Engineering | ASU Active Perception Group (APG) / Yezhou Yang

Yezhou Yang

Yezhou Yang

Assistant Professor, CIDSE, ASU

ASU Barrett Honors Faculty

ASU Keen EM Education Faculty

Global Sport Institute Affiliated Faculty

NVIDIA Deep Learning Institute (DLI) Certified Instructor (for Computer Vision, Natural Language Processing, and Multiple Data Types) and University Ambassador

ASU APG Sponsors:

ASU APG gratefully acknowledges the funding support and gifts from the following organizations to support our research and education activities:


Yezhou Yang is an Assistant Professor at School of Computing, Informatics, and Decision Systems Engineering, Arizona State University.  He is directing the ASU Active Perception Group. Before joining ASU, Dr. Yang was a Postdoctoral Research Associate at the Computer Vision Lab and the Perception and Robotics Lab, with the University of Maryland Institute for Advanced Computer Studies. His primary interests lie in Cognitive Robotics, Computer Vision, and Robot Vision, especially exploring visual primitives in human action understanding from visual input, grounding them by natural language as well as high-level reasoning over the primitives for intelligent robots; His research mainly focused on solutions to visual learning, which significantly reduces the time to program intelligent agents. These solutions involve Computer Vision, Deep Learning, and AI algorithms to interpret peoples’ actions and the scene’s geometry. His research draws on the strengths of the symbolic approach, connectionism, and dynamicism.


699 S Mill Ave.
Tempe, AZ 85281

Email: yz.yang at asu dot edu


Full Publication List

Latest News

  • One workshop is accepted for the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2018) which is among the flagship conferences in the field of robotics. Eren Erdal Aksoy, Yezhou Yang, Karinne Ramirez-Amaro, Neil Dantam, Gordon Cheng: Semantic Policy and Action Representations for Autonomous Robots Conference: 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems

  • Mo Izady: "Convolutional Neural Networks: Ensemble Modeling, Fine-Tuning and Unsupervised Semantic Localization for Neurosurgical CLE Images" has been accepted for publication at the Journal of Visual Communication and Image Representation (JVCI).

  • Our First Workshop on Induce and Deduce: Integrating learning of representations and models with deductive, explainable reasoning that leverages knowledge is accepted at KR 16th International Conference on Principles of Knowledge Representation and Reasoning . More info coming soon.

  • Somak Aditya received a ASU University Graduate Fellowship for the Spring 2018 semester. Congratulations Somak!

  • "Transductive Unbiased Embedding for Zero-Shot Learning ", a collaborative work with Zhejiang University and Alibaba research, has been accepted to appear in CVPR 2018.

  • "Extrinsic Dexterity through Active Slip Control using Deep Predictive Models", a work which is initiated from a class project of the CSE 591 Perception in Robotics course, and a collaboration with the Interactive Robotics Lab at ASU, has been accepted to appear in ICRA 2018. Congratulations to Simon!

  • Yezhou Yang receives the five-year NSF Faculty Early Career Development (CAREER) Award to address the problem of Visual Recognition with Knowledge (VR-K). Project public info

  • Yezhou Yang receives one of the awards of the 2018 round of the inaugural Global Sports Institute (GSI) "Sports 2036" Grant Program. GSI and Adidas ; The winning topic: Non-invasive Performance Tracking with Smart Cameras.

  • Mohammad Farhadi receives ASU Graduate and Professional Student Association (GPSA) Individual Travel Grant and AAAI student volunteer scholarship to attend AAAI 2018.

  • Somak Aditya: "Image Understanding using Vision and Reasoning through Scene Description Graph " has been accepted for publication in Journal of Computer Vision and Image Understanding (CVIU).

  • Somak Aditya: "Explicit Reasoning over End-to-End Neural Architectures for Visual Question Answering " has been accepted for presentation at the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18).

  • Xin Ye: "Collision-free Trajectory Planning in Human-robot Interaction through Hand Movement Prediction from Vision" has been accepted at 2017 Humanoids conference.

  • Yezhou: is invited to present a research poster at the Computing Community Consortium (CCC) Symposium on Computing Research Addressing National Priorities and Societal Needs in Washington, DC on October 23-24,

  • Yezhou: Tech talk "Vision-Language integration challenges and needs in Robotics" at the 3rd integrating Vision and Language training school, Sep 5th, Athens, Greece.

  • Yezhou: Tech talk "Active Perception Beyond Appearance, and its Robotic Applications" at the Brain team, Google Inc.

  • Yezhou: Co-organizing workshop 2nd Workshop on Semantic Policy and Action Representations for Autonomous Robots (SPAR) September 24th 2017 as part of the IROS 2017 conference in Vancouver, Canada.

  • Yezhou: Invited talk "Active Perception Beyond Appearance, and its Robotic Applications" at the Center for Vision, Cognition, Learning and Autonomy, University of California Los Angeles.

  • Somak Aditya Received the University Graduate Fellowship for the Spring 2017 semester. Congratulations!

  • Stephen McAleer has been selected as a Bidstrup Undergraduate Fellow for Spring 2017. Congratulations!

  • Yezhou Yang Received the KEEN Professorship award for Spring Semester 2017 The KEEN Professorship

  • "Prediction of Manipulation Actions" has been accepted for publication on International Journal of Computer Vision (IJCV) preprint draft

  • Three papers are accepted to appear at 2017 International Conference on Robotics and Automation (ICRA). "What Can I Do Around Here? Deep Functional Scene Understanding for Cognitive Robot"; For more information please refer to webpage for data and code.
    "Fast Task-Specific Target Detection via Graph Based Constraints Representation and Checking";
    and "Unsupervised Linking of Visual Features to Textual Descriptions in Long Manipulation Activities" is accepted together with RAL.

  • NEW Manuscript "Answering Image Riddles using Vision and Reasoning through Probabilistic Soft Logic" ; Full dataset and related materials.

  • NEW !!! "Co-active Learning to Adapt Humanoid Movement for Manipulation" is accepted at IEEE-RAS International Conference on Humanoid Robots (Humanoids) 2016.

  • Lightnet package and report is accepted at the ACMMM open source software competition 2016. LightNet: A Versatile, Standalone Matlab-based Environment for Deep Learning and Technical report and git: .
  • NEW !!! One paper is accepted at European Conference on Computer Vision (ECCV) 2016. More information to be uploaded here..
  • Check out our newly posted manuscript: From Images to Sentences through Scene Description Graphs using Commonsense Reasoning and Knowledge. For more information please refer to webpage for data and demonstration of SDGs. Conference version appears at Advances in Cognitive Systems 2016: DeepIU: An Architecture for Image Understanding.