Search Results for author: Karan Samel

Found 8 papers, 2 papers with code

On the Efficacy of Text-Based Input Modalities for Action Anticipation

no code implementations23 Jan 2024 Apoorva Beedu, Karan Samel, Irfan Essa

Compared to existing methods, MAT has the advantage of learning additional environmental context from two kinds of text inputs: action descriptions during the pre-training stage, and the text inputs for detected objects and actions during modality feature fusion.

Action Anticipation

Learning Temporal Rules from Noisy Timeseries Data

no code implementations11 Feb 2022 Karan Samel, Zelin Zhao, Binghong Chen, Shuang Li, Dharmashankar Subramanian, Irfan Essa, Le Song

Events across a timeline are a common data representation, seen in different temporal modalities.

ProTo: Program-Guided Transformer for Program-Guided Tasks

1 code implementation NeurIPS 2021 Zelin Zhao, Karan Samel, Binghong Chen, Le Song

Furthermore, we propose the Program-guided Transformer (ProTo), which integrates both semantic and structural guidance of a program by leveraging cross-attention and masked self-attention to pass messages between the specification and routines in the program.

Decision Making Learning to Execute +2

Neural Temporal Logic Programming

no code implementations29 Sep 2021 Karan Samel, Zelin Zhao, Binghong Chen, Shuang Li, Dharmashankar Subramanian, Irfan Essa, Le Song

Events across a timeline are a common data representation, seen in different temporal modalities.

How to Design Sample and Computationally Efficient VQA Models

no code implementations22 Mar 2021 Karan Samel, Zelin Zhao, Binghong Chen, Kuan Wang, Robin Luo, Le Song

In multi-modal reasoning tasks, such as visual question answering (VQA), there have been many modeling and training paradigms tested.

Question Answering Visual Question Answering

Differentiable End-to-End Program Executor for Sample and Computationally Efficient VQA

no code implementations1 Jan 2021 Karan Samel, Zelin Zhao, Kuan Wang, Robin Luo, Binghong Chen, Le Song

We present a differentiable end-to-end program executor (DePe), which addresses Visual Question Answering (VQA) in a sample and computationally efficient manner.

Question Answering Visual Question Answering

Cannot find the paper you are looking for? You can Submit a new open access paper.