Publications

29 / 2,863 publications found.


  •  Wu, Y., Marks, T., 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, October 2019.
    BibTeX Download PDFAbout TR2019-118
    • @inproceedings{Wu2019oct,
    • author = {Wu, Yuanwei and Marks, Tim 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,
    • month = oct,
    • url = {https://www.merl.com/publications/TR2019-118}
    • }
  •  Marks, T., 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), October 2019.
    BibTeX Download PDFAbout TR2019-117
    • @inproceedings{Marks2019oct,
    • author = {Marks, Tim 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,
    • month = oct,
    • url = {https://www.merl.com/publications/TR2019-117}
    • }
  •  Hori, C., Cherian, A., Marks, T., Hori, T., "Joint Student-Teacher Learning for Audio-Visual Scene-Aware Dialog", Interspeech, September 2019, pp. 1886-1890.
    BibTeX Download PDFAbout TR2019-097
    • @inproceedings{Hori2019sep,
    • author = {Hori, Chiori and Cherian, Anoop and Marks, Tim 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), June 2019.
    BibTeX Download PDFAbout TR2019-048
    • @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,
    • month = jun,
    • 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 Download PDFAbout TR2019-016
    • @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}
    • }
  •  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", arXiv, July 13, 2018.
    BibTeX Download PDFAbout TR2018-085
    • @article{Hori2018jul,
    • 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},
    • journal = {arXiv},
    • year = 2018,
    • month = jul,
    • url = {https://www.merl.com/publications/TR2018-085}
    • }
  •  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 Download PDFAbout TR2018-069
    • @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://www.merl.com/publications/TR2018-069}
    • }
  •  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 Download PDFAbout TR2018-067
    • @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 Download PDFAbout TR2017-183
    • @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 Download PDFAbout TR2017-184
    • @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,
    • 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 Download PDFAbout TR2017-156
    • @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}
    • }
  •  Hori, C., Hori, T., Lee, T.-Y., Sumi, K., Hershey, J.R., Marks, T.K., "Attention-Based Multimodal Fusion for Video Description," Tech. Rep. TR2017-008, arXiv, January 2017.
    BibTeX Download PDFAbout TR2017-008
    • @techreport{Hori2017jan,
    • author = {Hori, Chiori and Hori, Takaaki and Lee, Teng-Yok and Sumi, Kazuhiko and Hershey, John R. and Marks, Tim K.},
    • title = {Attention-Based Multimodal Fusion for Video Description},
    • journal = {arXiv},
    • year = 2017,
    • month = jan,
    • url = {https://www.merl.com/publications/TR2017-008}
    • }
  •  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 Download PDFAbout TR2016-129
    • @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 Download PDFAbout TR2016-105
    • @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 Download PDFAbout TR2016-080
    • @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}
    • }
  •  Ahmed, E., Jones, M.J., Marks, T.K., "An Improved Deep Learning Architecture for Person Re-Identification", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), DOI: 10.1109/CVPR.2015.7299016, June 2015, pp. 3908-3916.
    BibTeX Download PDFAbout TR2015-076
    • @inproceedings{Jones2015jun,
    • author = {Ahmed, E. and Jones, M.J. and Marks, T.K.},
    • title = {An Improved Deep Learning Architecture for Person Re-Identification},
    • booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    • year = 2015,
    • pages = {3908--3916},
    • month = jun,
    • doi = {10.1109/CVPR.2015.7299016},
    • url = {https://www.merl.com/publications/TR2015-076}
    • }
  •  Papazov, C., Marks, T.K., Jones, M.J., "Real-time Head Pose and Facial Landmark Estimation from Depth Images Using Triangular Surface Patch Features", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), DOI: 10.1109/CVPR.2015.7299104, June 2015, pp. 4722-4730.
    BibTeX Download PDFAbout TR2015-069
    • @inproceedings{Marks2015jun,
    • author = {Papazov, C. and Marks, T.K. and Jones, M.J.},
    • title = {Real-time Head Pose and Facial Landmark Estimation from Depth Images Using Triangular Surface Patch Features},
    • booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    • year = 2015,
    • pages = {4722--4730},
    • month = jun,
    • publisher = {IEEE},
    • doi = {10.1109/CVPR.2015.7299104},
    • url = {https://www.merl.com/publications/TR2015-069}
    • }
  •  Watanabe, S., Hershey, J.R., Marks, T.K., Fujii, Y., Koji, Y., "Cost-level integration of statistical and rule-based dialog managers", Interspeech, ISSN: 308-457X, September 2014, vol. 15, pp. 323-327.
    BibTeX Download PDFAbout TR2014-082
    • @inproceedings{Watanabe2014sep,
    • author = {Watanabe, S. and Hershey, J.R. and Marks, T.K. and Fujii, Y. and Koji, Y.},
    • title = {Cost-level integration of statistical and rule-based dialog managers},
    • booktitle = {Interspeech},
    • year = 2014,
    • volume = 15,
    • pages = {323--327},
    • month = sep,
    • publisher = {International Speech Communication Association},
    • issn = {308-457X},
    • url = {https://www.merl.com/publications/TR2014-082}
    • }
  •  Kumar, S., Marks, T.K., Jones, M., "Improving Person Tracking Using an Inexpensive Thermal Infrared Sensor", IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), DOI: 10.1109/CVPRW.2014.41, June 2014, pp. 217-224.
    BibTeX Download PDFAbout TR2014-036
    • @inproceedings{Kumar2014jun,
    • author = {Kumar, S. and Marks, T.K. and Jones, M.},
    • title = {Improving Person Tracking Using an Inexpensive Thermal Infrared Sensor},
    • booktitle = {IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
    • year = 2014,
    • pages = {217--224},
    • month = jun,
    • publisher = {IEEE},
    • doi = {10.1109/CVPRW.2014.41},
    • url = {https://www.merl.com/publications/TR2014-036}
    • }
  •  Tang, H., Watanabe, S., Marks, T.K., Hershey, J.R., "Log-linear Dialog Manager", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2014.6854371, May 2014, pp. 4092-4096.
    BibTeX Download PDFAbout TR2014-024
    • @inproceedings{Tang2014may,
    • author = {Tang, H. and Watanabe, S. and Marks, T.K. and Hershey, J.R.},
    • title = {Log-linear Dialog Manager},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2014,
    • pages = {4092--4096},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP.2014.6854371},
    • url = {https://www.merl.com/publications/TR2014-024}
    • }