Paper-Conference

[NeurIPS19] PerspectiveNet: 3D Object Detection from a Single RGB Image via Perspective Points

Detecting 3D objects from a single RGB image is intrinsically ambiguous, thus requiring appropriate prior knowledge and intermediate …

Siyuan Huang, Yixin Chen, Tao Yuan, Siyuan Qi, Yixin Zhu, Song-Chun Zhu

[NeurIPS19] PerspectiveNet: 3D Object Detection from a Single RGB Image via Perspective Points

[ICCV19] Holistic++ Scene Understanding: Single-view 3D Holistic Scene Parsing and Human Pose Estimation with Human-Object Interaction and Physical Commonsense

We propose a new 3D holistic++ scene understanding problem, which jointly tackles two tasks from a single-view image: (i) holistic …

Yixin Chen, Siyuan Huang, Tao Yuan, Yixin Zhu, Siyuan Qi, Song-Chun Zhu

[ICCV19] Holistic++ Scene Understanding: Single-view 3D Holistic Scene Parsing and Human Pose Estimation with Human-Object Interaction and Physical Commonsense

[IROS19] Learning Virtual Grasp with Failed Demonstrations via Bayesian Inverse Reinforcement Learning

We propose Bayesian Inverse Reinforcement Learning with Failure (BIRLF), which makes use of failed demonstrations that were often …

Xu Xie, Changyang Li, Chi Zhang, Yixin Zhu, Song-Chun Zhu

[IROS19] Learning Virtual Grasp with Failed Demonstrations via Bayesian Inverse Reinforcement Learning

[CogSci19] Decomposing Human Causal Learning: Bottom-up Associative Learning and Top-down Schema Reasoning

Transfer learning is fundamental for intelligence; agents expected to operate in novel and unfamiliar environments must be able to …

Mark Edmonds, Siyuan Qi, Yixin Zhu, James Kubricht, Song-Chun Zhu, Hongjing Lu

[CogSci19] Decomposing Human Causal Learning: Bottom-up Associative Learning and Top-down Schema Reasoning

[CVPR19] RAVEN: A Dataset for Relational and Analogical Visual Reasoning

Dramatic progress has been witnessed in basic vision tasks involving low-level perception, such as object recognition, detection, and …

Chi Zhang, Feng Gao, Baoxiong Jia, Yixin Zhu, Song-Chun Zhu

[CVPR19] RAVEN: A Dataset for Relational and Analogical Visual Reasoning

[TURC19] VRGym: A Virtual Testbed for Physical and Interactive AI

We propose VRGym, a virtual reality testbed for realistic human-robot interaction. Different from existing toolkits and virtual reality …

Xu Xie, Hangxin Liu, Zhenliang Zhang, Yuxing Qiu, Feng Gao, Siyuan Qi, Yixin Zhu, Song-Chun Zhu

[TURC19] VRGym: A Virtual Testbed for Physical and Interactive AI

[ICRA19] High-Fidelity Grasping in Virtual Reality using a Glove-based System

This paper presents a design that jointly provides hand pose sensing, hand localization, and haptic feedback to facilitate real-time …

Hangxin Liu, Zhenliang Zhang, Xu Xie, Yixin Zhu, Yue Liu, Yongtian Wang, Song-Chun Zhu

[ICRA19] High-Fidelity Grasping in Virtual Reality using a Glove-based System

[ICRA19] Self-Supervised Incremental Learning for Sound Source Localization in Complex Indoor Environment

This paper presents an incremental learning framework for mobile robots localizing the human sound source using a microphone array in a …

Hangxin Liu, Zeyu Zhang, Yixin Zhu, Song-Chun Zhu

[ICRA19] Self-Supervised Incremental Learning for Sound Source Localization in Complex Indoor Environment

[AAAI19] MetaStyle: Three-Way Trade-Off Among Speed, Flexibility and Quality in Neural Style Transfer

An unprecedented booming has been witnessed in the research area of artistic style transfer ever since Gatys et.al. introduced the …

Chi Zhang, Yixin Zhu, Song-Chun Zhu

[AAAI19] MetaStyle: Three-Way Trade-Off Among Speed, Flexibility and Quality in Neural Style Transfer

[AAAI19] Mirroring without Overimitation: Learning Functionally Equivalent Manipulation Actions

This paper presents a mirroring approach, inspired by the neuroscience discovery of the mirror neurons, to transfer demonstrated …

Hangxin Liu, Chi Zhang, Yixin Zhu, Chenfanfu Jiang, Song-Chun Zhu

[AAAI19] Mirroring without Overimitation: Learning Functionally Equivalent Manipulation Actions