Kuan-Chuan Peng

Kuan-Chuan Peng
  • Biography

    Before joining MERL, he was a Research Scientist (2016-2018) and Staff Scientist (2019) at Siemens Corporate Technology. His PhD research focuses on solving abstract tasks in computer vision using convolutional neural networks. In addition to his PhD, he received a bachelor's degree in Electrical Engineering and an MS degree in Computer Science and Information Engineering from National Taiwan University in 2009 and 2012 respectively. His research interests include incremental learning, developing practical solutions given biased or scarce data, and fundamental computer vision and machine learning problems.

  • Recent News & Events

    •  NEWS    MERL researchers presenting four papers and organizing the VLAR-SMART101 Workshop at ICCV 2023
      Date: October 2, 2023 - October 6, 2023
      Where: Paris/France
      MERL Contacts: Moitreya Chatterjee; Anoop Cherian; Michael J. Jones; Toshiaki Koike-Akino; Suhas Lohit; Tim K. Marks; Pedro Miraldo; Kuan-Chuan Peng; Ye Wang
      Research Areas: Artificial Intelligence, Computer Vision, Machine Learning
      Brief
      • MERL researchers are presenting 4 papers and organizing the VLAR-SMART-101 workshop at the ICCV 2023 conference, which will be held in Paris, France October 2-6. ICCV is one of the most prestigious and competitive international conferences in computer vision. Details are provided below.

        1. Conference paper: “Steered Diffusion: A Generalized Framework for Plug-and-Play Conditional Image Synthesis,” by Nithin Gopalakrishnan Nair, Anoop Cherian, Suhas Lohit, Ye Wang, Toshiaki Koike-Akino, Vishal Patel, and Tim K. Marks

        Conditional generative models typically demand large annotated training sets to achieve high-quality synthesis. As a result, there has been significant interest in plug-and-play generation, i.e., using a pre-defined model to guide the generative process. In this paper, we introduce Steered Diffusion, a generalized framework for fine-grained photorealistic zero-shot conditional image generation using a diffusion model trained for unconditional generation. The key idea is to steer the image generation of the diffusion model during inference via designing a loss using a pre-trained inverse model that characterizes the conditional task. Our model shows clear qualitative and quantitative improvements over state-of-the-art diffusion-based plug-and-play models, while adding negligible computational cost.

        2. Conference paper: "BANSAC: A dynamic BAyesian Network for adaptive SAmple Consensus," by Valter Piedade and Pedro Miraldo

        We derive a dynamic Bayesian network that updates individual data points' inlier scores while iterating RANSAC. At each iteration, we apply weighted sampling using the updated scores. Our method works with or without prior data point scorings. In addition, we use the updated inlier/outlier scoring for deriving a new stopping criterion for the RANSAC loop. Our method outperforms the baselines in accuracy while needing less computational time.

        3. Conference paper: "Robust Frame-to-Frame Camera Rotation Estimation in Crowded Scenes," by Fabien Delattre, David Dirnfeld, Phat Nguyen, Stephen Scarano, Michael J. Jones, Pedro Miraldo, and Erik Learned-Miller

        We present a novel approach to estimating camera rotation in crowded, real-world scenes captured using a handheld monocular video camera. Our method uses a novel generalization of the Hough transform on SO3 to efficiently find the camera rotation most compatible with the optical flow. Because the setting is not addressed well by other data sets, we provide a new dataset and benchmark, with high-accuracy and rigorously annotated ground truth on 17 video sequences. Our method is more accurate by almost 40 percent than the next best method.

        4. Workshop paper: "Tensor Factorization for Leveraging Cross-Modal Knowledge in Data-Constrained Infrared Object Detection" by Manish Sharma*, Moitreya Chatterjee*, Kuan-Chuan Peng, Suhas Lohit, and Michael Jones

        While state-of-the-art object detection methods for RGB images have reached some level of maturity, the same is not true for Infrared (IR) images. The primary bottleneck towards bridging this gap is the lack of sufficient labeled training data in the IR images. Towards addressing this issue, we present TensorFact, a novel tensor decomposition method which splits the convolution kernels of a CNN into low-rank factor matrices with fewer parameters. This compressed network is first pre-trained on RGB images and then augmented with only a few parameters. This augmented network is then trained on IR images, while freezing the weights trained on RGB. This prevents it from over-fitting, allowing it to generalize better. Experiments show that our method outperforms state-of-the-art.

        5. “Vision-and-Language Algorithmic Reasoning (VLAR) Workshop and SMART-101 Challenge” by Anoop Cherian,  Kuan-Chuan Peng, Suhas Lohit, Tim K. Marks, Ram Ramrakhya, Honglu Zhou, Kevin A. Smith, Joanna Matthiesen, and Joshua B. Tenenbaum

        MERL researchers along with researchers from MIT, GeorgiaTech, Math Kangaroo USA, and Rutgers University are jointly organizing a workshop on vision-and-language algorithmic reasoning at ICCV 2023 and conducting a challenge based on the SMART-101 puzzles described in the paper: Are Deep Neural Networks SMARTer than Second Graders?. A focus of this workshop is to bring together outstanding faculty/researchers working at the intersections of vision, language, and cognition to provide their opinions on the recent breakthroughs in large language models and artificial general intelligence, as well as showcase their cutting edge research that could inspire the audience to search for the missing pieces in our quest towards solving the puzzle of artificial intelligence.

        Workshop link: https://wvlar.github.io/iccv23/
    •  
    •  NEWS    MERL researchers presenting four papers and co-organizing a workshop at CVPR 2023
      Date: June 18, 2023 - June 22, 2023
      Where: Vancouver/Canada
      MERL Contacts: Anoop Cherian; Michael J. Jones; Suhas Lohit; Kuan-Chuan Peng
      Research Areas: Artificial Intelligence, Computer Vision, Machine Learning
      Brief
      • MERL researchers are presenting 4 papers and co-organizing a workshop at the CVPR 2023 conference, which will be held in Vancouver, Canada June 18-22. CVPR is one of the most prestigious and competitive international conferences in computer vision. Details are provided below.

        1. “Are Deep Neural Networks SMARTer than Second Graders,” by Anoop Cherian, Kuan-Chuan Peng, Suhas Lohit, Kevin Smith, and Joshua B. Tenenbaum

        We present SMART: a Simple Multimodal Algorithmic Reasoning Task and the associated SMART-101 dataset for evaluating the abstraction, deduction, and generalization abilities of neural networks in solving visuo-linguistic puzzles designed for children in the 6-8 age group. Our experiments using SMART-101 reveal that powerful deep models are not better than random accuracy when analyzed for generalization. We also evaluate large language models (including ChatGPT) on a subset of SMART-101 and find that while these models show convincing reasoning abilities, their answers are often incorrect.

        Paper: https://arxiv.org/abs/2212.09993

        2. “EVAL: Explainable Video Anomaly Localization,” by Ashish Singh, Michael J. Jones, and Erik Learned-Miller

        This work presents a method for detecting unusual activities in videos by building a high-level model of activities found in nominal videos of a scene. The high-level features used in the model are human understandable and include attributes such as the object class and the directions and speeds of motion. Such high-level features allow our method to not only detect anomalous activity but also to provide explanations for why it is anomalous.

        Paper: https://arxiv.org/abs/2212.07900

        3. "Aligning Step-by-Step Instructional Diagrams to Video Demonstrations," by Jiahao Zhang, Anoop Cherian, Yanbin Liu, Yizhak Ben-Shabat, Cristian Rodriguez, and Stephen Gould

        The rise of do-it-yourself (DIY) videos on the web has made it possible even for an unskilled person (or a skilled robot) to imitate and follow instructions to complete complex real world tasks. In this paper, we consider the novel problem of aligning instruction steps that are depicted as assembly diagrams (commonly seen in Ikea assembly manuals) with video segments from in-the-wild videos. We present a new dataset: Ikea Assembly in the Wild (IAW) and propose a contrastive learning framework for aligning instruction diagrams with video clips.

        Paper: https://arxiv.org/pdf/2303.13800.pdf

        4. "HaLP: Hallucinating Latent Positives for Skeleton-Based Self-Supervised Learning of Actions," by Anshul Shah, Aniket Roy, Ketul Shah, Shlok Kumar Mishra, David Jacobs, Anoop Cherian, and Rama Chellappa

        In this work, we propose a new contrastive learning approach to train models for skeleton-based action recognition without labels. Our key contribution is a simple module, HaLP: Hallucinating Latent Positives for contrastive learning. HaLP explores the latent space of poses in suitable directions to generate new positives. Our experiments using HaLP demonstrates strong empirical improvements.

        Paper: https://arxiv.org/abs/2304.00387

        The 4th Workshop on Fair, Data-Efficient, and Trusted Computer Vision

        MERL researcher Kuan-Chuan Peng is co-organizing the fourth Workshop on Fair, Data-Efficient, and Trusted Computer Vision (https://fadetrcv.github.io/2023/) in conjunction with CVPR 2023 on June 18, 2023. This workshop provides a focused venue for discussing and disseminating research in the areas of fairness, bias, and trust in computer vision, as well as adjacent domains such as computational social science and public policy.
    •  

    See All News & Events for Kuan-Chuan
  • Research Highlights

  • MERL Publications

    •  Sharma, M., Chatterjee, M., Peng, K.-C., Lohit, S., Jones, M.J., "Tensor Factorization for Leveraging Cross-Modal Knowledge in Data-Constrained Infrared Object Detection", IEEE International Conference on Computer Vision Workshops (ICCV), October 2023, pp. 924-932.
      BibTeX TR2023-125 PDF Presentation
      • @inproceedings{Sharma2023oct,
      • author = {Sharma, Manish and Chatterjee, Moitreya and Peng, Kuan-Chuan and Lohit, Suhas and Jones, Michael J.},
      • title = {Tensor Factorization for Leveraging Cross-Modal Knowledge in Data-Constrained Infrared Object Detection},
      • booktitle = {IEEE International Conference on Computer Vision Workshops (ICCV)},
      • year = 2023,
      • pages = {924--932},
      • month = oct,
      • url = {https://www.merl.com/publications/TR2023-125}
      • }
    •  Cherian, A., Peng, K.-C., Lohit, S., Smith, K., Tenenbaum, J.B., "Are Deep Neural Networks SMARTer than Second Graders?", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), March 2023, pp. 10834-10844.
      BibTeX TR2023-014 PDF Data Software Presentation
      • @inproceedings{Cherian2023mar,
      • author = {Cherian, Anoop and Peng, Kuan-Chuan and Lohit, Suhas and Smith, Kevin and Tenenbaum, Joshua B.},
      • title = {Are Deep Neural Networks SMARTer than Second Graders?},
      • booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
      • year = 2023,
      • pages = {10834--10844},
      • month = mar,
      • publisher = {CVF},
      • url = {https://www.merl.com/publications/TR2023-014}
      • }
    •  Aich, A., Peng, K.-C., Roy-Chowdhury, A.K., "Cross-Domain Video Anomaly Detection without Target Domain Adaptation", IEEE Winter Conference on Applications of Computer Vision (WACV), Crandall, D. and Gong, B. and Lee, Y. J. and Souvenir, R. and Yu, S., Eds., DOI: 10.1109/​WACV56688.2023.00261, January 2023, pp. 2578-2590.
      BibTeX TR2023-001 PDF Video Presentation
      • @inproceedings{Aich2023jan,
      • author = {Aich, Abhishek and Peng, Kuan-Chuan and Roy-Chowdhury, Amit K.},
      • title = {Cross-Domain Video Anomaly Detection without Target Domain Adaptation},
      • booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},
      • year = 2023,
      • editor = {Crandall, D. and Gong, B. and Lee, Y. J. and Souvenir, R. and Yu, S.},
      • pages = {2578--2590},
      • month = jan,
      • publisher = {IEEE},
      • doi = {10.1109/WACV56688.2023.00261},
      • issn = {2642-9381},
      • isbn = {978-1-6654-9346-8},
      • url = {https://www.merl.com/publications/TR2023-001}
      • }
    •  Ahmed, S.M., Lohit, S., Peng, K.-C., Jones, M.J., Roy Chowdhury, A.K., "Cross-Modal Knowledge Transfer Without Task-Relevant Source Data", European Conference on Computer Vision (ECCV), Avidan, S and Brostow, G and Cisse M and Farinella, G.M. and Hassner T., Eds., DOI: 10.1007/​978-3-031-19830-4_7, October 2022, pp. 111-127.
      BibTeX TR2022-135 PDF Video Software Presentation
      • @inproceedings{Ahmed2022oct,
      • author = {Ahmed, Sk Miraj and Lohit, Suhas and Peng, Kuan-Chuan and Jones, Michael J. and Roy Chowdhury, Amit K},
      • title = {Cross-Modal Knowledge Transfer Without Task-Relevant Source Data},
      • booktitle = {Computer Vision--ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23--27, 2022, Proceedings, Part XXXIV},
      • year = 2022,
      • editor = {Avidan, S and Brostow, G and Cisse M and Farinella, G.M. and Hassner T.},
      • pages = {111--127},
      • month = oct,
      • publisher = {Springer},
      • doi = {10.1007/978-3-031-19830-4_7},
      • isbn = {978-3-031-19830-4},
      • url = {https://www.merl.com/publications/TR2022-135}
      • }
    •  Peng, K.-C., "Iterative Self Knowledge Distillation -- From Pothole Classification To Fine-Grained And COVID Recognition", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Gan, W.-S. and Ma, K. K., Eds., DOI: 10.1109/​ICASSP43922.2022.9746470, April 2022, pp. 3139-3143.
      BibTeX TR2022-020 PDF Video Presentation
      • @inproceedings{Peng2022apr,
      • author = {Peng, Kuan-Chuan},
      • title = {Iterative Self Knowledge Distillation -- From Pothole Classification To Fine-Grained And COVID Recognition},
      • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
      • year = 2022,
      • editor = {Gan, W.-S. and Ma, K. K.},
      • pages = {3139--3143},
      • month = apr,
      • publisher = {IEEE},
      • doi = {10.1109/ICASSP43922.2022.9746470},
      • issn = {1520-6149},
      • isbn = {978-1-6654-0541-6},
      • url = {https://www.merl.com/publications/TR2022-020}
      • }
    See All MERL Publications for Kuan-Chuan
  • Other Publications

    •  Prithviraj Dhar, Rajat Vikram Singh, Kuan-Chuan Peng, Ziyan Wu and Rama Chellappa, "Learning without Memorizing", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
      BibTeX
      • @Inproceedings{Dhar_CVPR19,
      • author = {Dhar, Prithviraj and Singh, Rajat Vikram and Peng, Kuan-Chuan and Wu, Ziyan and Chellappa, Rama},
      • title = {Learning without Memorizing},
      • booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
      • year = 2019
      • }
    •  Kunpeng Li, Ziyan Wu, Kuan-Chuan Peng, Jan Ernst and Yun Fu, "Guided Attention Inference Network", IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2019.
      BibTeX
      • @Article{Li_TPAMI19,
      • author = {Li, Kunpeng and Wu, Ziyan and Peng, Kuan-Chuan and Ernst, Jan and Fu, Yun},
      • title = {Guided Attention Inference Network},
      • journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
      • year = 2019,
      • publisher = {IEEE}
      • }
    •  Lezi Wang, Ziyan Wu, Srikrishna Karanam, Kuan-Chuan Peng, Rajat Vikram Singh, Bo Liu and Dimitris N. Metaxas, "Sharpen Focus: Learning with Attention Separability and Consistency", IEEE International Conference on Computer Vision (ICCV), 2019.
      BibTeX
      • @Inproceedings{Wang_ICCV19,
      • author = {Wang, Lezi and Wu, Ziyan and Karanam, Srikrishna and Peng, Kuan-Chuan and Singh, Rajat Vikram and Liu, Bo and Metaxas, Dimitris N.},
      • title = {Sharpen Focus: Learning with Attention Separability and Consistency},
      • booktitle = {IEEE International Conference on Computer Vision (ICCV)},
      • year = 2019
      • }
    •  Yunye Gong, Srikrishna Karanam, Ziyan Wu, Kuan-Chuan Peng, Jan Ernst and Peter C. Doerschuk, "Learning Compositional Visual Concepts with Mutual Consistency", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
      BibTeX
      • @Inproceedings{Gong_CVPR18,
      • author = {Gong, Yunye and Karanam, Srikrishna and Wu, Ziyan and Peng, Kuan-Chuan and Ernst, Jan and Doerschuk, Peter C.},
      • title = {Learning Compositional Visual Concepts with Mutual Consistency},
      • booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
      • year = 2018
      • }
    •  Kunpeng Li, Ziyan Wu, Kuan-Chuan Peng, Jan Ernst and Yun Fu, "Tell Me Where to Look: Guided Attention Inference Network", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
      BibTeX
      • @Inproceedings{Li_CVPR18,
      • author = {Li, Kunpeng and Wu, Ziyan and Peng, Kuan-Chuan and Ernst, Jan and Fu, Yun},
      • title = {Tell Me Where to Look: Guided Attention Inference Network},
      • booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
      • year = 2018
      • }
    •  Kuan-Chuan Peng, Ziyan Wu and Jan Ernst, "Zero-Shot Deep Domain Adaptation", European Conference on Computer Vision (ECCV), 2018.
      BibTeX
      • @Inproceedings{Peng_ECCV18,
      • author = {Peng, Kuan-Chuan and Wu, Ziyan and Ernst, Jan},
      • title = {Zero-Shot Deep Domain Adaptation},
      • booktitle = {European Conference on Computer Vision (ECCV)},
      • year = 2018
      • }
    •  Kuan-Chuan Peng, Tsuhan Chen, Amir Sadovnik and Andrew C. Gallagher, "Where Do Emotions Come from? Predicting the Emotion Stimuli Map", IEEE International Conference on Image Processing (ICIP), 2016.
      BibTeX
      • @Inproceedings{Peng_ICIP16,
      • author = {Peng, Kuan-Chuan and Chen, Tsuhan and Sadovnik, Amir and Gallagher, Andrew C.},
      • title = {Where Do Emotions Come from? Predicting the Emotion Stimuli Map},
      • booktitle = {IEEE International Conference on Image Processing (ICIP)},
      • year = 2016
      • }
    •  Kuan-Chuan Peng and Tsuhan Chen, "Toward Correlating and Solving Abstract Tasks Using Convolutional Neural Networks", IEEE Winter Conference on Applications of Computer Vision (WACV), 2016.
      BibTeX
      • @Inproceedings{Peng_WACV16,
      • author = {Peng, Kuan-Chuan and Chen, Tsuhan},
      • title = {Toward Correlating and Solving Abstract Tasks Using Convolutional Neural Networks},
      • booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},
      • year = 2016
      • }
    •  Kuan-Chuan Peng, Tsuhan Chen, Amir Sadovnik and Andrew C. Gallagher, "A Mixed Bag of Emotions: Model, Predict, and Transfer Emotion Distributions", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.
      BibTeX
      • @Inproceedings{Peng_CVPR15,
      • author = {Peng, Kuan-Chuan and Chen, Tsuhan and Sadovnik, Amir and Gallagher, Andrew C.},
      • title = {A Mixed Bag of Emotions: Model, Predict, and Transfer Emotion Distributions},
      • booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
      • year = 2015
      • }
    •  Kuan-Chuan Peng and Tsuhan Chen, "Cross-layer Features in Convolutional Neural Networks for Generic Classification Tasks", IEEE International Conference on Image Processing (ICIP), 2015.
      BibTeX
      • @Inproceedings{Peng_ICIP15,
      • author = {Peng, Kuan-Chuan and Chen, Tsuhan},
      • title = {Cross-layer Features in Convolutional Neural Networks for Generic Classification Tasks},
      • booktitle = {IEEE International Conference on Image Processing (ICIP)},
      • year = 2015
      • }
    •  Kuan-Chuan Peng and Tsuhan Chen, "A Framework of Extracting Multi-scale Features Using Multiple Convolutional Neural Network", IEEE International Conference on Multimedia and Expo (ICME), 2015.
      BibTeX
      • @Inproceedings{Peng_ICME15,
      • author = {Peng, Kuan-Chuan and Chen, Tsuhan},
      • title = {A Framework of Extracting Multi-scale Features Using Multiple Convolutional Neural Network},
      • booktitle = {IEEE International Conference on Multimedia and Expo (ICME)},
      • year = 2015
      • }
    •  Kuan-Chuan Peng, Kolbeinn Karlsson, Tsuhan Chen, Dongqing Zhang and Hong Heather Yu, "A Framework of Changing Image Emotion Using Emotion Prediction", IEEE International Conference on Image Processing (ICIP), 2014.
      BibTeX
      • @Inproceedings{Peng_ICIP14,
      • author = {Peng, Kuan-Chuan and Karlsson, Kolbeinn and Chen, Tsuhan and Zhang, Dongqing and Yu, Hong Heather},
      • title = {A Framework of Changing Image Emotion Using Emotion Prediction},
      • booktitle = {IEEE International Conference on Image Processing (ICIP)},
      • year = 2014
      • }
    •  Kuan-Chuan Peng and Tsuhan Chen, "Incorporating Cloud Distribution in Sky Representation", IEEE International Conference on Computer Vision (ICCV), 2013.
      BibTeX
      • @Inproceedings{Peng_ICCV13,
      • author = {Peng, Kuan-Chuan and Chen, Tsuhan},
      • title = {Incorporating Cloud Distribution in Sky Representation},
      • booktitle = {IEEE International Conference on Computer Vision (ICCV)},
      • year = 2013
      • }
  • Software & Data Downloads

  • Videos