Projects
Multi-Critic Actor Learning: Teaching RL Policies to Act with Style
Siddharth Mysore, George Cheng, Yunqi Zhao, Kate Saenko, Meng Wu
International Conference on Learning Representations (ICLR), 2022
Moment Matching for Multi-Source Domain Adaptation
Xingchao Peng, Qinxun Bai, Xide Xia, Zijun Huang, Kate Saenko, Bo Wang
IEEE International Conference on Computer Vision (ICCV), 2019 Oral
Semi-supervised Domain Adaptation via Minimax Entropy
Kuniaki Saito, Donghyun Kim, Stan Sclaroff, Trevor Darrell and Kate Saenko
IEEE International Conference on Computer Vision (ICCV), 2019
Language Features Matter: Effective Language Representations for Vision-Language Tasks
Andrea Burns, Reuben Tan, Kate Saenko, Stan Sclaroff, Bryan A. Plummer
IEEE International Conference on Computer Vision (ICCV), 2019
Strong Weak Distribution Alignment for Adaptive Object Detection
Kuniaki Saito, Yoshitaka Ushiku, Tatsuya Harada, Kate Saenko
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019
RISE: Randomized Input Sampling for Explanation of Black-box Models
Vitali Petsiuk, Abir Das, Kate Saenko
British Machine Vision Conference (BMVC), 2018 oral
Syn2Real: A New Benchmark for Synthetic-to-Real Visual Domain Adaptation
Xingchao Peng, Ben Usman, Kuniaki Saito, Neela Kaushik, Judy Hoffman, Kate Saenko
Text-to-Clip Video Retrieval with Early Fusion and Re-Captioning
Huijuan Xu, Kun He, Leonid Sigal, Stan Sclaroff and Kate Saenko
In submission
Joint Event Detection and Description in Continuous Video Streams
Huijuan Xu, Boyang Li, Vasili Ramanishka, Leonid Sigal and Kate Saenko
In submission
Adversarial Dropout Reguralization
Kuniaki Saito, Yoshitaka Ushiku, Tatsuya Harada and Kate Saenko
ICLR 2018
Stable Distribution Alignment Using the Dual of the Adversarial Distance
We investigate whether dualizing the logistic adversarial adaptation problem improves the stability of adaptation procedure and explore its connections to Maximum Mean Discrepancy.
View Project
R-C3D: Region Convolutional 3D Network for Temporal Activity Detection
An end-to-end deep activity detection model based on 'detection by proposal' strategy.
View Project
Explaining Captions Generated by Neural Networks
An "Explainable AI" approach that recovers spatio-temporal locations responsible for the deep captioner's predictions.
View Project
Ask, Attend and Answer: Exploiting Question-guided Spatial Attention for Visual Question Answering
Huijuan Xu and Kate Saenko
European Conference on Computer Vision (ECCV), 2016
Fine-to-Coarse Knowledge Transfer for Low-Res Image Classification
Xingchao Peng, Judy Hoffman, Stella X Yu, Kate Saenko
The 23rd IEEE International Conference on Image Processing, 2016 (ICIP-2016)
Correlation Alignment for Unsupervised Domain Adaptation
Baochen Sun, Jiashi Feng, and Kate Saenko
The Thirtieth AAAI Conference on Artificial Intelligence, 2016 (AAAI-16)
Deep CORAL: Honorable Mention Paper at the TASK-CV workshop at ECCV'16
CORAL: Best Paper Prize at the TASK-CV workshop at ICCV'15
Building ImageNet in One Day (Generating Large Scale Image Datasets from 3D CAD Models)
Baochen Sun, Xingchao Peng, and Kate Saenko
CVPR Workshop on The Future of Datasets in Vision, 2015
VIDEO to TEXT: Automatic Natural Language Description of Video
Click below for papers, data and code.
View Project
Learning Deep Object Detectors from 3D Models
Xingchao Peng, Baochen Sun, Karim Ali, Kate Saenko
International Conference on Computer Vision (ICCV), 2015
From Virtual to Reality: Fast Adaptation of Virtual Object Detectors to Real Domains
Baochen Sun and Kate Saenko
British Machine Vision Conference, 2014
Probabilistic Color De-rendering
Y. Xiong, K. Saenko, T. Zickler, T. Darrell
Domain Adaptation for Object Recognition
Early work on visual domain adaptation for object recognition. View project for details, papers, code and datasets.
View Project