ABOUT THE 4th AII WORKSHOP
Schedule
Talks
For this 3-day workshop, we have invited six keynote speakers, 14 guest speakers, and 12 poster presenters. We have also invited Skymizer to hold a technology forum, and Appier and Microsoft Taiwan for recruitment sessions. The topics of the presentations range from computer vision, machine learning and natural language processing to speech recognition, intelligent robotics, and human–computer interaction.
Opening
9 : 50 - 10 : 00
Talks (Keynote)
Keynote Speech (I): 楊明玄 Prof. Ming-Hsuan Yang
Learning to Detect and Segment Objects across Domains
10 : 00 - 10 : 40
Keynote Speech (II): 陳維超 Dr. Wei-Chao Chen
OEM Meets AI: A Cultural and Research Perspective
10 : 40 - 11 : 20
Keynote Speech (III): 賴尚宏 Prof. Shang-Hong Lai
Recent Advances in Facial Recognition
11 : 30 - 12 : 10
Lunch Break
12 : 10 - 13 : 00
Talks (Invited)
Invited Speech (I): 周志遠 Prof. Jerry Chou
Solve Real World Problems By Building & Optimizing ML Pipelines on Kubernetes
13 : 00 - 13 : 25
Invited Speech (II): 楊佳玲 Prof. Chia-Lin Yang
Federated Learning: Application and Challenge
13 : 25 - 13 : 50
Invited Speech (III): 陳縕儂 Prof. Yun-Nung Vivian Chen
Conversational AI Challenges & Trends
13 : 50 - 14 : 15
Invited Speech (IV): 楊奕軒 Prof. Yi-Hsuan Yang
Research on Automatic Music Composition at the Taiwan AI Labs
14 : 15 - 14 : 40
Invited Speech (V): 王鈺強 Prof. Yu-Chiang Frank Wang
Learning to Learn for Visual Classification
14 : 40 - 15 : 05
Invited Speech (VI): 林守德 Prof. Shou-De Lin
Machine Learning as a Service (MLaaS): The Challenges and Opportunities
15 : 05 - 15 : 30
Invited Speech (VII): 孫民 Prof. Min Sun
Building Unfair Advantages - A Case Study of Neural Architecture Search
15 : 30 - 15 : 55
Talks
For this 3-day workshop, we have invited six keynote speakers, 14 guest speakers, and 12 poster presenters. We have also invited Skymizer to hold a technology forum, and Appier and Microsoft Taiwan for recruitment sessions. The topics of the presentations range from computer vision, machine learning and natural language processing to speech recognition, intelligent robotics, and human–computer interaction.
Opening
9 : 50 - 10 : 00
Talks (Keynote)
Keynote Speech (IV): 劉洺堉 Dr. Ming-Yu Liu
Image and video synthesis with Conditional GANs
10 : 00 - 10 : 40
Keynote Speech (V): 阮大成 Dr. Da-Cheng Juan
Neural Structured Learning: Research and Applications
10 : 40 - 11 : 20
Keynote Speech (VI): 謝卓叡 Prof. Cho-Jui Hsieh
On Scalability and Tunibility of Neural Network Optimizers
11 : 30 - 12 : 10
Lunch Break
12 : 10 - 13 : 00
Talks (Invited)
Invited Speech (VIII): 李政德 Prof. Cheng-Te Li
How Powerful are Graph Neural Networks on Social Data Science?
13 : 00 - 13 : 25
Invited Speech (IX): 邱維辰 Prof. Wei-Chen Walon Chiu
Colorization of Depth Map via Disentanglement
13 : 25 - 13 : 50
Invited Speech (X): 李宏毅 Prof. Hung-Yi Lee
Self-supervised Learning and Meta Learning for Human Language Processing
13 : 50 - 14 : 15
Invited Speech (XI): 陳尚澤 Prof. Shang-Tse Chen
Robust Physical Adversarial Attack on Object Detectors
14 : 15 - 14 : 40
Invited Speech (XII): 陳煥宗 Prof. Hwann-Tzong Chen
Learning Object Detection from One Example
14 : 40 - 15 : 05
Invited Speech (XIII): 李濬屹 Prof. Chun-Yi Lee
Deep Reinforcement Learning for Intelligent Robotics
15 : 05 - 15 : 30
Invited Speech (XIV): 鄭龍磻 Prof. Lung-Pan Cheng
Reality Rift: 混合幻想實境
15 : 30 - 15 : 55
Panels, Posters and Recruit
We have invited students who have presented at top conferences, such as CVPR, ICLR, IJCAI, ECCV, and AAAI, to share their research results. In addition, we will have Skymizer to hold a technology forum, and Appier and Microsoft Taiwan for recruitment sessions.
Opening
9 : 50 - 10 : 00
Poster: 蔡育哲 Yu-Che Tsai
DATE: Dual Attentive Tree-aware Embedding for Customs Fraud Detection. KDD 2020.
10 : 00 - 10 : 30
Poster: 李艾霓 Ai-Ni Li
GCAN:Graph-aware Co-Attention Networks for Explainable Fake News Detection on Social Media. ACL 2020.
10 : 30 - 11 : 00
Skymizer 技術論壇 Technology Forum
11 : 00 - 12 : 00
Lunch Break
12 : 00 - 13 : 00
Poster: 宋易霖 Yi-Lin Sung
Difference-Seeking Generative Adversarial Network—Unseen Data Generation. ICLR 2020.
13 : 00 - 13 : 30
Poster: 楊福恩 Fu-En Yang
Learning Identity-Invariant Motion Representations for Cross-ID Face Reenactment. CVPR 2020.
13 : 30 - 14 : 00
Poster: 林志皓 Chih-Hao Lin
Convolution in the Cloud: Learning Deformable Kernels in 3D Graph Convolution Networks for Point Cloud Analysis. CVPR 2020.
14 : 00 - 14 : 30
Poster: 徐晟鈞 Cheng-Chun Hsu
Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector. ECCV 2020.
14 : 30 - 15 : 00
Poster: 葉浩同 Hao-Tung Yeh
Empirical Study of Content Understanding in Conversational Question Answering. AAAI 2020.
15 : 00 - 15 : 30
Poster: 蘇上育 Shang-Yu Su
Towards Unsupervised Language Understanding and Generation by Joint Dual Learning. ACL 2020.
15 : 30 - 16 : 00
Recruit: Appier
16 : 00 - 16 : 20
Recruit: Microsoft Taiwan
16 : 20 - 16 : 40
Poster: 陳泓仁 Hung-Jen Chen
Mitigating Forgetting in Online Continual Learning via Instance-Aware Parameterization. NeurIPS 2020.
16 : 40 - 17 : 10
Poster: 鄭晏奇 Yen-Chi Cheng
Controllable Image Synthesis via SegVAE. ECCV 2020.
17 : 10 - 17 : 40
Poster: 朱彥竹 Yen-Chu Chu
KubeShare: A Framework to Manage GPUs as First-Class and Shared Resources in Container Cloud. HPDC 2020.
17 : 40 - 18 : 10
Poster: 楊炫恭 Hsuan-Kung Yang
Flow Based Intrinsic Curiosity Module. IJCAI 2020.
18 : 10 - 18 : 40
OUR SPEAKERS
Keynote Speakers
楊明玄 (Ming-Hsuan Yang)
Professor, University of California, Merced
Ming-Hsuan Yang is a Professor in Electrical Engineering and Computer Science at University of California, Merced. Professor Yang served as a program co-chair of IEEE International Conference on Computer Vision (ICCV) in 2019, program co-chair of Asian Conference on Computer Vision (ACCV) in 2014, and general co-chair of ACCV 2016. His research interests include computer vision, pattern recognition, AI, robotics, and machine learning.
劉洺堉 (Ming-Yu Liu)
Distinguished Research Scientist and Manager, NVIDIA
Ming-Yu Liu is a Distinguished Research Scientist and Manager at NVIDIA Research. His research interests focus on generative image modeling. His goal is to enable human-like imagination capability in machines.
賴尚宏 (Shang-Hong Lai)
Principal Researcher, Microsoft AI R&D Center
Shang-Hong Lai has been a faculty member in the Department of Computer Science, National Tsing Hua University, since 1999. Since the summer of 2018, Dr. Lai has been on leave to join Microsoft as a principal researcher in the Microsoft AI R&D Center, Taiwan. Dr. Lai’s research interests are mainly focused on computer vision, image processing, and ML. He has authored more than 200 papers that have been published in refereed international journals and conferences in these areas. In addition, he has been awarded around 30 patents on his research on computer vision.
阮大成 (Da-Cheng Juan)
Researcher, Google AI
Da-Cheng received his Ph.D. from the Department of Electrical and Computer Engineering and his Master’s from Machine Learning Department, both at Carnegie Mellon University. His research interests include machine learning and energy-efficient computing. Da-Cheng has published more than 15 papers in the related fields. Meanwhile, he also enjoys algorithmic programming and has won several awards in major programming contests. Currently, Da-Cheng is affiliated with Google Research, working on large-scale, semi-supervised learning and deep learning.
謝卓叡 (Cho-Jui Hsieh)
Assistant Professor, UCLA
Cho-Jui Hsieh's research interests are in developing new algorithms and optimization techniques for large-scale machine learning problems. Currently, he is working on developing new machine learning models as well as improving the model size, training speed, prediction speed, and robustness of popular (deep learning) models.
陳維超 (Wei-Chao Chen)
Wei-Chao Chen is Chief AI Advisor at Inventec Inc. and co-founder at Skywatch Innovation Inc., a leading provider of cloud-based video products and solutions. He is also an adjunct faculty member at National Taiwan University. His research interests include graphics hardware, computational photography, augmented reality, and user interfaces. Dr. Chen was a senior research scientist at the Nokia Research Center at Palo Alto, where he co-authored papers and patents and developed applications related to mobile computer vision and computational photography. Prior to working at Nokia, he was a 3D graphics architect at NVIDIA between 2002 and 2006, and was the shader architecture lead for several GPUs, including the Sony Playstation 3 RSX GPU. While at Intel Corporation during 2000–2001, he co-developed light field mapping technology and the open source light field project (OpenLF)
OUR SPEAKERS
Invited Speakers
OUR ORGANIZERS
Organizers
Co-organizers
Alphabetical order by name.
