31 citations · 86 across the 21 of their papers we have counts for
22 papers
Enriching Phrases with Coupled Pixel and Object Contexts for Panoptic Narrative Grounding
Tianrui Hui, Zihan Ding, Junshi Huang +5
Panoptic narrative grounding (PNG) aims to segment things and stuff objects in an image described by noun phrases of a narrative caption. As a multimodal task, an essential aspect…
Learning a Universal Human Prior for Dexterous Manipulation from Human Preference
Zihan Ding, Yuanpei Chen, Allen Z. Ren +4
Generating human-like behavior on robots is a great challenge especially in dexterous manipulation tasks with robotic hands. Scripting policies from scratch is intractable due to t…
Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection
Luting Wang, Yi Liu, Penghui Du +5
Open-vocabulary object detection aims to provide object detectors trained on a fixed set of object categories with the generalizability to detect objects described by arbitrary tex…
Anchor3DLane: Learning to Regress 3D Anchors for Monocular 3D Lane Detection
Shaofei Huang, Zhenwei Shen, Zehao Huang +5
Monocular 3D lane detection is a challenging task due to its lack of depth information. A popular solution is to first transform the front-viewed (FV) images or features into the b…
PPMN: Pixel-Phrase Matching Network for One-Stage Panoptic Narrative Grounding
Zihan Ding, Zi-han Ding, Tianrui Hui +4
Panoptic Narrative Grounding (PNG) is an emerging task whose goal is to segment visual objects of things and stuff categories described by dense narrative captions of a still image…
A Deep Reinforcement Learning Approach for Finding Non-Exploitable Strategies in Two-Player Atari Games
Zihan Ding, Dijia Su, Qinghua Liu +1
This paper proposes new, end-to-end deep reinforcement learning algorithms for learning two-player zero-sum Markov games. Different from prior efforts on training agents to beat a…
Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation
Zihan Ding, Tianrui Hui, Junshi Huang +3
Referring video object segmentation aims to predict foreground labels for objects referred by natural language expressions in videos. Previous methods either depend on 3D ConvNets…
Learning Distributed and Fair Policies for Network Load Balancing as Markov Potential Game
Zhiyuan Yao, Zihan Ding
This paper investigates the network load balancing problem in data centers (DCs) where multiple load balancers (LBs) are deployed, using the multi-agent reinforcement learning (MAR…
Multi-Agent Reinforcement Learning for Network Load Balancing in Data Center
Zhiyuan Yao, Zihan Ding, Thomas Clausen
This paper presents the network load balancing problem, a challenging real-world task for multi-agent reinforcement learning (MARL) methods. Traditional heuristic solutions like We…
Reinforced Workload Distribution Fairness
Zhiyuan Yao, Zihan Ding, Thomas Heide Clausen
Network load balancers are central components in data centers, that distributes workloads across multiple servers and thereby contribute to offering scalable services. However, whe…
Not Only Domain Randomization: Universal Policy with Embedding System Identification
Zihan Ding
Domain randomization (DR) cannot provide optimal policies for adapting the learning agent to the dynamics of the environment, although it can generalize sub-optimal policies to wor…
Collaborative Spatial-Temporal Modeling for Language-Queried Video Actor Segmentation
Tianrui Hui, Shaofei Huang, Si Liu +5
Language-queried video actor segmentation aims to predict the pixel-level mask of the actor which performs the actions described by a natural language query in the target frames. E…
Probabilistic Mixture-of-Experts for Efficient Deep Reinforcement Learning
Jie Ren, Yewen Li, Zihan Ding +2
Deep reinforcement learning (DRL) has successfully solved various problems recently, typically with a unimodal policy representation. However, grasping distinguishable skills for s…
DMotion: Robotic Visuomotor Control with Unsupervised Forward Model Learned from Videos
Haoqi Yuan, Ruihai Wu, Andrew Zhao +3
Learning an accurate model of the environment is essential for model-based control tasks. Existing methods in robotic visuomotor control usually learn from data with heavily labell…
Sim-to-Real Transfer for Robotic Manipulation with Tactile Sensory
Zihan Ding, Ya-Yen Tsai, Wang Wei Lee +1
Reinforcement Learning (RL) methods have been widely applied for robotic manipulations via sim-to-real transfer, typically with proprioceptive and visual information. However, the…
DROID: Minimizing the Reality Gap using Single-Shot Human Demonstration
Ya-Yen Tsai, Hui Xu, Zihan Ding +3
Reinforcement learning (RL) has demonstrated great success in the past several years. However, most of the scenarios focus on simulated environments. One of the main challenges of…
Efficient Reinforcement Learning Development with RLzoo
Zihan Ding, Tianyang Yu, Yanhua Huang +5
Many researchers and developers are exploring for adopting Deep Reinforcement Learning (DRL) techniques in their applications. They however often find such an adoption challenging.…
Crossing The Gap: A Deep Dive into Zero-Shot Sim-to-Real Transfer for Dynamics
Eugene Valassakis, Zihan Ding, Edward Johns
Zero-shot sim-to-real transfer of tasks with complex dynamics is a highly challenging and unsolved problem. A number of solutions have been proposed in recent years, but we have fo…
Sim-to-Real Transfer for Optical Tactile Sensing
Zihan Ding, Nathan F. Lepora, Edward Johns
Deep learning and reinforcement learning methods have been shown to enable learning of flexible and complex robot controllers. However, the reliance on large amounts of training da…
Arena: A General Evaluation Platform and Building Toolkit for Multi-Agent Intelligence
Yuhang Song, Andrzej Wojcicki, Thomas Lukasiewicz +6
Learning agents that are not only capable of taking tests, but also innovating is becoming a hot topic in AI. One of the most promising paths towards this vision is multi-agent lea…
TGAN: Deep Tensor Generative Adversarial Nets for Large Image Generation
Zihan Ding, Xiao-Yang Liu, Miao Yin +1
Deep generative models have been successfully applied to many applications. However, existing works experience limitations when generating large images (the literature usually gene…
Deep Reinforcement Learning for Intelligent Transportation Systems
Xiao-Yang Liu, Zihan Ding, Sem Borst +1
Intelligent Transportation Systems (ITSs) are envisioned to play a critical role in improving traffic flow and reducing congestion, which is a pervasive issue impacting urban areas…