209 citations
- Tsinghua UniversityCN19 papers
- University of Science and Technology of ChinaCN14 papers
- OriginWater (China)CN12 papers
- Peking UniversityCN10 papers
- Renmin University of ChinaCN8 papers
- Chinese Academy of SciencesCN7 papers
- National University of SingaporeSG7 papers
- University of Electronic Science and Technology of ChinaCN6 papers
- City University of Hong KongHK5 papers
- Hong Kong University of Science and TechnologyHK5 papers
- Tencent (China)CN5 papers
- University of Chinese Academy of SciencesCN5 papers
13 papers · 1 filter
DeViT: Deformed Vision Transformers in Video Inpainting
Jiayin Cai, Changlin Li, Xin Tao +2
This paper proposes a novel video inpainting method. We make three main contributions: First, we extended previous Transformers with patch alignment by introducing Deformed Patch-b…
Deep Stable Representation Learning on Electronic Health Records
Yingtao Luo, Zhaocheng Liu, Qiang Liu
Deep learning models have achieved promising disease prediction performance of the Electronic Health Records (EHR) of patients. However, most models developed under the I.I.D. hypo…
Billion-user Customer Lifetime Value Prediction: An Industrial-scale Solution from Kuaishou
Kunpeng Li, Guangcui Shao, Naijun Yang +2
Customer Life Time Value (LTV) is the expected total revenue that a single user can bring to a business. It is widely used in a variety of business scenarios to make operational de…
KuaiRand: An Unbiased Sequential Recommendation Dataset with Randomly Exposed Videos
Chongming Gao, Shijun Li, Yuan Zhang +5
Recommender systems deployed in real-world applications can have inherent exposure bias, which leads to the biased logged data plaguing the researchers. A fundamental way to addres…
Fast Learning Radiance Fields by Shooting Much Fewer Rays
Wenyuan Zhang, Ruofan Xing, Yunfan Zeng +3
Learning radiance fields has shown remarkable results for novel view synthesis. The learning procedure usually costs lots of time, which motivates the latest methods to speed up th…
Automatic Quantization for Physics-Based Simulation
Jiafeng Liu, Haoyang Shi, Siyuan Zhang +3
Quantization has proven effective in high-resolution and large-scale simulations, which benefit from bit-level memory saving. However, identifying a quantization scheme that meets…