Publications

675 / 3,860 publications found.


  •  Schperberg, A., Tanaka, Y., Mowlavi, S., Xu, F., Balaji, B., Hong, D., "OptiState: State Estimation of Legged Robots using Gated Networks with Transformer-based Vision and Kalman Filtering", IEEE International Conference on Robotics and Automation (ICRA), May 2024.
    BibTeX TR2024-054 PDF
    • @inproceedings{Schperberg2024may,
    • author = {Schperberg, Alexander and Tanaka, Yusuke and Mowlavi, Saviz and Xu, Feng and Balaji, Bharathan and Hong, Dennis},
    • title = {{OptiState: State Estimation of Legged Robots using Gated Networks with Transformer-based Vision and Kalman Filtering}},
    • booktitle = {IEEE International Conference on Robotics and Automation (ICRA)},
    • year = 2024,
    • month = may,
    • publisher = {IEEE},
    • url = {https://www.merl.com/publications/TR2024-054}
    • }
  •  Uhlich, S., Fabbro, G., Hirano, M., Takahashi, S., Wichern, G., Le Roux, J., Chakraborty, D., Mohanty, S., Li, K., Luo, Y., Yu, J., Gu, R., Solovyev, R., Stempkovskiy, A., Habruseva, T., Sukhovei, M., Mitsufuji, Y., "The Sound Demixing Challenge 2023 – Cinematic Demixing Track", Transactions of the International Society for Music Information Retrieval, DOI: 10.5334/​tismir.172, Vol. 7, No. 1, pp. 44-62, May 2024.
    BibTeX TR2024-047 PDF
    • @article{Uhlich2024may,
    • author = {Uhlich, Stefan and Fabbro, Giorgio and Hirano, Masato and Takahashi, Shusuke and Wichern, Gordon and {Le Roux}, Jonathan and Chakraborty, Dipam and Mohanty, Sharada and Li, Kai and Luo, Yi and Yu, Jianwei and Gu, Rongzhi and Solovyev, Roman and Stempkovskiy, Alexander and Habruseva, Tatiana and Sukhovei, Mikhail and Mitsufuji, Yuki},
    • title = {{The {S}ound {D}emixing {C}hallenge 2023 – {C}inematic {D}emixing {T}rack}},
    • journal = {Transactions of the International Society for Music Information Retrieval},
    • year = 2024,
    • volume = 7,
    • number = 1,
    • pages = {44--62},
    • month = may,
    • doi = {10.5334/tismir.172},
    • url = {https://www.merl.com/publications/TR2024-047}
    • }
  •  Vaca-Rubio, C., Wang, P., Koike-Akino, T., Wang, Y., Boufounos, P.T., Popovski, P., "Object Trajectory Estimation with Continuous-Time Neural Dynamic Learning of Millimeter-Wave Wi-Fi", IEEE Journal of Selected Topics in Signal Processing, DOI: 10.1109/​JSTSP.2024.3388930, April 2024.
    BibTeX TR2024-044 PDF
    • @article{Vaca-Rubio2024apr,
    • author = {Vaca-Rubio, Cristian and Wang, Pu and Koike-Akino, Toshiaki and Wang, Ye and Boufounos, Petros T. and Popovski, Petar},
    • title = {{Object Trajectory Estimation with Continuous-Time Neural Dynamic Learning of Millimeter-Wave Wi-Fi}},
    • journal = {IEEE Journal of Selected Topics in Signal Processing},
    • year = 2024,
    • month = apr,
    • doi = {10.1109/JSTSP.2024.3388930},
    • issn = {1941-0484},
    • url = {https://www.merl.com/publications/TR2024-044}
    • }
  •  Dey, R., Egger, B., Boddeti, V., Wang, Y., Marks, T.K., "CoLa-SDF: Controllable Latent StyleSDF for Disentangled 3D Face Generation", IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), April 2024.
    BibTeX TR2024-045 PDF
    • @inproceedings{Dey2024apr,
    • author = {Dey, Rahul and Egger, Bernhard and Boddeti, Vishnu and Wang, Ye and Marks, Tim K.},
    • title = {{CoLa-SDF: Controllable Latent StyleSDF for Disentangled 3D Face Generation}},
    • booktitle = {IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
    • year = 2024,
    • month = apr,
    • url = {https://www.merl.com/publications/TR2024-045}
    • }
  •  Pan, Z., Wichern, G., Germain, F.G., Subramanian, A., Le Roux, J., "Late Audio-Visual Fusion for In-The-Wild Speaker Diarization", Hands-free Speech Communication and Microphone Arrays (HSCMA), DOI: 10.1109/​ICASSPW62465.2024.10626914, April 2024, pp. 174-178.
    BibTeX TR2024-029 PDF
    • @inproceedings{Pan2024apr,
    • author = {Pan, Zexu and Wichern, Gordon and Germain, François G and Subramanian, Aswin and {Le Roux}, Jonathan},
    • title = {{Late Audio-Visual Fusion for In-The-Wild Speaker Diarization}},
    • booktitle = {Hands-free Speech Communication and Microphone Arrays (HSCMA)},
    • year = 2024,
    • pages = {174--178},
    • month = apr,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSPW62465.2024.10626914},
    • isbn = {979-8-3503-7451-3},
    • url = {https://www.merl.com/publications/TR2024-029}
    • }
  •  Queeney, J., Ozcan, E.C., Paschalidis, I.C., Cassandras, C.G., "Optimal Transport Perturbations for Safe Reinforcement Learning with Robustness Guarantees", Transactions on Machine Learning Research (TMLR), April 2024.
    BibTeX TR2024-037 PDF
    • @article{Queeney2024apr,
    • author = {Queeney, James and Ozcan, Erhan Can and Paschalidis, Ioannis Ch. and Cassandras, Christos G.},
    • title = {{Optimal Transport Perturbations for Safe Reinforcement Learning with Robustness Guarantees}},
    • journal = {Transactions on Machine Learning Research (TMLR)},
    • year = 2024,
    • month = apr,
    • issn = {2835-8856},
    • url = {https://www.merl.com/publications/TR2024-037}
    • }
  •  Yang, Z., Liu, J., Chen, P., Cherian, A., Marks, T.K., Le Roux, J., Gan, C., "RILA: Reflective and Imaginative Language Agent for Zero-Shot Semantic Audio-Visual Navigation", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), April 2024, pp. 16251-16261.
    BibTeX TR2024-043 PDF
    • @inproceedings{Yang2024apr,
    • author = {Yang, Zeyuan and Liu, Jiageng and Chen, Peihao and Cherian, Anoop and Marks, Tim K. and {Le Roux}, Jonathan and Gan, Chuang},
    • title = {{RILA: Reflective and Imaginative Language Agent for Zero-Shot Semantic Audio-Visual Navigation}},
    • booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    • year = 2024,
    • pages = {16251--16261},
    • month = apr,
    • publisher = {CVF},
    • url = {https://www.merl.com/publications/TR2024-043}
    • }
  •  Koo, J., Wichern, G., Germain, F.G., Khurana, S., Le Roux, J., "Understanding and Controlling Generative Music Transformers by Probing Individual Attention Heads", IEEE ICASSP Satellite Workshop on Explainable Machine Learning for Speech and Audio (XAI-SA), April 2024.
    BibTeX TR2024-032 PDF
    • @inproceedings{Koo2024apr,
    • author = {Koo, Junghyun and Wichern, Gordon and Germain, François G and Khurana, Sameer and {Le Roux}, Jonathan},
    • title = {{Understanding and Controlling Generative Music Transformers by Probing Individual Attention Heads}},
    • booktitle = {IEEE ICASSP Satellite Workshop on Explainable Machine Learning for Speech and Audio (XAI-SA)},
    • year = 2024,
    • month = apr,
    • url = {https://www.merl.com/publications/TR2024-032}
    • }
  •  Zhu, X., Jha, D.K., Romeres, D., Sun, L., Tomizuka, M., Cherian, A., "Multi-level Reasoning for Robotic Assembly: From Sequence Inference to Contact Selection", IEEE International Conference on Robotics and Automation (ICRA), March 2024, pp. 816-823.
    BibTeX TR2024-033 PDF Video
    • @inproceedings{Zhu2024mar,
    • author = {Zhu, Xinghao and Jha, Devesh K. and Romeres, Diego and Sun, Lingfeng and Tomizuka, Masayoshi and Cherian, Anoop},
    • title = {{Multi-level Reasoning for Robotic Assembly: From Sequence Inference to Contact Selection}},
    • booktitle = {IEEE International Conference on Robotics and Automation (ICRA)},
    • year = 2024,
    • pages = {816--823},
    • month = mar,
    • publisher = {IEEE},
    • url = {https://www.merl.com/publications/TR2024-033}
    • }
  •  Jeon, C.-B., Wichern, G., Germain, F.G., Le Roux, J., "Why does music source separation benefit from cacophony?", IEEE ICASSP Satellite Workshop on Explainable Machine Learning for Speech and Audio (XAI-SA), DOI: 10.1109/​ICASSPW62465.2024.10669899, March 2024, pp. 873-877.
    BibTeX TR2024-030 PDF Video
    • @inproceedings{Jeon2024mar,
    • author = {Jeon, Chang-Bin and Wichern, Gordon and Germain, François G and {Le Roux}, Jonathan},
    • title = {{Why does music source separation benefit from cacophony?}},
    • booktitle = {IEEE ICASSP Satellite Workshop on Explainable Machine Learning for Speech and Audio (XAI-SA)},
    • year = 2024,
    • pages = {873--877},
    • month = mar,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSPW62465.2024.10669899},
    • isbn = {979-8-3503-7451-3},
    • url = {https://www.merl.com/publications/TR2024-030}
    • }
  •  Bralios, D., Wichern, G., Germain, F.G., Pan, Z., Khurana, S., Hori, C., Le Roux, J., "Generation or Replication: Auscultating Audio Latent Diffusion Models", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP48485.2024.10447705, March 2024, pp. 1156-1160.
    BibTeX TR2024-027 PDF
    • @inproceedings{Bralios2024mar,
    • author = {Bralios, Dimitrios and Wichern, Gordon and Germain, François G and Pan, Zexu and Khurana, Sameer and Hori, Chiori and {Le Roux}, Jonathan},
    • title = {{Generation or Replication: Auscultating Audio Latent Diffusion Models}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2024,
    • pages = {1156--1160},
    • month = mar,
    • doi = {10.1109/ICASSP48485.2024.10447705},
    • url = {https://www.merl.com/publications/TR2024-027}
    • }
  •  Masuyama, Y., Wichern, G., Germain, F.G., Pan, Z., Khurana, S., Hori, C., Le Roux, J., "NIIRF: Neural IIR Filter Field for HRTF Upsampling and Personalization", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP48485.2024.10448477, March 2024, pp. 1016-1020.
    BibTeX TR2024-026 PDF Software
    • @inproceedings{Masuyama2024mar,
    • author = {Masuyama, Yoshiki and Wichern, Gordon and Germain, François G and Pan, Zexu and Khurana, Sameer and Hori, Chiori and {Le Roux}, Jonathan},
    • title = {{NIIRF: Neural IIR Filter Field for HRTF Upsampling and Personalization}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2024,
    • pages = {1016--1020},
    • month = mar,
    • doi = {10.1109/ICASSP48485.2024.10448477},
    • url = {https://www.merl.com/publications/TR2024-026}
    • }
  •  Pan, Z., Wichern, G., Germain, F.G., Khurana, S., Le Roux, J., "NeuroHeed+: Improving Neuro-steered Speaker Extraction with Joint Auditory Attention Detection", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP48485.2024.10446333, March 2024, pp. 11456-11460.
    BibTeX TR2024-025 PDF
    • @inproceedings{Pan2024mar,
    • author = {Pan, Zexu and Wichern, Gordon and Germain, François G and Khurana, Sameer and {Le Roux}, Jonathan},
    • title = {{NeuroHeed+: Improving Neuro-steered Speaker Extraction with Joint Auditory Attention Detection}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2024,
    • pages = {11456--11460},
    • month = mar,
    • doi = {10.1109/ICASSP48485.2024.10446333},
    • url = {https://www.merl.com/publications/TR2024-025}
    • }
  •  Wu, S.-L., Chang, X., Wichern, G., Jung, J.-W., Germain, F.G., Le Roux, J., Watanabe, S., "Improving Audio Captioning Models with Fine-grained Audio Features, Text Embedding Supervision, and LLM Mix-up Augmentation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP48485.2024.10447215, March 2024, pp. 316-320.
    BibTeX TR2024-028 PDF
    • @inproceedings{Wu2024mar,
    • author = {Wu, Shih-Lun and Chang, Xuankai and Wichern, Gordon and Jung, Jee-weon and Germain, François G and {Le Roux}, Jonathan and Watanabe, Shinji},
    • title = {{Improving Audio Captioning Models with Fine-grained Audio Features, Text Embedding Supervision, and LLM Mix-up Augmentation}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2024,
    • pages = {316--320},
    • month = mar,
    • doi = {10.1109/ICASSP48485.2024.10447215},
    • url = {https://www.merl.com/publications/TR2024-028}
    • }
  •  Baoueb, T., Liu, H., Fontaine, M., Le Roux, J., Richard, G., "SpecDiff-GAN: A Spectrally-Shaped Noise Diffusion GAN for Speech and Music Synthesis", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP48485.2024.10446830, March 2024, pp. 986-990.
    BibTeX TR2024-013 PDF
    • @inproceedings{Baoueb2024mar,
    • author = {Baoueb, Teysir and Liu, Haocheng and Fontaine, Mathieu and {Le Roux}, Jonathan and Richard, Gaël},
    • title = {{SpecDiff-GAN: A Spectrally-Shaped Noise Diffusion GAN for Speech and Music Synthesis}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2024,
    • pages = {986--990},
    • month = mar,
    • doi = {10.1109/ICASSP48485.2024.10446830},
    • issn = {2379-190X},
    • isbn = {979-8-3503-4485-1},
    • url = {https://www.merl.com/publications/TR2024-013}
    • }
  •  Hori, C., Wang, P., Rahman, M., Vaca-Rubio, C., Khurana, S., Cherian, A., Le Roux, J., "Wi-Fi based Indoor Monitoring Enhanced by Multimodal Fusion", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP48485.2024.10447600, March 2024, pp. 13296-13300.
    BibTeX TR2024-012 PDF
    • @inproceedings{Hori2024mar,
    • author = {Hori, Chiori and Wang, Pu and Rahman, Mahbub and Vaca-Rubio, Cristian and Khurana, Sameer and Cherian, Anoop and {Le Roux}, Jonathan},
    • title = {{Wi-Fi based Indoor Monitoring Enhanced by Multimodal Fusion}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2024,
    • pages = {13296--13300},
    • month = mar,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP48485.2024.10447600},
    • issn = {2379-190X},
    • isbn = {979-8-3503-4485-1},
    • url = {https://www.merl.com/publications/TR2024-012}
    • }
  •  Liu, H., Baoueb, T., Fontaine, M., Le Roux, J., Richard, G., "GLA-Grad: A Griffin-Lim Extended Waveform Generation Diffusion Model", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP48485.2024.10446058, March 2024, pp. 11611-11615.
    BibTeX TR2024-014 PDF
    • @inproceedings{Liu2024mar,
    • author = {Liu, Haocheng and Baoueb, Teysir and Fontaine, Mathieu and {Le Roux}, Jonathan and Richard, Gaël},
    • title = {{GLA-Grad: A Griffin-Lim Extended Waveform Generation Diffusion Model}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2024,
    • pages = {11611--11615},
    • month = mar,
    • doi = {10.1109/ICASSP48485.2024.10446058},
    • issn = {2379-190X},
    • isbn = {979-8-3503-4485-1},
    • url = {https://www.merl.com/publications/TR2024-014}
    • }
  •  Lowy, A., Li, Z., Liu, J., Koike-Akino, T., Parsons, K., Wang, Y., "Why Does Differential Privacy with Large ε Defend Against Practical Membership Inference Attacks?", AAAI Workshop on Privacy-Preserving Artificial Intelligence, February 2024.
    BibTeX TR2024-009 PDF
    • @inproceedings{Lowy2024feb2,
    • author = {Lowy, Andrew and Li, Zhuohang and Liu, Jing and Koike-Akino, Toshiaki and Parsons, Kieran and Wang, Ye},
    • title = {{Why Does Differential Privacy with Large ε Defend Against Practical Membership Inference Attacks?}},
    • booktitle = {AAAI Workshop on Privacy-Preserving Artificial Intelligence},
    • year = 2024,
    • month = feb,
    • url = {https://www.merl.com/publications/TR2024-009}
    • }
  •  Boeddeker, C., Subramanian, A.S., Wichern, G., Haeb-Umbach, R., Le Roux, J., "TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings", IEEE/ACM Transactions on Audio, Speech, and Language Processing, DOI: 10.1109/​TASLP.2024.3350887, Vol. 32, pp. 1185-1197, February 2024.
    BibTeX TR2024-006 PDF Software
    • @article{Boeddeker2024feb,
    • author = {Boeddeker, Christoph and Subramanian, Aswin Shanmugam and Wichern, Gordon and Haeb-Umbach, Reinhold and {Le Roux}, Jonathan},
    • title = {{TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings}},
    • journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing},
    • year = 2024,
    • volume = 32,
    • pages = {1185--1197},
    • month = feb,
    • doi = {10.1109/TASLP.2024.3350887},
    • issn = {2329-9304},
    • url = {https://www.merl.com/publications/TR2024-006}
    • }
  •  Carmichael, Z., Jones, L.S., Cherian, A., Michael J., , Scheirer, W., "Pixel-Grounded Prototypical Part Networks", IEEE Winter Conference on Applications of Computer Vision (WACV), DOI: 10.1109/​WACV57701.2024.00470, January 2024.
    BibTeX TR2024-002 PDF Video Software Presentation
    • @inproceedings{Carmichael2024jan,
    • author = {Carmichael, Zachariah and Jones, Lohit, Suhas and Cherian, Anoop and Michael J. and Scheirer, Walter},
    • title = {{Pixel-Grounded Prototypical Part Networks}},
    • booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},
    • year = 2024,
    • month = jan,
    • doi = {10.1109/WACV57701.2024.00470},
    • url = {https://www.merl.com/publications/TR2024-002}
    • }
  •  Liu, X., Paul, S., Chatterjee, M., Cherian, A., "CAVEN: An Embodied Conversational Agent for Efficient Audio-Visual Navigation in Noisy Environments", AAAI Conference on Artificial Intelligence, DOI: 10.1609/​aaai.v38i4.28167, December 2023, pp. 3765-3773.
    BibTeX TR2023-154 PDF
    • @inproceedings{Liu2023dec2,
    • author = {Liu, Xiulong and Paul, Sudipta and Chatterjee, Moitreya and Cherian, Anoop},
    • title = {{CAVEN: An Embodied Conversational Agent for Efficient Audio-Visual Navigation in Noisy Environments}},
    • booktitle = {Proceedings of the 38th AAAI Conference on Artificial Intelligence},
    • year = 2023,
    • pages = {3765--3773},
    • month = dec,
    • doi = {10.1609/aaai.v38i4.28167},
    • url = {https://www.merl.com/publications/TR2023-154}
    • }
  •  Liu, J., Koike-Akino, T., Wang, P., Brand, M., Wang, Y., Parsons, K., "LoDA: Low-Dimensional Adaptation of Large Language Models", Advances in Neural Information Processing Systems (NeurIPS) workshop, December 2023.
    BibTeX TR2023-150 PDF
    • @inproceedings{Liu2023dec,
    • author = {Liu, Jing and Koike-Akino, Toshiaki and Wang, Pu and Brand, Matthew and Wang, Ye and Parsons, Kieran},
    • title = {{LoDA: Low-Dimensional Adaptation of Large Language Models}},
    • booktitle = {Advances in Neural Information Processing Systems (NeurIPS) workshop},
    • year = 2023,
    • month = dec,
    • url = {https://www.merl.com/publications/TR2023-150}
    • }
  •  Pan, Z., Wichern, G., Masuyama, Y., Germain, F.G., Khurana, S., Hori, C., Le Roux, J., "Scenario-Aware Audio-Visual TF-GridNet for Target Speech Extraction", IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), DOI: 10.1109/​ASRU57964.2023.10389618, December 2023.
    BibTeX TR2023-152 PDF Video
    • @inproceedings{Pan2023dec2,
    • author = {Pan, Zexu and Wichern, Gordon and Masuyama, Yoshiki and Germain, François G and Khurana, Sameer and Hori, Chiori and {Le Roux}, Jonathan},
    • title = {{Scenario-Aware Audio-Visual TF-GridNet for Target Speech Extraction}},
    • booktitle = {IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)},
    • year = 2023,
    • month = dec,
    • doi = {10.1109/ASRU57964.2023.10389618},
    • isbn = {979-8-3503-0689-7},
    • url = {https://www.merl.com/publications/TR2023-152}
    • }
  •  Li, Z., Lowy, A., Liu, J., Koike-Akino, T., Malin, B., Parsons, K., Wang, Y., "Exploring User-level Gradient Inversion with a Diffusion Prior", International Workshop on Federated Learning in the Age of Foundation Models in Conjunction with NeurIPS, December 2023.
    BibTeX TR2023-149 PDF
    • @inproceedings{Li2023dec,
    • author = {Li, Zhuohang and Lowy, Andrew and Liu, Jing and Koike-Akino, Toshiaki and Malin, Bradley and Parsons, Kieran and Wang, Ye},
    • title = {{Exploring User-level Gradient Inversion with a Diffusion Prior}},
    • booktitle = {International Workshop on Federated Learning in the Age of Foundation Models in Conjunction with NeurIPS},
    • year = 2023,
    • month = dec,
    • url = {https://www.merl.com/publications/TR2023-149}
    • }
  •  He, Y., Shin, S., Cherian, A., Markham, A., Trigon, N., "Sound3DVDet: 3D Sound Source Detection using Multiview Microphone Array and RGB Images", IEEE Winter Conference on Applications of Computer Vision (WACV), December 2023, pp. 5496-5507.
    BibTeX TR2023-144 PDF
    • @inproceedings{He2023dec,
    • author = {He, Yuhang and Shin, Sangyun and Cherian, Anoop and Markham, Andrew and Trigon, Niki},
    • title = {{Sound3DVDet: 3D Sound Source Detection using Multiview Microphone Array and RGB Images}},
    • booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},
    • year = 2023,
    • pages = {5496--5507},
    • month = dec,
    • url = {https://www.merl.com/publications/TR2023-144}
    • }