Chetan Kumar
I am third-year doctoral candidate in Computer and Information Science at University of Massachusetts, Dartmouth, working under supervision of Dr.Ming Shao. I have completed my master’s in data science and bachelor’s in computer science. My research interests are in Machine Learning and Artificial Intelligence. Currently, I am working on semi-supervised graph based learning using deep learning.
[NEWS]
[03/2021] Our paper on Collaborative Knowledge Distillation for Incomplete Multi-view Action Prediction has been accepted by Journal of Image and Vision Computing 2021
[08/2020] Defended PhD dissertation proposal on Graph Induced Adversarial Learning and now officially a PhD candidate
[07/2020] Our paper on Adversaril Attack on Multi-Modal data got accepted (acceptance rate: 27.8%) in ACM Multimedia 2020
[06/2020] Accepted an offer to intern at ReviveMed in Cambridge, MA this summer
[04/2020] Received CIS Graduate Research Award for the year 2020 from UMass Dartmouth
[02/2020] Presented our paper on Adversary for Social Good: Protecting Familial Privacy through Joint Adversarial Attacks at AAAI 2020 conference [PDF] [PPT]
[01/2020] Received UMass Dartmouth Provost and Graduate Student Senate (GSS) Travel Award
[11/2019] Received AAAI 2020 Student Travel Award
[11/2019] One paper has been accepted in AAAI 2020 conference (acceptance rate: 20.6%, oral presentation) on Adversarial Samples for Social Good
[10/2019] Gave a seminar on Graph Convolutional Network (GCN) and my current research on Adversary Samples for Social Good in UMass Dartmouth
Conference Paper
- D. Kumar, C. Kumar and M. Shao, Collaborative knowledge distillation for incomplete multi-view action prediction in Image and Vision Computing, 2021 • Paper
- D. Kumar, C. Kumar C. Seah, S. Xia and M. Shao, Finding Achilles' Heel: Adversarial Attack on Multi-modal Action Recognition in 2020 ACM International Conference on Multimedia, Seattle, WA, USA, 2020 • Paper
- C. Kumar, R. Ryan and M. Shao, Adversary for Social Good: Protecting Familial Privacy through Joint Adversarial Attacks in 2020 AAAI Conference on Artifical Intelligence, New York, USA, 2020 • Paper • PPT
- D. Kumar, C. Kumar and M. Shao, Cross-database mammographic image analysis through unsupervised domain adaptation in 2017 IEEE International Conference on Big Data (Big Data), Boston, MA, USA, 2017 • Paper • PPT • Code
Poster Presentation
- Adversary for Social Good: Protecting Familial Privacy through Joint Adversarial Attacks in AAAI 2020 Conference, New York • Poster
- Cross-view Action Recognition via Joint Dictionary and Transfer Learning in 2018 New England Computer Vision Workshop (NECV), Boston
- Cross-database Mammographic Image Analysis through Unsupervised Domain Adaptation in 2017 New England Computer Vision Workshop (NECV), Boston • Poster