Adobe Media and Data Science Research (MDSR) Laboratory
Adobe Media and Data Science Research (MDSR) Laboratory
News
Publications
People
Join us!
Collaborators
Charting the Right Manifold: Manifold Mixup for Few-shot Learning
Few-shot learning algorithms aim to learn model parameters capable of adapting to unseen classes with the help of only a few labeled …
Puneet Mangla
,
Nupur Kumari
,
Mayank Singh
,
Abhishek Sinha
,
Balaji Krishnamurthy
,
V N Balasubramaniam.
PDF
Document Structure Extraction using Prior based High Resolution Hierarchical Semantic Segmentation
Structure extraction from document images has been a long-standing research topic due to its high impact on a wide range of practical …
Mausoom Sarkar
,
Milan Aggarwal
,
Arneh Jain
,
Hiresh Gupta
,
Balaji Krishnamurthy
PDF
Explain Your Move: Understanding Agent Actions Using Specific and Relevant Feature Attribution
As deep reinforcement learning (RL) is applied to more tasks, there is a need to visualize and understand the behavior of learned …
Nikaash Puri
,
Sukriti Verma
,
Piyush Gupta
,
Dhruv Kayastha
,
Shripad Deshmukh
,
Balaji Krishnamurthy
,
Sameer Singh
PDF
Form2Seq : A Framework for Higher-Order Form Structure Extraction
Document structure extraction has been a widely researched area for decades with recent works performing it as a semantic segmentation …
Milan Aggarwal
,
Hiresh Gupta
,
Mausoom Sarkar
,
Balaji Krishnamurthy
PDF
Harnessing GANs for Zero-shot Learning of New Classes in Visual Speech Recognition
Visual Speech Recognition (VSR) is the process of recognizing or interpreting speech by watching the lip movements of the speaker. …
Yaman Kumar Singla
,
Dhruva Sharawat
,
Shubham Maheshwari
,
Debanjan Mahata
,
Rajiv Ratn Shah
,
Yifang Yin
,
Roger Zimmermann
,
Amanda Stent
PDF
Keyphrase Extraction as Sequence Labeling Task using Transformers
In this paper, we formulate keyphrase extraction from scholarly articles as a sequence labeling task solved using a BiLSTM-CRF, where …
Dhruva Sahrawat
,
Debanjan Mahata
,
Raymond Zhang
,
Mayank Kulkarni
,
Agniv Sharma
,
Rakesh Gosangi
,
Amanda Stent
,
Yaman Kumar Singla
,
Rajiv Ratn Shah
,
Roger Zimmermann
PDF
Learning based Methods for Code Runtime Complexity Prediction
Predicting the runtime complexity of a programming code is an arduous task. In fact, even for humans, it requires a subtle analysis and …
Jagriti Sikka
,
Kushal Satya
,
Yaman Kumar Singla
,
Shagun Uppal
,
Rajiv Ratn Shah
,
Roger Zimmermann
PDF
MixBoost: Synthetic Oversampling with Boosted Mixup for Handling Extreme Imbalance
Training a classification model on a dataset where the instances of one class outnumber those of the other class is a challenging …
Anubha Kabra
,
Ayush Chopra
,
Nikaash Puri
,
Pinkesh Badjatiya
,
Sukriti Verma
,
Piyush Gupta
,
Balaji Krishnamurthy
PDF
Multi-Modal Association based Grouping for Form Structure Extraction
Document structure extraction has been a widely researched area for decades. Recent work in this direction has been deep …
Milan Aggarwal
,
Mausoom Sarkar
,
Hiresh Gupta
,
Balaji Krishnamurthy
PDF
Retrospective Loss: Looking Back to Improve Training of Deep Neural Networks
Deep neural networks (DNNs) are powerful learning machines that have enabled breakthroughs in several domains. In this work, we …
Surgan Jandial
,
Ayush Chopra
,
Mausoom Sarkar
,
Piyush Gupta
,
Balaji Krishnamurthy
,
Vineeth Balasubramanian
PDF
«
»
Cite
×