Chinmaya Devaraj — accepted AI-conference papers

2024

Diving Deep into the Motion Representation of Video-Text Models

Chinmaya Devaraj, Cornelia Fermuller, Yiannis Aloimonos

ACL 2024findings

Videos are more informative than images becausethey capture the dynamics of the scene.By representing motion in videos, we can capturedynamic activities. In this work, we introduceGPT-4 generated motion descriptions thatcapture fine-grained motion descriptions of activitiesand apply them to three ac…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2020

From Symbols to Signals: Symbolic Variational Autoencoders

Chinmaya Devaraj, Aritra Chowdhury, Arpit Jain, James R. Kubricht, Peter H. Tu, Alberto Santamaría-Pang

ICASSP 2020accepted

We introduce Symbolic Variational Autoencoders which generate images from symbols that represent semantic concepts. Unlike generic Variational Autoencoders (VAEs) or Generative Adversarial Networks (GANs), the latent distribution from the Symbolic Variational Autoencoder is discrete. The symbols are…

Cited by 0 Source ↗Scholar ↗