Research Interests

My research broadly lies at the intersection of vision and language. Specifically, I am interested in grounding language in images and videos which entails associating language phrases to visual concepts. Such visual-linguistic associations encompass objects, actions, their relations and are crucial to rich image and video understanding.

Publications

Google Scholar Semantic Scholar

1. Vision-Language Pre-training Generalization: From Image-Text Pairs to Diverse Vision-Text Tasks
   Arka Sadhu, Ram Nevatia
   Accepted to WACV’24
   Paper

2. Unaligned Video-Text Pre-training using Iterative Alignment
   Arka Sadhu, Licheng Yu, Animesh Sinha, Yu Chen, Ram Nevatia, Ning Zhang
   
   Paper

3. Gradient-based Memory Editing for Task-Free Continual Learning
   Xisen Jin, Arka Sadhu, Junyi Du, Xiang Ren
   Neurips 2021
   ArXiv Code

4. Visual Semantic Role Labeling for Video Understanding
   Arka Sadhu, Tanmay Gupta, Mark Yatskar, Ram Nevatia, Aniruddha Kembhavi
   CVPR 2021
   ArXiv Code Website

5. Video Question Answering with Phrases via Semantic Roles
   Arka Sadhu, Kan Chen, Ram Nevatia
   NAACL 2021
   ArXiv Code

6. Improving Object Detection and Attribute Recognition by Feature Entanglement Reduction
   Zhaoheng Zheng, Arka Sadhu, Ram Nevatia
   ICIP 2021
   ArXiv

7. Utilizing Every Image Object for Semi-supervised Phrase Grounding
   Haidong Zhu, Arka Sadhu, Zhaoheng Zheng, Ram Nevatia
   WACV 2021
   ArXiv

8. Visually Grounded Continual Learning of Compositional Phrases
   Xisen Jin, Junyi Du, Arka Sadhu, Ram Nevatia, Xiang Ren
   EMNLP 2020
   ArXiv Code Website

9. Video Object Grounding using Semantic Roles in Language Description
   Arka Sadhu, Kan Chen, Ram Nevatia
   CVPR 2020
   ArXiv Code

10. Zero-Shot Grounding of Objects from Natural Language Queries
    Arka Sadhu, Kan Chen, Ram Nevatia
    ICCV 2019 (Oral)
    ArXiv Code