HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actions

1 code implementation • CVPR 2023 • Anshul Shah, Aniket Roy, Ketul Shah, Shlok Kumar Mishra, David Jacobs, Anoop Cherian, Rama Chellappa

In this work, we propose a new contrastive learning approach to train models for skeleton-based action recognition without labels.

Action Recognition Contrastive Learning +5

MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis

1 code implementation • CVPR 2023 • Tianhong Li, Huiwen Chang, Shlok Kumar Mishra, Han Zhang, Dina Katabi, Dilip Krishnan

In this work, we propose MAsked Generative Encoder (MAGE), the first framework to unify SOTA image generation and self-supervised representation learning.

Image Generation Representation Learning +1

Improved Detection of Face Presentation Attacks Using Image Decomposition

no code implementations • 22 Mar 2021 • Shlok Kumar Mishra, Kuntal Sengupta, Max Horowitz-Gelb, Wen-Sheng Chu, Sofien Bouaziz, David Jacobs

Presentation attack detection (PAD) is a critical component in secure face authentication.

Towards Automatic Generation of Questions from Long Answers

no code implementations • 10 Apr 2020 • Shlok Kumar Mishra, Pranav Goel, Abhishek Sharma, Abhyuday Jagannatha, David Jacobs, Hal Daumé III

Therefore, we propose a novel evaluation benchmark to assess the performance of existing AQG systems for long-text answers.

Information Retrieval Natural Questions +4