Publications
Visual Programming: Compositional visual reasoning without training
arXiv 2022
GRIT: General Robust Image Task Benchmark
arXiv 2022
Webly Supervised Concept Expansion for General Purpose Vision Models
ECCV 2022
Towards General Purpose Vision Systems: An End-to-End Task-Agnostic Vision-Language Architecture
CVPR 2022 (Oral)
Learning Curves for Analysis of Deep Networks
ICML 2021
Visual Semantic Role Labeling for Video Understanding
CVPR 2021
Contrastive Learning for Weakly Supervised Phrase Grounding
ECCV 2020 (Spotlight)
PhD Thesis: Representations from Vision and Language
Thomas M. Siebel Center for Computer Science
University of Illinois Urbana-Champaign
May 2020
University of Illinois Urbana-Champaign
May 2020
ViCo: Word Embeddings from Visual Co-occurrences
ICCV 2019
No-Frills Human-Object Interaction Detection: Factorization, Layout Encodings, and Training Techniques
ICCV 2019
Imagine This! Scripts to Compositions to Videos
ECCV 2018
Aligned Image-Word Representations Improve Inductive Transfer Across Vision-Language Tasks
ICCV 2017
3DFS: Deformable Dense Depth Fusion and Segmentation for Object Reconstruction from a Handheld Camera
arXiv 2016
Completing 3D Object Shape from One Depth Image
CVPR 2015
Face Tracking and Recognition with Orientation, Pose and Illumination Variations
Undergraduate Thesis, Department of Electrical Engineeging, IIT Kanpur. 2014
