Publications

47 / 3,604 publications found.


  •  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 Video
    • @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}
    • }
  •  Geng, S., Gao, P., Chatterjee, M., Hori, C., Le Roux, J., Zhang, Y., Li, H., Cherian, A., "Dynamic Graph Representation Learning for Video Dialog via Multi-Modal Shuffled Transformers", AAAI Conference on Artificial Intelligence, February 2021, pp. 1415-1423.
    BibTeX TR2021-010 PDF
    • @inproceedings{Geng2021feb,
    • author = {Geng, Shijie and Gao, Peng and Chatterjee, Moitreya and Hori, Chiori and Le Roux, Jonathan and Zhang, Yongfeng and Li, Hongsheng and Cherian, Anoop},
    • title = {Dynamic Graph Representation Learning for Video Dialog via Multi-Modal Shuffled Transformers},
    • booktitle = {AAAI Conference on Artificial Intelligence},
    • year = 2021,
    • pages = {1415--1423},
    • month = feb,
    • publisher = {AAAI Press, Palo Alto, California USA},
    • isbn = {978-1-57735-866-4},
    • url = {https://www.merl.com/publications/TR2021-010}
    • }
  •  Benosman, M., Cherian, A., Romero, O., "Optimizing Deep Neural Networks via Discretization of Finite-Time Convergent Flows", arXiv, October 2020.
    BibTeX arXiv
    • @article{Benosman2020oct,
    • author = {Benosman, Mouhacine and Cherian, Anoop and Romero, Orlando},
    • title = {Optimizing Deep Neural Networks via Discretization of Finite-Time Convergent Flows},
    • journal = {arXiv},
    • year = 2020,
    • month = oct,
    • url = {https://arxiv.org/abs/2010.02990v2}
    • }
  •  Cherian, A., Chatterjee, M., Ahuja, N., "Sound2Sight: Generating Visual Dynamics from Sound and Context", European Conference on Computer Vision (ECCV), Vedaldi, A. and Bischof, H. and Brox, Th. and Frahm, J.-M., Eds., August 2020.
    BibTeX TR2020-121 PDF Software
    • @inproceedings{Cherian2020aug,
    • author = {Cherian, Anoop and Chatterjee, Moitreya and Ahuja, Narendra},
    • title = {Sound2Sight: Generating Visual Dynamics from Sound and Context},
    • booktitle = {European Conference on Computer Vision (ECCV)},
    • year = 2020,
    • editor = {Vedaldi, A. and Bischof, H. and Brox, Th. and Frahm, J.-M.},
    • month = aug,
    • publisher = {Springer},
    • url = {https://www.merl.com/publications/TR2020-121}
    • }
  •  Geng, S., Gao, P., Hori, C., Le Roux, J., Cherian, A., "Spatio-Temporal Scene Graphs for Video Dialog", arXiv, July 2020.
    BibTeX arXiv
    • @article{Geng2020jul,
    • author = {Geng, Shijie and Gao, Peng and Hori, Chiori and Le Roux, Jonathan and Cherian, Anoop},
    • title = {Spatio-Temporal Scene Graphs for Video Dialog},
    • journal = {arXiv},
    • year = 2020,
    • month = jul,
    • url = {https://arxiv.org/abs/2007.03848}
    • }
  •  Cherian, A., Aeron, S., "Representation Learning via Adversarially-Contrastive Optimal Transport", International Conference on Machine Learning (ICML), Daumé, H. and Singh, A., Eds., July 2020, pp. 10675-10685.
    BibTeX TR2020-093 PDF Software
    • @inproceedings{Cherian2020jul,
    • author = {Cherian, Anoop and Aeron, Shuchin},
    • title = {Representation Learning via Adversarially-Contrastive Optimal Transport},
    • booktitle = {International Conference on Machine Learning (ICML)},
    • year = 2020,
    • editor = {Daumé, H. and Singh, A.},
    • pages = {10675--10685},
    • month = jul,
    • url = {https://www.merl.com/publications/TR2020-093}
    • }
  •  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}
    • }
  •  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}
    • }
  •  Wang, J., Cherian, A., "GODS: Generalized One-class Discriminative Subspaces for Anomaly Detection", IEEE International Conference on Computer Vision (ICCV), DOI: 10.1109/​ICCV.2019.00829, October 2019, pp. 8200-8210.
    BibTeX TR2019-121 PDF
    • @inproceedings{Wang2019oct2,
    • author = {Wang, Jue and Cherian, Anoop},
    • title = {GODS: Generalized One-class Discriminative Subspaces for Anomaly Detection},
    • booktitle = {2019 IEEE/CVF International Conference on Computer Vision (ICCV)},
    • year = 2019,
    • pages = {8200--8210},
    • month = oct,
    • publisher = {IEEE},
    • doi = {10.1109/ICCV.2019.00829},
    • url = {https://www.merl.com/publications/TR2019-121}
    • }
  •  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}
    • }
  •  Wang, J., Cherian, A., "Discriminative Video Representation Learning Using Support Vector Classifiers", IEEE Transactions on Pattern Analysis and Machine Intelligence, DOI: 10.1109/​TPAMI.2019.2937292, August 2019.
    BibTeX TR2019-107 PDF
    • @article{Wang2019aug,
    • author = {Wang, Jue and Cherian, Anoop},
    • title = {Discriminative Video Representation Learning Using Support Vector Classifiers},
    • journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
    • year = 2019,
    • month = aug,
    • doi = {10.1109/TPAMI.2019.2937292},
    • url = {https://www.merl.com/publications/TR2019-107}
    • }
  •  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}
    • }
  •  Raghunathan, A., Cherian, A., Jha, D.K., "Game Theoretic Optimization via Gradient-based Nikaido-Isoda Function", International Conference on Machine Learning (ICML), Lawrence, N. and Reid, M., Eds., June 2019, pp. 5291-5300.
    BibTeX TR2019-045 PDF Software
    • @inproceedings{Raghunathan2019jun,
    • author = {Raghunathan, Arvind and Cherian, Anoop and Jha, Devesh K.},
    • title = {Game Theoretic Optimization via Gradient-based Nikaido-Isoda Function},
    • booktitle = {International Conference on Machine Learning (ICML)},
    • year = 2019,
    • editor = {Lawrence, N. and Reid, M.},
    • pages = {5291--5300},
    • month = jun,
    • publisher = {PMLR},
    • issn = {2640-3498},
    • url = {https://www.merl.com/publications/TR2019-045}
    • }
  •  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}
    • }
  •  Cherian, A., Sullivan, A., "Sem-GAN: Semantically-Consistent Image-to-Image Translation", IEEE Winter Conference on Applications of Computer Vision (WACV), DOI: 10.1109/​WACV.2019.00196, January 2019.
    BibTeX TR2018-178 PDF
    • @inproceedings{Cherian2019jan,
    • author = {Cherian, Anoop and Sullivan, Alan},
    • title = {Sem-GAN: Semantically-Consistent Image-to-Image Translation},
    • booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},
    • year = 2019,
    • month = jan,
    • doi = {10.1109/WACV.2019.00196},
    • url = {https://www.merl.com/publications/TR2018-178}
    • }
  •  Wang, J., Cherian, A., "Learning Discriminative Video Representations Using Adversarial Perturbations", European Conference on Computer Vision (ECCV), September 2018.
    BibTeX TR2018-139 PDF Software
    • @inproceedings{Wang2018sep3,
    • author = {Wang, Jue and Cherian, Anoop},
    • title = {Learning Discriminative Video Representations Using Adversarial Perturbations},
    • booktitle = {European Conference on Computer Vision (ECCV)},
    • year = 2018,
    • month = sep,
    • url = {https://www.merl.com/publications/TR2018-139}
    • }
  •  Wang, J., Cherian, A., "Discriminative Subspace Pooling for Action Recognition", Workshop on Perceptual Organization in Computer Vision as part of the European Conference on Computer Vision (ECCV), September 2018.
    BibTeX TR2018-141 PDF
    • @inproceedings{Wang2018sep2,
    • author = {Wang, Jue and Cherian, Anoop},
    • title = {Discriminative Subspace Pooling for Action Recognition},
    • booktitle = {Workshop on Perceptual Organization in Computer Vision as part of the European Conference on Computer Vision (ECCV)},
    • year = 2018,
    • month = sep,
    • url = {https://www.merl.com/publications/TR2018-141}
    • }
  •  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}
    • }
  •  Santa Cruz, R., Fernando, B., Cherian, A., Gould, S., "Neural Algebra of Classifiers", IEEE Winter Conference on Applications of Computer Vision (WACV), DOI: 10.1109/​WACV.2018.00085, March 2018, pp. 729-737.
    BibTeX TR2018-033 PDF
    • @inproceedings{Santacruz2018mar,
    • author = {Santa Cruz, Rodrigo and Fernando, Basura and Cherian, Anoop and Gould, Stephen},
    • title = {Neural Algebra of Classifiers},
    • booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},
    • year = 2018,
    • pages = {729--737},
    • month = mar,
    • doi = {10.1109/WACV.2018.00085},
    • url = {https://www.merl.com/publications/TR2018-033}
    • }