Preprints

- Saito, Kuniaki, Donghyun Kim, Piotr Teterwak, Rogerio Feris, and Kate Saenko. Mind the Backbone: Minimizing Backbone Distortion for Robust Object Detection. arXiv

- Jongwoo Park, Kumara Kahatapitiya, Donghyun Kim, Shivchander Sudalairaj, Quanfu Fan, Michael S Ryoo. Grafting Vision Transformers. arXiv

- Quanfu Fan, Donghyun Kim, Richard Chen, Stan Sclaroff, Kate Saenko, Sarah Adel Bargal. Temporal Relevance Analysis for Video Action Modeling. arXiv

Conference Publications

- Howard Zhong, Samarth Mishra, Donghyun Kim, SouYoung Jin, Rameswar Panda, Hilde Kuehne, Leonid Karlinsky, Venkatesh Saligrama, Aude Oliva, Rogerio Feris. Learning Human Action Recognition Representations Without Real Humans. NeurIPS, 2023. arXiv

- Sivan Doveh, Assaf Arbelle, Sivan Harary, Roei Herzig, Donghyun Kim, Paola Cascante-Bonilla, Amit Alfassy, Rameswar Panda, Raja Giryes, Rogerio Feris, Shimon Ullman, Leonid Karlinsky. Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models. NeurIPS, 2023 (spotlight). arXiv

- Kaihong Wang, Donghyun Kim, Rogerio Feris, Margrit Betke, Kate Saenko. CDAC: Cross-domain Attention Consistency in Transformer for Domain Adaptive Semantic Segmentation. ICCV, 2023. arXiv

- Cascante-Bonilla P, Shehada K, Smith JS, Doveh S, Kim D, Panda R, Varol G, Oliva A, Ordonez V, Feris R, Karlinsky L. Going Beyond Nouns With Vision & Language Models Using Synthetic Data. ICCV, 2023. arXiv

- Doveh, S., Arbelle, A., Harary, S., Panda, R., Herzig, R., Schwartz, E., Kim, D., Giryes, R., Feris, R., Ullman, S. and Karlinsky, L. Teaching Structured Vision&Language Concepts to Vision&Language Models. CVPR, 2023. arXiv

- Smith, J.S., Karlinsky, L., Gutta, V., Cascante-Bonilla, P., Kim, D., Arbelle, A., Panda, R., Feris, R. and Kira, Z. CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning. CVPR, 2023. arXiv

- Smith, J.S., Cascante-Bonilla, P., Arbelle, A., Kim, D., Panda, R., Cox, D., Yang, D., Kira, Z., Feris, R. and Karlinsky, L. ConStruct-VL: Data-Free Continual Structured VL Concepts Learning. CVPR, 2023. arXiv

- D. Bashkirova, P. Teterwak, S. Mishra, D. Kim, , R. Lai, F. Alladkani, J. Akl, B. Calli, V. Ablavsky, S. Bargal, K. Saenko. VisDA 2022 Challenge: Sim2Real Domain Adaptation for Industrial Recycling. Neural Information Processing Systems (NeurIPS) Competition, 2022.

- Donghyun Kim, Kaihong Wang, Stan Sclaroff, and Kate Saenko. A Broad Study of Pre-training for Domain Generalization and Adaptation. ECCV, 2022. arXiv

- Donghyun Kim*, Kaihong Wang*, Kate Saenko, Margrit Betke, Stan Sclaroff. A Unified Framework for Domain Adaptive Pose Estimation. ECCV, 2022. arXiv

- D. Bashkirova*, D Hendrycks*, D. Kim*, S. Mishra*, K. Saenko*, K. Saito*, P. Teterwak*, B. Usman*. VisDA-2021 Competition: Universal Domain Adaptation to Improve Performance on Out-of-Distribution Data. Neural Information Processing Systems (NeurIPS) Competition, 2021.

- Kuniaki Saito, Donghyun Kim, Kate Saenko. OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outliers. NeurIPS, 2021. arXiv

- Donghyun Kim, Kuniaki Saito, Tae-Hyun Oh, Bryan A. Plummer, Stan Sclaroff, Kate Saenko. CDSP: Cross-domain Self-supervised Pre-training. ICCV, 2021. arXiv

- Donghyun Kim, Yi-Hsuan Tsai, Bingbing Zhuang, Xiang Yu, Stan Sclaroff, Kate Saenko, Manmohan Chandraker. Learning Cross-Modal Contrastive Features for Video Domain Adaptation. ICCV, 2021.

- Kuniaki Saito, Donghyun Kim, Piotr Teterwak, Stan Sclaroff, Trevor Darrell, Kate Saenko. Tune it the Right Way: Unsupervised Validation of Domain Adaptation via Neighborhood Density. ICCV, 2021.

- Donghyun Kim, Kuniaki Saito, Kate Saenko, Stan Sclaroff, Bryan A Plummer. Self-supervised Visual Attribute Learning for Fashion Compatibility. ICCV VIPriors Workshop, 2021. arXiv

- Donghyun Kim, Tian Lan, Chuhang Zou, Ning Xu, Bryan A Plummer, Stan Sclaroff, Jayan Eledath, Gerard Medioni. Multi-Task Learning from Videos via Efficient Inter-Frame Attention. ICCV MTL Workshop, 2021. arXiv

- Kuniaki Saito, Donghyun Kim, Stan Sclaroff, Kate Saenko. Universal Domain Adaptation through Self Supervision. NeurIPS, 2020. arXiv

- Andrea Burns, Donghyun Kim, Derry Wijaya, Kate Saenko, Bryan A Plummer. Learning to Scale Multilingual Representations for Vision-Language Tasks. ECCV, 2020 (Spotlight). arXiv

- Donghyun Kim, Sarah Adel Bargal, Jianming Zhang, Stan Sclaroff. Multi-way Encoding for Robustness. WACV, 2020. arXiv

- Donghyun Kim, Kuniaki Saito, Kate Saenko, Stan Sclaroff, Bryan A. Plummer. MULE: Multimodal Universal Language Embedding. AAAI, 2020 (Oral). arXiv

- Kuniaki Saito, Donghyun Kim, Stan Sclaroff, Trevor Darrell, Kate Saenko. Semi-supervised Domain Adaptation via Minimax Entropy. International Conference on Computer Vision (ICCV), 2019. arXiv

- Donghyun Kim, Kuniaki Saito, Kate Saenko, Stan Sclaroff, Bryan A. Plummer. MULE: Multimodal Universal Language Embedding. ICCV CLVL Workshop, 2019. PDF

- Sarah Adel Bargal^*, Andrea Zunino^*, Donghyun Kim, Jianming Zhang, Vittorio Murino, Stan Sclaroff. Excitation Backprop for RNNs. Computer Vision and Pattern Recognition (CVPR), 2018. arXiv

- Donghyun Kim, Matthias Hernandez, Jongmoo Choi, G ́erard Medioni. Deep 3D Face Identification. International Joint Conference on Biometrics (IJCB) 2017 (Oral). arXiv

- Donghyun Kim, Jongmoo Choi, Jatuporn Toy Leksut, G ́erard Medioni. Expression Invariant 3D Face Modeling from an RGB-D Video. International Conference on Pattern Recognition (ICPR) 2016 (Oral). PDF

- Donghyun Kim, Jongmoo Choi, Jatuporn Toy Leksut, G ́erard Medioni. Accurate 3D face modeling and recognition from RGB-D stream in the presence of large pose changes. IEEE International Conference on Image Processing (ICIP) 2016. PDF