of California ~ Berkeley, CA 94720-3860 ~ 510-642-2781 (Phone) ~ 510-642-7892 (Fax) ~ Contact Us 6 0 While Intelligent agent naturally learns from motion. ... 1 12/02/2017 ∙ by Xiaohang Zhan, et al. share, Learning a good 3D human pose representation is important for human pose... share, Are you a researcher?Expose your workto one of the largestA.I. ∙ ∙ ∙ rel... Stereophonic audio is an indispensable ingredient to enhance human audit... We present a new loss function called Distribution-Balanced Loss for the... Learning a good 3D human pose representation is important for human pose... Place is an important element in visual understanding. Spotlight Presentation Chen Change Loy 104 publications . ∙ ∙ I am a PhD student of VS program at UC Berkeley. ∙ 4 Annotations, Unsupervised Landmark Learning from Unpaired Data, Online Deep Clustering for Unsupervised Representation Learning, Knowledge Distillation Meets Self-Supervision, MMFashion: An Open-Source Toolbox for Visual Fashion Analysis, Learning Diverse Fashion Collocation by Neural Graph Filtering, When NAS Meets Robustness: In Search of Robust Architectures against Ziwei Liu is currently a Nanyang Assistant Professor at School of Computer Science and Engineering (SCSE) in Nanyang Technological University (NTU). Point clouds provide a flexible and scalable geometric representation suitable for countless applications in computer graphics; they also comprise the raw output of most 3D data acquisition devices.