Picture for Bhavan Jasani

Bhavan Jasani

Synthesize Step-by-Step: Tools, Templates and LLMs as Data Generators for Reasoning-Based Chart VQA

Add code
Mar 28, 2024
Viaarxiv icon

YORO -- Lightweight End to End Visual Grounding

Add code
Nov 15, 2022
Viaarxiv icon

DocFormer: End-to-End Transformer for Document Understanding

Add code
Jun 22, 2021
Viaarxiv icon

Skeleton based Zero Shot Action Recognition in Joint Pose-Language Semantic Space

Add code
Nov 26, 2019
Figure 1 for Skeleton based Zero Shot Action Recognition in Joint Pose-Language Semantic Space
Figure 2 for Skeleton based Zero Shot Action Recognition in Joint Pose-Language Semantic Space
Figure 3 for Skeleton based Zero Shot Action Recognition in Joint Pose-Language Semantic Space
Figure 4 for Skeleton based Zero Shot Action Recognition in Joint Pose-Language Semantic Space
Viaarxiv icon

Are we asking the right questions in MovieQA?

Add code
Nov 08, 2019
Figure 1 for Are we asking the right questions in MovieQA?
Figure 2 for Are we asking the right questions in MovieQA?
Figure 3 for Are we asking the right questions in MovieQA?
Figure 4 for Are we asking the right questions in MovieQA?
Viaarxiv icon

Learning Sampling Policies for Domain Adaptation

Add code
May 19, 2018
Figure 1 for Learning Sampling Policies for Domain Adaptation
Figure 2 for Learning Sampling Policies for Domain Adaptation
Viaarxiv icon