Domain agnostic learning with disentangled representations X Peng, Z Huang, X Sun, K Saenko International conference on machine learning, 5102-5112, 2019 | 310 | 2019 |
Adashare: Learning what to share for efficient deep multi-task learning X Sun, R Panda, R Feris, K Saenko Advances in Neural Information Processing Systems 33, 8728-8740, 2020 | 270 | 2020 |
Dualcoop: Fast adaptation to multi-label recognition with limited annotations X Sun, P Hu, K Saenko Advances in Neural Information Processing Systems 35, 30569-30582, 2022 | 104 | 2022 |
Adamml: Adaptive multi-modal learning for efficient video recognition R Panda, CFR Chen, Q Fan, X Sun, K Saenko, A Oliva, R Feris Proceedings of the IEEE/CVF international conference on computer vision …, 2021 | 59 | 2021 |
Dynamic network quantization for efficient video inference X Sun, R Panda, CFR Chen, A Oliva, R Feris, K Saenko Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021 | 50 | 2021 |
Twostreamvan: Improving motion modeling in video generation X Sun, H Xu, K Saenko Proceedings of the IEEE/CVF Winter Conference on Applications of Computer …, 2020 | 34* | 2020 |
A temporally-aware interpolation network for video frame inpainting R Szeto, X Sun, K Lu, JJ Corso IEEE transactions on pattern analysis and machine intelligence 42 (5), 1053-1068, 2019 | 29 | 2019 |
Weakly-supervised compositional featureaggregation for few-shot recognition P Hu, X Sun, K Saenko, S Sclaroff arXiv preprint arXiv:1906.04833, 2019 | 26 | 2019 |
Dime-fm: Distilling multimodal and efficient foundation models X Sun, P Zhang, P Zhang, H Shah, K Saenko, X Xia Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2023 | 19 | 2023 |
Dualcoop++: Fast and effective adaptation to multi-label recognition with limited annotations P Hu, X Sun, S Sclaroff, K Saenko IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023 | 14 | 2023 |
Revisiting few-shot activity detection with class similarity control H Xu, X Sun, E Tzeng, A Das, K Saenko, T Darrell arXiv preprint arXiv:2004.00137, 2020 | 13 | 2020 |
Similarity R-C3D for few-shot temporal activity detection H Xu, B Kang, X Sun, J Feng, K Saenko, T Darrell arXiv preprint arXiv:1812.10000, 2018 | 13 | 2018 |
Koala: Key frame-conditioned long video-LLM R Tan, X Sun, P Hu, J Wang, H Deilamsalehy, BA Plummer, B Russell, ... Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2024 | 11 | 2024 |
A temporally-aware interpolation network for video frame inpainting X Sun, R Szeto, JJ Corso Computer Vision–ACCV 2018: 14th Asian Conference on Computer Vision, Perth …, 2019 | 6 | 2019 |
Improved Techniques for Quantizing Deep Networks with Adaptive Bit-Widths X Sun, R Panda, CFR Chen, N Wang, B Pan, A Oliva, R Feris, K Saenko Proceedings of the IEEE/CVF Winter Conference on Applications of Computer …, 2024 | 4* | 2024 |
CLAMP: Contrastive LAnguage Model Prompt-tuning P Teterwak, X Sun, BA Plummer, K Saenko, SN Lim arXiv preprint arXiv:2312.01629, 2023 | 2 | 2023 |
Label Budget Allocation in Multi-Task Learning X Sun, K Sohn, K Saenko, C Mellina, X Bian arXiv preprint arXiv:2308.12949, 2023 | | 2023 |
Dynamic network quantization for efficient video inference R Panda, X Sun, R Chen, RS Feris, E Saenko US Patent App. 17/566,782, 2023 | | 2023 |
A temporally-aware interpolation network for video frame inpainting X Sun, R Szeto, JJ Corso Computer Vision–ACCV 2018: 14th Asian Conference on Computer Vision, Perth …, 2019 | | 2019 |
DIME-FM: Distilling Multimodal and Efficient Foundation Models from CLIP (Supplementary Materials) X Sun, P Zhang, P Zhang, H Shah, K Saenko, X Xia | | |