Conference Publications

ShapeGrasp: Zero-Shot Object Grasping with LLMs via Geometric Decomposition

S. Li, S. Bhagat, J. Campbell, Y. Xie, W. Kim, K. Sycara, S. Stepputtis
Under Review, 2024
Website Paper

Let Me Help You! Neuro-Symbolic Short-Context Action Anticipation

S. Bhagat, S. Li, J. Campbell, Y. Xie, K. Sycara, S. Stepputtis
IEEE Robotics and Automation Letters (RA-L) (Under Review), 2024
Website Video Demo

Sample-Efficient Learning of Novel Visual Concepts

S. Bhagat*, S. Stepputtis*, J. Campbell, K. Sycara
Conference on Lifelong Learning Agents (CoLLAs), 2023
🏆 Oral; Top 20% of Accepted Papers Website Paper Code Video Thread

Suspect Identification Framework using Contrastive Relevance Feedback

D. Gupta, A. Saini, D. Bhasin, S. Bhagat, S. Uppal, P. Kumaraguru, R. Shah
Winter Conference on Applications of Computer Vision (WACV), 2023 Paper Video

Emotional Talking Faces: Making Videos More Expressive and Realistic

S. Goyal, S. Uppal, S. Bhagat, D. Goel, S. Mali, Y. Yu, Y. Yin, R. Shah
ACM Multimedia Asia (MMAsia), 2022
🏆 Best Demo Paper Award; 300+ stars on GitHub Paper Code Video Project Page

Disentangling Multiple Features in Video Sequences using Gaussian Processes in Variational Autoencoders

S. Bhagat*, S. Uppal*, Z. Yin, N. Lim
European Conference on Computer Vision (ECCV), 2020
ICVGIP 2020 Vision India Paper Code Video

UAV Target Tracking in Urban Environments Using Deep Reinforcement Learning

S. Bhagat, P.B. Sujit
International Conference on Unmanned Aircraft Systems (ICUAS), 2020
🏆 Oral; 50+ Citations Paper Video

C3VQG: Category Consistent Cyclic Visual Question Generation.

S. Uppal*, A. Madan*, S. Bhagat*, Y. Yu, R. Shah
ACM Multimedia Asia (MMAsia), 2020
VQA and Dialogue Workshop, Computer Vision and Pattern Recognition (CVPR), 2020 (Spotlight) Paper Code Video

PrOSe: Product of Orthogonal Spheres Parameterization for Disentangled Representation Learning

A. Shukla, S. Bhagat*, S. Uppal*, S. Anand, P. Turaga
British Machine Vision Conference (BMVC), 2019 Paper

Geometry of Deep Generative Models for Disentangled Representations

A. Shukla, S. Uppal*, S. Bhagat*, S. Anand, P. Turaga
Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP), 2018 Paper

Journal Publications

Multimodal Research in Vision and Language: A Review of Current and Emerging Trends

S. Uppal*, S. Bhagat*, D. Hazarika, N. Majumdar, S. Poria, R. Zimmermann, A. Zadeh
Information Fusion Journal, 2021 (Impact Factor: 15.7)
🏆 50+ citations Paper

Deep Reinforcement Learning for Soft Robotic Applications: Brief Overview with Impending Challenges

S. Bhagat*, H. Banerjee*, Z. Tse, H. Ren
Robotics 2019, 8(1), 4
🏆 100+ citations Paper

Thesis

Geometry of Neural Network based Disentangled Latent Space Models

Advisors: S. Anand (IIIT-Delhi), P. Turaga (Arizona State University)
Bachelor's Thesis Thesis

Workshop Publications

Knowledge-Guided Short-Context Action Anticipation in Human-Centric Videos

S. Bhagat, S. Stepputtis, J. Campbell, K. Sycara
Workshop on AI for Creative Video Editing and Understanding, ICCV 2023 Paper Video Thread

Emotionally Enhanced Talking Face Generation

S. Goyal, S. Bhagat, S. Uppal, Y. Yu, Y. Yin, R. Shah
Workshop on AI for Creative Video Editing and Understanding, ICCV 2023
Workshop on Multimedia Content Generation and Evaluation: New Methods and Practice (McGE), MM 2023 Paper Code Video

Contrastive Personalization Approach to Suspect Identification

D. Gupta, D. Bhasin, S. Bhagat, S. Uppal, P. Kumaraguru, R. Shah
AAAI Student Abstract 2021 Paper

DisCont: Self-Supervised Visual Attribute Disentanglement using Context Vectors

S. Bhagat*, V. Udandarao*, S. Uppal*, S. Anand
Perception Through Structured Generative Models, ECCV 2020
ML Interpretability for Scientific Discovery, ICML 2020. Paper Code Video