Publications

39 / 3,180 publications found.


  •  Medin, S., Egger, B., Cherian, A., Wang, Y., Tenanbaum, J., Liu, X., Marks, T.K., "MOST-GAN: 3D Morphable StyleGAN for Disentangled Face Image Manipulation", arXiv, October 2021.
    BibTeX
    • @article{Medin2021oct,
    • author = {Medin, Safa and Egger, Bernhard and Cherian, Anoop and Wang, Ye and Tenanbaum, Joshua and Liu, Xiaoming and Marks, Tim K.},
    • title = {MOST-GAN: 3D Morphable StyleGAN for Disentangled Face Image Manipulation},
    • journal = {arXiv},
    • year = 2021,
    • month = oct
    • }
  •  Shah, A.P., Geng, S., Gao, P., Cherian, A., Hori, T., Marks, T.K., Le Roux, J., Hori, C., "Audio-Visual Scene-Aware Dialog and Reasoning Using Audio-Visual Transformers with Joint Student-Teacher Learning", arXiv, October 2021.
    BibTeX arXiv
    • @inproceedings{Shah2021oct,
    • author = {Shah, Ankit Parag and Geng, Shijie and Gao, Peng and Cherian, Anoop and Hori, Takaaki and Marks, Tim K. and Le Roux, Jonathan and Hori, Chiori},
    • title = {Audio-Visual Scene-Aware Dialog and Reasoning Using Audio-Visual Transformers with Joint Student-Teacher Learning},
    • booktitle = {arXiv},
    • year = 2021,
    • month = oct,
    • url = {https://arxiv.org/abs/2110.06894}
    • }
  •  Cherian, A., Pais, G., Jain, S., Marks, T.K., Sullivan, A., "InSeGAN: A Generative Approach to Segmenting Identical Instances in Depth Images", IEEE International Conference on Computer Vision (ICCV), October 2021.
    BibTeX TR2021-097 PDF
    • @inproceedings{Cherian2021oct,
    • author = {Cherian, Anoop and Pais, Goncalo and Jain, Siddarth and Marks, Tim K. and Sullivan, Alan},
    • title = {InSeGAN: A Generative Approach to Segmenting Identical Instances in Depth Images},
    • booktitle = {IEEE International Conference on Computer Vision (ICCV)},
    • year = 2021,
    • month = oct,
    • url = {https://www.merl.com/publications/TR2021-097}
    • }
  •  Comas, A., Marks, T.K., Mansour, H., Lohit, S., Ma, Y., Liu, X., "TURNIP: Time-series U-NET with Recurrence for NIR Imaging PPG", IEEE International Conference on Image Processing (ICIP), September 2021.
    BibTeX TR2021-099 PDF
    • @inproceedings{Comas2021sep,
    • author = {Comas, Armand and Marks, Tim K. and Mansour, Hassan and Lohit, Suhas and Ma, Yechi and Liu, Xiaoming},
    • title = {TURNIP: Time-series U-NET with Recurrence for NIR Imaging PPG},
    • booktitle = {IEEE International Conference on Image Processing (ICIP)},
    • year = 2021,
    • month = sep,
    • url = {https://www.merl.com/publications/TR2021-099}
    • }
  •  Kim, S., Galley, M., Gunasekara, C., Lee, S., Atkinson, A., Peng, B., Schulz, H., Gao, J., Li, J., Adada, M., Huang, M., Lastras, L., Kummerfeld, J.K., Lasecki, W.S., Hori, C., Cherian, A., Marks, T.K., Rastogi, A., Zang, X., Sunkara, S., Gupta, R., "Overview of the Eighth Dialog System Technology Challenge: DSTC8", IEEE/ACM Transactions on Audio, Speech, and Language Processing, DOI: 10.1109/​TASLP.2021.3078368, May 2021.
    BibTeX TR2021-064 PDF
    • @article{Kim2021may,
    • author = {Kim, Seokhwan and Galley, Michel and Gunasekara, Chulaka and Lee, Sungjin and Atkinson, Adam and Peng, Baolin and Schulz, Hannes and Gao, Jianfeng and Li, Jinchao and Adada, Mahmoud and Huang, Minlie and Lastras, Luis and Kummerfeld, Jonathan K. and Lasecki, Walter S. and Hori, Chiori and Cherian, Anoop and Marks, Tim K. and Rastogi, Abhinav and Zang, Xiaoxue and Sunkara, Srinivas and Gupta, Raghav},
    • title = {Overview of the Eighth Dialog System Technology Challenge: DSTC8},
    • journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing},
    • year = 2021,
    • month = may,
    • doi = {10.1109/TASLP.2021.3078368},
    • issn = {2329-9290},
    • url = {https://www.merl.com/publications/TR2021-064}
    • }
  •  Hori, C., Tsuchiya, M., Chen, S., Cherian, A., Hori, T., Harsham, B.A., Marks, T.K., Le Roux, J., Sullivan, A., Vetro, A., "マルチモーダルセンシング情報に基づくScene-aware Interaction 技術", Society of Automotive Engineers of Japan, Vol. 75, No. 5, pp. 66-71, May 2021.
    BibTeX TR2021-042 PDF
    • @article{Hori2021may,
    • author = {Hori, Chiori and Tsuchiya, Masato and Chen, Siheng and Cherian, Anoop and Hori, Takaaki and Harsham, Bret A. and Marks, Tim K. and Le Roux, Jonathan and Sullivan, Alan and Vetro, Anthony},
    • title = {マルチモーダルセンシング情報に基づくScene-aware Interaction 技術},
    • journal = {Society of Automotive Engineers of Japan},
    • year = 2021,
    • volume = 75,
    • number = 5,
    • pages = {66--71},
    • month = may,
    • url = {https://www.merl.com/publications/TR2021-042}
    • }
  •  Nowara, E., Marks, T.K., Mansour, H., Veeraraghavan, A., "Near-Infrared Imaging Photoplethysmography During Driving", IEEE Transactions on Intelligent Transportation Systems, DOI: 10.1109/​TITS.2020.3038317, pp. 1-12, December 2020.
    BibTeX TR2020-161 PDF
    • @article{Nowara2020dec,
    • author = {Nowara, Ewa and Marks, Tim K. and Mansour, Hassan and Veeraraghavan, Ashok},
    • title = {Near-Infrared Imaging Photoplethysmography During Driving},
    • journal = {IEEE Transactions on Intelligent Transportation Systems},
    • year = 2020,
    • pages = {1--12},
    • month = dec,
    • doi = {10.1109/TITS.2020.3038317},
    • url = {https://www.merl.com/publications/TR2020-161}
    • }
  •  Nowara, E., Marks, T.K., Mansour, H., Pai, A., Nagamatsu, G., Kawasaki, H., Veeraraghavan, A., "HeartCam: Camera-Based Physiology Monitoring in the Wild", IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), June 2020.
    BibTeX CCD 2020
    • @inproceedings{Nowara2020jun,
    • author = {Nowara, Ewa and Marks, Tim K. and Mansour, Hassan and Pai, Amruta and Nagamatsu, Genki and Kawasaki, Hiroshi and Veeraraghavan, Ashok},
    • title = {HeartCam: Camera-Based Physiology Monitoring in the Wild},
    • booktitle = {IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
    • year = 2020,
    • month = jun,
    • url = {http://ccd2020.cms.caltech.edu/}
    • }
  •  Kumar, A., Marks, T.K., Mou, W., Wang, Y., Cherian, A., Jones, M.J., Liu, X., Koike-Akino, T., Feng, C., "LUVLi Face Alignment: Estimating Landmarks’ Location, Uncertainty, and Visibility Likelihood", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), DOI: 10.1109/​CVPR42600.2020.00826, June 2020.
    BibTeX TR2020-067 PDF Video Data Software
    • @inproceedings{Kumar2020jun,
    • author = {Kumar, Abhinav and Marks, Tim K. and Mou, Wenxuan and Wang, Ye and Cherian, Anoop and Jones, Michael J. and Liu, Xiaoming and Koike-Akino, Toshiaki and Feng, Chen},
    • title = {LUVLi Face Alignment: Estimating Landmarks’ Location, Uncertainty, and Visibility Likelihood},
    • booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    • year = 2020,
    • month = jun,
    • publisher = {IEEE},
    • doi = {10.1109/CVPR42600.2020.00826},
    • issn = {2575-7075},
    • isbn = {978-1-7281-7168-5},
    • url = {https://www.merl.com/publications/TR2020-067}
    • }
  •  D’Haro, L.F., Yoshino, K., Hori, C., Marks, T.K., Polymenakos, L., Kummerfeld, J.K., Galley, M., Gao, X., "Overview of the seventh Dialog System Technology Challenge: DSTC7", Computer Speech and Language, DOI: 10.1016/​j.csl.2020.101068, Vol. 62, March 2020.
    BibTeX TR2020-029 PDF
    • @article{D’Haro2020mar,
    • author = {D’Haro, Luis Fernando and Yoshino, Koichiro and Hori, Chiori and Marks, Tim K. and Polymenakos, Lazaros and Kummerfeld, Jonathan K. and Galley, Michel and Gao, Xiang},
    • title = {Overview of the seventh Dialog System Technology Challenge: DSTC7},
    • journal = {Computer Speech and Language},
    • year = 2020,
    • volume = 62,
    • month = mar,
    • doi = {10.1016/j.csl.2020.101068},
    • url = {https://www.merl.com/publications/TR2020-029}
    • }
  •  Cherian, A., Wang, J., Hori, C., Marks, T.K., "Spatio-Temporal Ranked-Attention Networks for Video Captioning", IEEE Winter Conference on Applications of Computer Vision (WACV), DOI: 10.1109/​WACV45572.2020.9093291, February 2020, pp. 1606-1615.
    BibTeX TR2020-016 PDF
    • @inproceedings{Cherian2020feb,
    • author = {Cherian, Anoop and Wang, Jue and Hori, Chiori and Marks, Tim K.},
    • title = {Spatio-Temporal Ranked-Attention Networks for Video Captioning},
    • booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},
    • year = 2020,
    • pages = {1606--1615},
    • month = feb,
    • publisher = {IEEE},
    • doi = {10.1109/WACV45572.2020.9093291},
    • url = {https://www.merl.com/publications/TR2020-016}
    • }
  •  Huang, R., Xu, W., Lee, T.-Y., Cherian, A., Wang, Y., Marks, T.K., "FX-GAN: Self-Supervised GAN Learning via Feature Exchange", IEEE Winter Conference on Applications of Computer Vision (WACV), DOI: 10.1109/​WACV45572.2020.9093525, February 2020, pp. 3183-3191.
    BibTeX TR2020-014 PDF
    • @inproceedings{Huang2020feb,
    • author = {Huang, Rui and Xu, Wenju and Lee, Teng-Yok and Cherian, Anoop and Wang, Ye and Marks, Tim K.},
    • title = {FX-GAN: Self-Supervised GAN Learning via Feature Exchange},
    • booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},
    • year = 2020,
    • pages = {3183--3191},
    • month = feb,
    • publisher = {IEEE},
    • doi = {10.1109/WACV45572.2020.9093525},
    • url = {https://www.merl.com/publications/TR2020-014}
    • }
  •  Wu, Y., Marks, T.K., Cherian, A., Chen, S., Feng, C., Wang, G., Sullivan, A., "Unsupervised Joint 3D Object Model Learning and 6D Pose Estimation for Depth-Based Instance Segmentation", IEEE ICCV Workshop on Recovering 6D Object Pose, DOI: 10.1109/​ICCVW.2019.00339, October 2019, pp. 2777-2786.
    BibTeX TR2019-118 PDF
    • @inproceedings{Wu2019oct,
    • author = {Wu, Yuanwei and Marks, Tim K. and Cherian, Anoop and Chen, Siheng and Feng, Chen and Wang, Guanghui and Sullivan, Alan},
    • title = {Unsupervised Joint 3D Object Model Learning and 6D Pose Estimation for Depth-Based Instance Segmentation},
    • booktitle = {IEEE ICCV Workshop on Recovering 6D Object Pose},
    • year = 2019,
    • pages = {2777--2786},
    • month = oct,
    • doi = {10.1109/ICCVW.2019.00339},
    • url = {https://www.merl.com/publications/TR2019-118}
    • }
  •  Marks, T.K., Kumar, A., Mou, W., Feng, C., Liu, X., "UGLLI Face Alignment: Estimating Uncertainty with Gaussian Log-Likelihood Loss", IEEE International Conference on Computer Vision (ICCV) Workshop on Statistical Deep Learning for Computer Vision (SDL-CV), DOI: 10.1109/​ICCVW.2019.00103, October 2019, pp. 778-782.
    BibTeX TR2019-117 PDF Software
    • @inproceedings{Marks2019oct,
    • author = {Marks, Tim K. and Kumar, Abhinav and Mou, Wenxuan and Feng, Chen and Liu, Xiaoming},
    • title = {UGLLI Face Alignment: Estimating Uncertainty with Gaussian Log-Likelihood Loss},
    • booktitle = {IEEE International Conference on Computer Vision (ICCV) Workshop on Statistical Deep Learning for Computer Vision (SDL-CV)},
    • year = 2019,
    • pages = {778--782},
    • month = oct,
    • publisher = {IEEE},
    • doi = {10.1109/ICCVW.2019.00103},
    • url = {https://www.merl.com/publications/TR2019-117}
    • }
  •  Hori, C., Cherian, A., Marks, T.K., Hori, T., "Joint Student-Teacher Learning for Audio-Visual Scene-Aware Dialog", Interspeech, September 2019, pp. 1886-1890.
    BibTeX TR2019-097 PDF
    • @inproceedings{Hori2019sep,
    • author = {Hori, Chiori and Cherian, Anoop and Marks, Tim K. and Hori, Takaaki},
    • title = {Joint Student-Teacher Learning for Audio-Visual Scene-Aware Dialog},
    • booktitle = {Interspeech},
    • year = 2019,
    • pages = {1886--1890},
    • month = sep,
    • publisher = {ISCA},
    • url = {https://www.merl.com/publications/TR2019-097}
    • }
  •  Alamri, H., Cartillier, V., Das, A., Wang, J., Lee, S., Anderson, P., Essa, I., Parikh, D., Batra, D., Cherian, A., Marks, T.K., Hori, C., "Audio-Visual Scene-Aware Dialog", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), DOI: 10.1109/​CVPR.2019.00774, June 2019, pp. 7550-7559.
    BibTeX TR2019-048 PDF
    • @inproceedings{Alamri2019jun,
    • author = {Alamri, Huda and Cartillier, Vincent and Das, Abhishek and Wang, Jue and Lee, Stefan and Anderson, Peter and Essa, Irfan and Parikh, Devi and Batra, Dhruv and Cherian, Anoop and Marks, Tim K. and Hori, Chiori},
    • title = {Audio-Visual Scene-Aware Dialog},
    • booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    • year = 2019,
    • pages = {7550--7559},
    • month = jun,
    • doi = {10.1109/CVPR.2019.00774},
    • url = {https://www.merl.com/publications/TR2019-048}
    • }
  •  Hori, C., Alamri, H., Wang, J., Wichern, G., Hori, T., Cherian, A., Marks, T.K., Cartillier, V., Lopes, R., Das, A., Essa, I., Batra, D., Parikh, D., "End-to-End Audio Visual Scene-Aware Dialog Using Multimodal Attention-Based Video Features", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP.2019.8682583, May 2019.
    BibTeX TR2019-016 PDF
    • @inproceedings{Hori2019may2,
    • author = {Hori, Chiori and Alamri, Huda and Wang, Jue and Wichern, Gordon and Hori, Takaaki and Cherian, Anoop and Marks, Tim K. and Cartillier, Vincent and Lopes, Raphael and Das, Abhishek and Essa, Irfan and Batra, Dhruv and Parikh, Devi},
    • title = {End-to-End Audio Visual Scene-Aware Dialog Using Multimodal Attention-Based Video Features},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2019,
    • month = may,
    • doi = {10.1109/ICASSP.2019.8682583},
    • url = {https://www.merl.com/publications/TR2019-016}
    • }
  •  Alamri, H., Cartillier, V., Lopes, R., Das, A., Wang, J., Essa, I., Batra, D., Parikh, D., Cherian, A., Marks, T.K., Hori, C., "Audio Visual Scene-Aware Dialog (AVSD) Challenge at DSTC7", arXiv, July 12, 2018.
    BibTeX arXiv
    • @article{Alamri2018jul,
    • author = {Alamri, Huda and Cartillier, Vincent and Lopes, Raphael and Das, Abhishek and Wang, Jue and Essa, Irfan and Batra, Dhruv and Parikh, Devi and Cherian, Anoop and Marks, Tim K. and Hori, Chiori},
    • title = {Audio Visual Scene-Aware Dialog (AVSD) Challenge at DSTC7},
    • journal = {arXiv},
    • year = 2018,
    • month = jul,
    • url = {https://arxiv.org/abs/1806.00525}
    • }
  •  Nowara, E., Marks, T.K., Mansour, H., Nakamura, Y., Veeraraghavan, A., "SparsePPG: Towards Driver Monitoring Using Camera-Based Vital Signs Estimation in Near-Infrared", IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshop on Computer Vision for Physiological Measurement (CVPM, June 2018, pp. 1272-1281.
    BibTeX TR2018-067 PDF
    • @inproceedings{Nowara2018jun,
    • author = {Nowara, Ewa and Marks, Tim K. and Mansour, Hassan and Nakamura, Yudai and Veeraraghavan, Ashok},
    • title = {SparsePPG: Towards Driver Monitoring Using Camera-Based Vital Signs Estimation in Near-Infrared},
    • booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshop on Computer Vision for Physiological Measurement (CVPM},
    • year = 2018,
    • pages = {1272--1281},
    • month = jun,
    • url = {https://www.merl.com/publications/TR2018-067}
    • }
  •  Hori, C., Hori, T., Marks, T.K., Hershey, J.R., "Early and Late Integration of Audio Features for Automatic Video Description", IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), DOI: 10.1109/​ASRU.2017.8268968, December 2017.
    BibTeX TR2017-183 PDF
    • @inproceedings{Hori2017dec2,
    • author = {Hori, Chiori and Hori, Takaaki and Marks, Tim K. and Hershey, John R.},
    • title = {Early and Late Integration of Audio Features for Automatic Video Description},
    • booktitle = {IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)},
    • year = 2017,
    • month = dec,
    • doi = {10.1109/ASRU.2017.8268968},
    • url = {https://www.merl.com/publications/TR2017-183}
    • }
  •  Lin, C., Marks, T.K., Pajovic, M., Watanabe, S., Tung, C., "Model parameter learning using Kullback-Leibler divergence", Physica A, DOI: 10.1016/​j.physa.2017.09.018, Vol. 491, No. 1, pp. 549-559, November 2017.
    BibTeX TR2017-184 PDF
    • @article{Lin2017nov,
    • author = {Lin, Chungwei and Marks, Tim K. and Pajovic, Milutin and Watanabe, Shinji and Tung, Chihkuan},
    • title = {Model parameter learning using Kullback-Leibler divergence},
    • journal = {Physica A},
    • year = 2017,
    • volume = 491,
    • number = 1,
    • pages = {549--559},
    • month = nov,
    • publisher = {Elsevier},
    • doi = {10.1016/j.physa.2017.09.018},
    • url = {https://www.merl.com/publications/TR2017-184}
    • }
  •  Hori, C., Hori, T., Lee, T.-Y., Zhang, Z., Harsham, B.A., Sumi, K., Marks, T.K., Hershey, J.R., "Attention-Based Multimodal Fusion for Video Description", IEEE International Conference on Computer Vision (ICCV), DOI: 10.1109/​ICCV.2017.450, October 2017.
    BibTeX TR2017-156 PDF
    • @inproceedings{Hori2017oct,
    • author = {Hori, Chiori and Hori, Takaaki and Lee, Teng-Yok and Zhang, Ziming and Harsham, Bret A. and Sumi, Kazuhiko and Marks, Tim K. and Hershey, John R.},
    • title = {Attention-Based Multimodal Fusion for Video Description},
    • booktitle = {IEEE International Conference on Computer Vision (ICCV)},
    • year = 2017,
    • month = oct,
    • doi = {10.1109/ICCV.2017.450},
    • url = {https://www.merl.com/publications/TR2017-156}
    • }
  •  Tuzel, C.O., Marks, T.K., Tambe, S., "Robust Face Alignment Using a Mixture of Invariant Experts", European Conference on Computer Vision (ECCV), DOI: 10.1007/​978-3-319-46454-1_50, October 2016, vol. 9909, pp. 825-841.
    BibTeX TR2016-129 PDF
    • @inproceedings{Tuzel2016oct,
    • author = {Tuzel, C. Oncel and Marks, Tim K. and Tambe, Salil},
    • title = {Robust Face Alignment Using a Mixture of Invariant Experts},
    • booktitle = {European Conference on Computer Vision (ECCV)},
    • year = 2016,
    • volume = 9909,
    • pages = {825--841},
    • month = oct,
    • doi = {10.1007/978-3-319-46454-1_50},
    • url = {https://www.merl.com/publications/TR2016-129}
    • }
  •  Koike-Akino, T., Mahajan, R., Marks, T.K., Tuzel, C.O., Wang, Y., Watanabe, S., Orlik, P.V., "High-Accuracy User Identification Using EEG Biometrics", International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), DOI: 10.1109/​EMBC.2016.7590835, August 2016, pp. 854-858.
    BibTeX TR2016-105 PDF Presentation
    • @inproceedings{Koike-Akino2016aug,
    • author = {Koike-Akino, Toshiaki and Mahajan, Ruhi and Marks, Tim K. and Tuzel, C. Oncel and Wang, Ye and Watanabe, Shinji and Orlik, Philip V.},
    • title = {High-Accuracy User Identification Using EEG Biometrics},
    • booktitle = {International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)},
    • year = 2016,
    • pages = {854--858},
    • month = aug,
    • doi = {10.1109/EMBC.2016.7590835},
    • url = {https://www.merl.com/publications/TR2016-105}
    • }
  •  Singh, B., Marks, T.K., Jones, M.J., Tuzel, C.O., Shao, M., "A Multi-Stream Bi-Directional Recurrent Neural Network for Fine-Grained Action Detection", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), DOI: 10.1109/​CVPR.2016.216, June 2016, pp. 1961-1970.
    BibTeX TR2016-080 PDF Data
    • @inproceedings{Singh2016jun,
    • author = {Singh, Bharat and Marks, Tim K. and Jones, Michael J. and Tuzel, C. Oncel and Shao, Ming},
    • title = {A Multi-Stream Bi-Directional Recurrent Neural Network for Fine-Grained Action Detection},
    • booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    • year = 2016,
    • pages = {1961--1970},
    • month = jun,
    • doi = {10.1109/CVPR.2016.216},
    • url = {https://www.merl.com/publications/TR2016-080}
    • }