About Me
Welcome to my homepage! I am a Research Scientist at Adobe Inc., currently working on the development and evaluation of generative AI models for multimodal content synthesis consisting of text, images, videos, and 3D. My general research interests span the domains of affective computing and human motion recognition and synthesis. I completed my Ph.D. in Computer Science at the University of Maryland, College Park, USA, where I worked on Affective Human Motion Detection and Synthesis, and was advised by Prof. Dinesh Manocha and Prof. Aniket Bera. Prior to this, I completed my Master of Engineering and then worked one year as a research associate with Prof. Venu Madhav Govindu at the Department of Electrical Engineering, Indian Institute of Science, where I developed efficient and robust algorithms for robust large-scale 3D reconstructions of objects and scenes from RGB images and raw depth maps.
Highlights
[Upcoming] June 2025
Two papers at CVPR 2025
March 2025
Best paper award at IAAI 2025
August 2024
One paper at ACL 2024
June 2024
Two papers at CVPR 2024
Education
Ph.D. in Computer Science
2018 - 2022
University of Maryland, College Park, USA
Advisor: Dinesh Manocha
M.E. in System Science and Automation
2015 - 2017
Indian Institute of Science, Bengaluru, India
Advisor: Venu Madhav Govindu
B.Tech. in Computer Science and Engineering
2011 - 2015
West Bengal University of Technology, Kolkata, India
Experience
Research Scientist
September 2022 - Present
Adobe Inc., San Jose, CA, USA
Research Intern
May 2022 - August 2022
Google LLC, Mountain View, CA, USA
Research Intern
May 2021 - August 2021, May 2020 - March 2021
Adobe Inc., San Jose, CA, USA
Research Associate
July 2017 - May 2018
Indian Institute of Science, Bengaluru, India
Software Engineer Intern
June 2014 - July 2014
Tata Consultancy Services Innovations Lab, Kolkata, India
Invited Talks
Current Trends in 3D Pose and Motion Generation
2024-04-23 Purdue University
2024-03-12 ACM@UMD Speaker Series
Affective Human Motion Detection and Synthesis
2022-11-08 University of Southern California
Awards and Nominations
IAAI 2025 AI Incidents and Best Practices Best Paper Award
"Evaluation and Incident Prevention in an Enterprise AI Assistant" by
Akash V. Maharaj, David Arbour, Daniel Lee, Uttaran Bhattacharya, Anup Rao, Austin Zane, Avi Feller, Kun Qian, and Yunyao Li.
ACM MIG 2022 Best Paper Award
"Learning Gait Emotions Using Affective and Deep Features" by
Tanmay Randhavane, Uttaran Bhattacharya, Pooja Kabra, Kyra Kapsaskis, Kurt Gray, Dinesh Manocha, and Aniket Bera.
UMD Invention of the Year Award 2022 Nominee
"Deepfake Detection Tool" by Trisha Mittal, Aniket Bera, Uttaran Bhattacharya, Rohan Chandra, and Dinesh Manocha.
UMD Invention of the Year Award 2021 Nominee
"M3ER: Multiplicative Multimodal Emotion Recognition" by Trisha Mittal, Aniket Bera, Uttaran Bhattacharya, Rohan Chandra, and Dinesh Manocha.
ACMMM 2021 Best Paper Award Nominee
"Speech2AffectiveGestures: Synthesizing Co-Speech Gestures with Generative Adversarial Affective
Expression Learning" by Uttaran Bhattacharya, Elizabeth Childs, Nicholas Rewkowski, and Dinesh Manocha.
IEEE VR 2021 Best Paper Award
"Text2Gestures: A Transformer-Based Network for Generating Emotive Body Gestures for Virtual
Agents" by Uttaran Bhattacharya, Nicholas Rewkowski, Abhishek Banerjee, Pooja Guhan, Aniket Bera,
and Dinesh Manocha.
Adobe Research Fellowship, 2021
Adobe Inc.
ACM SAP 2019 Best Poster Award
"Identifying Emotions from Walking Using Affective and Deep Features" by
Tanmay Randhavane, Uttaran Bhattacharya, Aniket Bera, Kyra Kapsaskis, Kurt Gray,
and Dinesh Manocha.
Dean's Fellowship, 2018
University of Maryland, College Park, USA.
Outstanding Student Award, 2013
Institute of Engineering and Management under the West Bengal University of Technology,
Kolkata, India.
Research Interests
- All
- Evaluation of Generative AI Models
- Multimodal Content Understanding
- Affective Computing
Bibliography
Selected Publications
Evaluation of Generative AI Models
-
Akash V. Maharaj, David Arbour, Daniel Lee, Uttaran Bhattacharya, Anup Rao, Austin Zane, Avi Feller, Kun Qian, and Yunyao Li.
"Evaluation and Incident Prevention in an Enterprise AI Assistant".
The Thirty-Seventh Annual Conference on Innovative Applications of Artificial Intelligence (IAAI), 2025.
Conference OralBest Paper Paper Google Scholar
Multimodal Content Understanding
-
Pooja Guhan, Uttaran Bhattacharya, Somdeb Sarkhel, Vahid Azizi, Xiang Chen, Saayan Mitra, Aniket Bera, and Dinesh Manocha.
"TAME-RD: Text Assisted Replication of Image Multi-Adjustments for Reverse Designing".
The 62nd Annual Meeting of the Association for Computational Linguistics (ACL), 2024.
Findings Paper Dataset Google Scholar -
Supreeth Narasimhaswamy, Uttaran Bhattacharya, Xiang Chen, Ishita Dasgupta, Saayan Mitra, and Minh Hoai.
"HanDiffuser: Text-to-Image Generation With Realistic Hand Appearances".
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
Conference Poster Paper Google Scholar -
Ashmit Khandelwal, Aditya Agrawal, Aanisha Bhattacharyya, Yaman K Singla, Somesh Singh, Uttaran Bhattacharya,
Ishita Dasgupta, Stefano Petrangeli, Rajiv Ratn Shah, Changyou Chen, and Balaji Krishnamurthy.
"Large Content And Behavior Models To Understand, Simulate, And Optimize Content And Behavior".
International Conference on Learning Representations (ICLR), 2024.
Conference Spotlight Paper Google Scholar -
Aneesh Bhattacharya, Manas Paranjape, Uttaran Bhattacharya, and Aniket Bera.
"DanceAnyWay: Synthesizing Beat-Guided 3D Dances with Randomized Temporal Contrastive Learning".
The 38th Annual AAAI Conference on Artificial Intelligence (AAAI), 2024.
Conference Poster Paper Code Google Scholar
Affective Computing
-
Tanmay Randhavane, Uttaran Bhattacharya, Pooja Kabra, Kyra Kapsaskis, Kurt Gray, Dinesh Manocha, and Aniket Bera.
"Learning Gait Emotions Using Affective and Deep Features".
ACM SIGGRAPH Conference on Motion, Interaction and Games (MIG), 2022.
Conference OralBest Paper Paper Google Scholar -
Uttaran Bhattacharya, Gang Wu, Stefano Petrangeli, Viswanathan Swaminathan, and Dinesh Manocha.
"HighlightMe: Detecting Highlights from Human-Centric Videos".
IEEE/CVF International Conference on Computer Vision (ICCV), 2021.
Conference Poster Paper Google Scholar -
Uttaran Bhattacharya, Elizabeth Childs, Nicholas Rewkowski, and Dinesh Manocha.
"Speech2AffectiveGestures: Synthesizing Co-Speech Gestures with Generative Adversarial Affective
Expression Learning".
ACM International Conference on Multimedia (ACMMM), 2021.
Conference OralBest Paper Nominee Paper Project Code Google Scholar -
Uttaran Bhattacharya, Nicholas Rewkowski, Abhishek Banerjee, Pooja Guhan, Aniket Bera, and Dinesh Manocha.
"Text2Gestures: A Transformer-Based Network for Generating Emotive Body Gestures for Virtual Agents".
IEEE Conference on Virtual Reality and 3D User Interfaces (IEEE VR), 2021.
Conference OralBest Paper Paper Project Code Google Scholar -
Uttaran Bhattacharya, Trisha Mittal, Rohan Chandra, Tanmay Randhavane, Aniket Bera, and Dinesh Manocha.
"STEP: Spatial Temporal Graph Convolutional Networks for Emotion Perception from Gaits".
The 34th Annual AAAI Conference on Artificial Intelligence (AAAI), 2020.
Conference Spotlight Paper Project Code Google Scholar
3D Scene Reconstruction
-
Uttaran Bhattacharya, and Venu Madhav Govindu.
"Efficient and Robust Registration on The 3D Special Euclidean Group".
IEEE/CVF International Conference on Computer Vision (ICCV), 2019.
Conference Poster Paper Google Scholar -
Uttaran Bhattacharya, Sumit Veerawal, and Venu Madhav Govindu.
"Fast Multiview Registration of 3D Scans using Planar Structures".
International Conference on 3D Vision (3DV), 2017.
Conference Spotlight Paper Google Scholar
Preprints
- Yizhou Wang, Ruiyi Zhang, Haoliang Wang, Uttaran Bhattacharya, Yun Fu, and Gang Wu. "VaQuitA: Enhancing Alignment in LLM-Assisted Video Understanding".