Publications

31 / 2,975 publications found.


  •  Kumar, A., Marks, T., 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), June 2020.
    BibTeX TR2020-067 PDF Video Data
    • @inproceedings{Kumar2020jun,
    • author = {Kumar, Abhinav and Marks, Tim 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,
    • url = {https://www.merl.com/publications/TR2020-067}
    • }
  •  D’Haro, L.F., Yoshino, K., Hori, C., Marks, T., 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 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., "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},
    • 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., "FX-GAN: Self-Supervised GAN Learning via Feature Exchange", IEEE Winter Conference on Applications of Computer Vision (WACV), February 2020, pp. 3194-3202.
    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},
    • title = {FX-GAN: Self-Supervised GAN Learning via Feature Exchange},
    • booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},
    • year = 2020,
    • pages = {3194--3202},
    • month = feb,
    • url = {https://www.merl.com/publications/TR2020-014}
    • }
  •  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, DOI: 10.1109/ICCVW.2019.00339, October 2019, pp. 2777-2786.
    BibTeX TR2019-118 PDF
    • @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,
    • pages = {2777--2786},
    • month = oct,
    • doi = {10.1109/ICCVW.2019.00339},
    • 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 TR2019-117 PDF
    • @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 TR2019-097 PDF
    • @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), 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
    • @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}
    • }
  •  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 TR2015-076 PDF
    • @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 TR2015-069 PDF
    • @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, September 2014, vol. 15, pp. 323-327.
    BibTeX TR2014-082 PDF
    • @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 TR2014-036 PDF
    • @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 TR2014-024 PDF
    • @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}
    • }
  •  Ni, J., Marks, T.K., Tuzel, O., Porikli, F., "Detecting 3D geometric Boundaries of Indoor Scenes Under Varying Lighting", IEEE Winter Conference on Applications of Computer Vision (WACV), March 2014.
    BibTeX TR2014-013 PDF
    • @inproceedings{Ni2014mar,
    • author = {Ni, J. and Marks, T.K. and Tuzel, O. and Porikli, F.},
    • title = {Detecting 3D geometric Boundaries of Indoor Scenes Under Varying Lighting},
    • booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},
    • year = 2014,
    • month = mar,
    • url = {https://www.merl.com/publications/TR2014-013}
    • }
  •  Liu, M.-Y., Tuzel, O., Veeraraghavan, A., Taguchi, Y., Marks, T.K., Chellappa, R., "Fast Object Localization and Pose Estimation in Heavy Clutter for Robotic Bin Picking", International Journal of Robotics Research, May 2012.
    BibTeX TR2012-007 PDF
    • @article{Liu2012may,
    • author = {Liu, M.-Y. and Tuzel, O. and Veeraraghavan, A. and Taguchi, Y. and Marks, T.K. and Chellappa, R.},
    • title = {Fast Object Localization and Pose Estimation in Heavy Clutter for Robotic Bin Picking},
    • journal = {International Journal of Robotics Research},
    • year = 2012,
    • month = may,
    • url = {https://www.merl.com/publications/TR2012-007}
    • }
  •  Asthana, A., Marks, T.K., Jones, M.J., Tieu, K.H., Rohith, M., "Fully Automatic Pose-Invariant Face Recognition via 3D Pose Normalization", IEEE International Conference on Computer Vision (ICCV), DOI: 10.1109/ICCV.2011.6126336, November 2011, pp. 937-944.
    BibTeX TR2011-074 PDF
    • @inproceedings{Asthana2011nov,
    • author = {Asthana, A. and Marks, T.K. and Jones, M.J. and Tieu, K.H. and Rohith, M.},
    • title = {Fully Automatic Pose-Invariant Face Recognition via 3D Pose Normalization},
    • booktitle = {IEEE International Conference on Computer Vision (ICCV)},
    • year = 2011,
    • pages = {937--944},
    • month = nov,
    • doi = {10.1109/ICCV.2011.6126336},
    • url = {https://www.merl.com/publications/TR2011-074}
    • }