I received my PhD at UC San Diego supervised by Truong Nguyen and Serge Belongie in 2018. My research interests include object detection, semantic segmentation in images and videos. See my UCSD webpage
for more details. At present, I am a researcher in Intel AI Lab.
2018 |
| Tripathi, Subarna; Lipton, Zachary Chase; Nguyen, Truong Correction by Projection: Denoising Images with Generative Adversarial Networks CoRR, abs/1803.04477 2018. (Links | BibTeX) @article{Tripathi2018,
title = {Correction by Projection: Denoising Images with Generative Adversarial Networks},
author = {Subarna Tripathi and Zachary Chase Lipton and Truong Nguyen},
url = {http://arxiv.org/abs/1803.04477},
year = {2018},
date = {2018-03-12},
journal = {CoRR},
volume = {abs/1803.04477},
keywords = {}
}
|
2017 |
| Tripathi, Subarna; Dane, Gokce; Kang, Byeongkeun; Bhaskaran, Vasudev; Nguyen, Truong LCDet: Low-Complexity Fully-Convolutional Neural Networks for Object Detection in Embedded Systems Computer Vision and Pattern Recognition Workshop (CVPRW), Honolulu, HI, 2017. (Links | BibTeX) @conference{Tripathi2017b,
title = {LCDet: Low-Complexity Fully-Convolutional Neural Networks for Object Detection in Embedded Systems},
author = {Subarna Tripathi and Gokce Dane and Byeongkeun Kang and Vasudev Bhaskaran and Truong Nguyen},
url = {https://vision.cornell.edu/se3/wp-content/uploads/2017/07/LCDet_CVPRW.pdf},
year = {2017},
date = {2017-07-21},
booktitle = {Computer Vision and Pattern Recognition Workshop (CVPRW)},
journal = {Computer Vision and Pattern Recognition Workshop},
address = {Honolulu, HI},
keywords = {}
}
|
| Lipton, Zachary; Tripathi, Subarna Precise Recovery of Latent Vectors from Generative Adversarial Networks ICLR workshop, 2017. (Links | BibTeX) @article{Lipton2017,
title = {Precise Recovery of Latent Vectors from Generative Adversarial Networks},
author = {Zachary C. Lipton and Subarna Tripathi},
url = {https://vision.cornell.edu/se3/wp-content/uploads/2017/03/recovering-latent-vectors.pdf},
year = {2017},
date = {2017-04-26},
journal = {ICLR workshop},
keywords = {}
}
|
| Tripathi, Subarna; Collins, Maxwell; Brown, Matthew; Belongie, Serge Pose2Instance: Harnessing Keypoints for Person Instance Segmentation arXiv preprint arXiv:1704.01152, 2017. (Links | BibTeX) @article{Tripathi2017,
title = {Pose2Instance: Harnessing Keypoints for Person Instance Segmentation},
author = {Subarna Tripathi and Maxwell Collins and Matthew Brown and Serge Belongie},
url = {https://vision.cornell.edu/se3/wp-content/uploads/2017/05/pose2instance-arxiv.pdf},
year = {2017},
date = {2017-04-04},
journal = {arXiv preprint arXiv:1704.01152},
keywords = {}
}
|
| Tripathi, Subarna; Guenter, Brian A Statistical Approach to Continuous Self-Calibrating Eye Gaze Tracking for Head-Mounted Virtual Reality Systems WACV, 2017. (Abstract | Links | BibTeX) @article{Tripathi2016b,
title = {A Statistical Approach to Continuous Self-Calibrating Eye Gaze Tracking for Head-Mounted Virtual Reality Systems},
author = {Subarna Tripathi and Brian Guenter},
url = {https://vision.cornell.edu/se3/wp-content/uploads/2016/12/statistical-approach-continuous.pdf},
year = {2017},
date = {2017-03-01},
journal = {WACV},
abstract = {We present a novel, automatic eye gaze tracking scheme inspired by smooth pursuit eye motion while playing mobile games or watching virtual reality contents. Our algorithm continuously calibrates an eye tracking system for a head mounted display. This eliminates the need for an explicit calibration step and automatically compensates for small movements of the headset with respect to the head. The algorithm finds correspondences between corneal motion and
screen space motion, and uses these to generate Gaussian Process Regression models. A combination of those models provides a continuous mapping from corneal position to screen space position. Accuracy is nearly as good as achieved with an explicit calibration step.},
keywords = {}
}
We present a novel, automatic eye gaze tracking scheme inspired by smooth pursuit eye motion while playing mobile games or watching virtual reality contents. Our algorithm continuously calibrates an eye tracking system for a head mounted display. This eliminates the need for an explicit calibration step and automatically compensates for small movements of the headset with respect to the head. The algorithm finds correspondences between corneal motion and
screen space motion, and uses these to generate Gaussian Process Regression models. A combination of those models provides a continuous mapping from corneal position to screen space position. Accuracy is nearly as good as achieved with an explicit calibration step.
|
2016 |
| Tripathi, Subarna; Lipton, Zachary; Belongie, Serge; Nguyen, Truong Context Matters: Refining Object Detection in Video with Recurrent Neural Networks British Machine Vision Conference (BMVC), York, UK, 2016. (Links | BibTeX) @conference{Tripathi2016_BMVC,
title = {Context Matters: Refining Object Detection in Video with Recurrent Neural Networks},
author = {Subarna Tripathi and Zachary C. Lipton and Serge Belongie and Truong Nguyen},
url = {http://vision.cornell.edu/se3/wp-content/uploads/2016/07/video_object_detection_BMVC.pdf},
year = {2016},
date = {2016-09-22},
booktitle = {British Machine Vision Conference (BMVC)},
address = {York, UK},
keywords = {}
}
|
| Tripathi, Subarna; Belongie, Serge; Hwang, Youngbae; Nguyen, Truong Detecting Temporally Consistent Objects in Videos through Object Class Label Propagation Winter Conference on Applications of Computer Vision (WACV), 2016. (Links | BibTeX) @conference{Tripathi2016,
title = {Detecting Temporally Consistent Objects in Videos through Object Class Label Propagation},
author = {Subarna Tripathi and Serge Belongie and Youngbae Hwang and Truong Nguyen},
url = {http://vision.cornell.edu/se3/wp-content/uploads/2016/01/OVERLAP_WACV_275.pdf},
year = {2016},
date = {2016-03-07},
booktitle = {Winter Conference on Applications of Computer Vision (WACV)},
keywords = {}
}
|
2015 |
| Tripathi, Subarna; Belongie, Serge; Hwang, Youngbae; Nguyen, Truong Semantic Video Segmentation : Exploring Inference Efficiency ISOCC, 2015. (Links | BibTeX) @conference{Tripathi2015,
title = {Semantic Video Segmentation : Exploring Inference Efficiency},
author = {Subarna Tripathi and Serge Belongie and Youngbae Hwang and Truong Nguyen},
url = {http://vision.cornell.edu/se3/wp-content/uploads/2016/07/ISOCC_video_inference.pdf},
year = {2015},
date = {2015-11-05},
booktitle = {ISOCC},
keywords = {}
}
|
2014 |
| Tripathi, Subarna; Hwang, Youngbae; Belongie, Serge; Nguyen, Truong Improving Streaming Video Segmentation with Early and Mid-Level Visual Processing Winter Conference on Applications of Computer Vision (WACV), Steamboat Springs, CO, 2014. (Links | BibTeX) @inproceedings{491,
title = {Improving Streaming Video Segmentation with Early and Mid-Level Visual Processing},
author = {Subarna Tripathi and Youngbae Hwang and Serge Belongie and Truong Nguyen},
url = {/se3/wp-content/uploads/2014/09/ImprovingStreamGBH.pdf},
year = {2014},
date = {2014-01-01},
booktitle = {Winter Conference on Applications of Computer Vision (WACV)},
address = {Steamboat Springs, CO},
keywords = {}
}
|