Author pages are created from data sourced from our academic publisher partnerships and public sources.
- Publications
- Influence
Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations
- R. Krishna, Yuke Zhu, +9 authors Li Fei-Fei
- Computer Science
- International Journal of Computer Vision
- 23 February 2016
Despite progress in perceptual tasks such as image classification, computers still perform poorly on cognitive tasks such as image description and question answering. Cognition is core to tasks that… Expand
Scene Graph Generation by Iterative Message Passing
- Danfei Xu, Yuke Zhu, Christopher B. Choy, Li Fei-Fei
- Computer Science
- IEEE Conference on Computer Vision and Pattern…
- 10 January 2017
Understanding a visual scene goes beyond recognizing individual objects in isolation. Relationships between objects also constitute rich semantic information about the scene. In this work, we… Expand
Target-driven visual navigation in indoor scenes using deep reinforcement learning
- Yuke Zhu, R. Mottaghi, +4 authors Ali Farhadi
- Computer Science, Engineering
- IEEE International Conference on Robotics and…
- 16 September 2016
Two less addressed issues of deep reinforcement learning are (1) lack of generalization capability to new goals, and (2) data inefficiency, i.e., the model requires several (and often costly)… Expand
Visual7W: Grounded Question Answering in Images
- Yuke Zhu, O. Groth, Michael S. Bernstein, Li Fei-Fei
- Computer Science
- IEEE Conference on Computer Vision and Pattern…
- 11 November 2015
We have seen great progress in basic perceptual tasks such as object recognition and detection. However, AI models still fail to match humans in high-level vision tasks due to the lack of capacities… Expand
DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion
- C. Wang, Danfei Xu, +4 authors S. Savarese
- Computer Science
- IEEE/CVF Conference on Computer Vision and…
- 15 January 2019
A key technical challenge in performing 6D object pose estimation from RGB-D image is to fully leverage the two complementary data sources. Prior works either extract information from the RGB image… Expand
AI2-THOR: An Interactive 3D Environment for Visual AI
- Eric Kolve, R. Mottaghi, D. Gordon, Yuke Zhu, A. Gupta, Ali Farhadi
- Computer Science
- ArXiv
- 14 December 2017
We introduce The House Of inteRactions (THOR), a framework for visual AI research, available at this http URL AI2-THOR consists of near photo-realistic 3D indoor scenes, where AI agents can navigate… Expand
Reasoning about Object Affordances in a Knowledge Base Representation
- Yuke Zhu, Alireza Fathi, Li Fei-Fei
- Computer Science
- ECCV
- 6 September 2014
Reasoning about objects and their affordances is a fundamental problem for visual intelligence. Most of the previous work casts this problem as a classification task where separate classifiers are… Expand
SURREAL: Open-Source Reinforcement Learning Framework and Robot Manipulation Benchmark
- Linxi (Jim) Fan, Yuke Zhu, +6 authors Li Fei-Fei
- Computer Science
- CoRL
- 23 October 2018
Reproducibility has been a significant challenge in deep reinforcement learning and robotics research. Open-source frameworks and standardized benchmarks can serve an integral role in rigorous… Expand
Neural Task Programming: Learning to Generalize Across Hierarchical Tasks
- Danfei Xu, Suraj Nair, +4 authors S. Savarese
- Computer Science, Engineering
- IEEE International Conference on Robotics and…
- 4 October 2017
In this work, we propose a novel robot learning framework called Neural Task Programming (NTP), which bridges the idea of few-shot learning from demonstration and neural program induction. NTP takes… Expand
Reinforcement and Imitation Learning for Diverse Visuomotor Skills
- Yuke Zhu, Ziyu Wang, +8 authors N. Heess
- Engineering, Computer Science
- Robotics: Science and Systems
- 15 February 2018
We propose a model-free deep reinforcement learning method that leverages a small amount of demonstration data to assist a reinforcement learning agent. We apply this approach to robotic manipulation… Expand