Search Results for author: Abhishek Jha

Found 8 papers, 4 papers with code

Assigning people to tasks identified in email: The EPA dataset for addressee tagging for detected task intent

no code implementations WS 2018 Revanth Rameshkumar, Peter Bailey, Abhishek Jha, Chris Quirk

We describe the Enron People Assignment (EPA) dataset, in which tasks that are described in emails are associated with the person(s) responsible for carrying out these tasks.

Towards Automatic Face-to-Face Translation

1 code implementation ACM Multimedia, 2019 2019 Prajwal K R, Rudrabha Mukhopadhyay, Jerin Philip, Abhishek Jha, Vinay Namboodiri, C. V. Jawahar

As today's digital communication becomes increasingly visual, we argue that there is a need for systems that can automatically translate a video of a person speaking in language A into a target language B with realistic lip synchronization.

 Ranked #1 on Talking Face Generation on LRW (using extra training data)

Face to Face Translation Machine Translation +3

Glimpse-Attend-and-Explore: Self-Attention for Active Visual Exploration

1 code implementation ICCV 2021 Soroush Seifi, Abhishek Jha, Tinne Tuytelaars

In this paper, we propose the Glimpse-Attend-and-Explore model which: (a) employs self-attention to guide the visual exploration instead of task-specific uncertainty maps; (b) can be used for both dense and sparse prediction tasks; and (c) uses a contrastive stream to further improve the representations learned.

Exploring Low-Cost Transformer Model Compression for Large-Scale Commercial Reply Suggestions

no code implementations27 Nov 2021 Vaishnavi Shrivastava, Radhika Gaonkar, Shashank Gupta, Abhishek Jha

Fine-tuning pre-trained language models improves the quality of commercial reply suggestion systems, but at the cost of unsustainable training times.

Model Compression

Barlow constrained optimization for Visual Question Answering

1 code implementation7 Mar 2022 Abhishek Jha, Badri N. Patro, Luc van Gool, Tinne Tuytelaars

In this paper, we propose a novel regularization for VQA models, Constrained Optimization using Barlow's theory (COB), that improves the information content of the joint space by minimizing the redundancy.

Question Answering Visual Question Answering

The Common Stability Mechanism behind most Self-Supervised Learning Approaches

1 code implementation22 Feb 2024 Abhishek Jha, Matthew B. Blaschko, Yuki M. Asano, Tinne Tuytelaars

Last couple of years have witnessed a tremendous progress in self-supervised learning (SSL), the success of which can be attributed to the introduction of useful inductive biases in the learning process to learn meaningful visual representations while avoiding collapse.

Self-Supervised Learning

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