106 citations · 1k across the 95 of their papers we have counts for
18 papers · 1 filter
Offline Policy Selection under Uncertainty
Mengjiao Yang, Bo Dai, Ofir Nachum +2
The presence of uncertainty in policy evaluation significantly complicates the process of policy ranking and selection in real-world settings. We formally consider offline policy s…
Slow Control System for PandaX-III experiment
Xiyu Yan, Xun Chen, Yu Chen +9
The PandaX-III experiment uses high pressure gaseous time projection chamber to search for the neutrinoless double beta decay of Xe. A modular slow control system~(SCS) has…
Focal Frequency Loss for Image Reconstruction and Synthesis
Liming Jiang, Bo Dai, Wayne Wu +1
Image reconstruction and synthesis have witnessed remarkable progress thanks to the development of generative models. Nonetheless, gaps could still exist between the real and gener…
Learning Discrete Energy-based Models via Auxiliary-variable Local Exploration
Hanjun Dai, Rishabh Singh, Bo Dai +2
Discrete structures play an important role in applications like program language modeling and software engineering. Current approaches to predicting complex structures typically co…
Do 2D GANs Know 3D Shape? Unsupervised 3D shape reconstruction from 2D Image GANs
Xingang Pan, Bo Dai, Ziwei Liu +2
Natural images are projections of 3D objects on a 2D image plane. While state-of-the-art 2D generative models like GANs show unprecedented quality in modeling the natural image man…
Named Entity Recognition for Social Media Texts with Semantic Augmentation
Yuyang Nie, Yuanhe Tian, Xiang Wan +2
Existing approaches for named entity recognition suffer from data sparsity problems when conducted on short and informal texts, especially user-generated social media content. Sema…
CoinDICE: Off-Policy Confidence Interval Estimation
Bo Dai, Ofir Nachum, Yinlam Chow +3
We study high-confidence behavior-agnostic off-policy evaluation in reinforcement learning, where the goal is to estimate a confidence interval on a target policy's value, given on…
Unsupervised Landmark Learning from Unpaired Data
Yinghao Xu, Ceyuan Yang, Ziwei Liu +2
Recent attempts for unsupervised landmark learning leverage synthesized image pairs that are similar in appearance but different in poses. These methods learn landmarks by encourag…
Video Representation Learning with Visual Tempo Consistency
Ceyuan Yang, Yinghao Xu, Bo Dai +1
Visual tempo, which describes how fast an action goes, has shown its potential in supervised action recognition. In this work, we demonstrate that visual tempo can also serve as a…
Zeroth-Order Supervised Policy Improvement
Hao Sun, Ziping Xu, Yuhang Song +4
Policy gradient (PG) algorithms have been widely used in reinforcement learning (RL). However, PG algorithms rely on exploiting the value function being learned with the first-orde…
Intra- and Inter-Action Understanding via Temporal Action Parsing
Dian Shao, Yue Zhao, Bo Dai +1
Current methods for action recognition primarily rely on deep convolutional networks to derive feature embeddings of visual and motion features. While these methods have demonstrat…
Novel Policy Seeking with Constrained Optimization
Hao Sun, Zhenghao Peng, Bo Dai +3
In problem-solving, we humans can come up with multiple novel solutions to the same problem. However, reinforcement learning algorithms can only produce a set of monotonous policie…
Evolutionary Stochastic Policy Distillation
Hao Sun, Xinyu Pan, Bo Dai +2
Solving the Goal-Conditioned Reward Sparse (GCRS) task is a challenging reinforcement learning problem due to the sparsity of reward signals. In this work, we propose a new formula…
FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding
Dian Shao, Yue Zhao, Bo Dai +1
On public benchmarks, current action recognition techniques have achieved great success. However, when used in real-world applications, e.g. sport analysis, which requires the capa…
Self-Supervised Scene De-occlusion
Xiaohang Zhan, Xingang Pan, Bo Dai +3
Natural scene understanding is a challenging task, particularly when encountering images of multiple objects that are partially occluded. This obstacle is given rise by varying obj…
Temporal Pyramid Network for Action Recognition
Ceyuan Yang, Yinghao Xu, Jianping Shi +2
Visual tempo characterizes the dynamics and the temporal scale of an action. Modeling such visual tempos of different actions facilitates their recognition. Previous works often ca…
Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
Xingang Pan, Xiaohang Zhan, Bo Dai +3
Learning a good image prior is a long-term goal for image restoration and manipulation. While existing methods like deep image prior (DIP) capture low-level image statistics, there…
Real or Not Real, that is the Question
Yuanbo Xiangli, Yubin Deng, Bo Dai +2
While generative adversarial networks (GAN) have been widely adopted in various topics, in this paper we generalize the standard GAN to a new perspective by treating realness as a…