Publications

* indicates equal contribution.



Conference Papers



A variational autoencoder (MGP-VAE) which uses Gaussian processes (GP) to model the latent space for the unsupervised learning of disentangled representations in video sequences.
European Conference on Computer Vision (ECCV) 2020
An NLI framework to improve classification performance using textual entailment.
Asia-Pacific Chapter of the Association for Computational Linguistics (AACL-IJCNLP) 2020
Learning disentangled latent space representations as a parameterized product of orthogonal spheres for images.
British Machine Vision Conference (BMVC) 2019
A selfsupervised framework to disentangle multiple factors of variation by exploiting the structural inductive biases within images.
PTSGM Workshop, ECCV, 2020, MLI4SD Workshop, ICML, 2020
A weakly-supervised VAE setting for question generation using category consistent cyclic loss and structured latent space constraints.
Computer Vision and Pattern Recognition Workshop (CVPRW), 2020

Analysis of latent spaces of different models of disentanglement under the lens of Riemannian Geometry.
Indian Conference on Vision, Graphics and Image Processing (ICVGIP) 2018

Predicting the code complexity of programming codes using feature engineering as well as code embeddings.
European Conference on Information Retrieval (ECIR), 2020

Teaching

Deep Learning (CSE641)

Graduate Level Course
Worked as a Teaching Assistant in my final year for the Deep Learning course offered by Dr. Saket Anand in Spring 2020.
Responsibilities: Preparing and grading assignments, grading sheets, doubt-clearing sessions and office hours.

Machine Learning (CSE543)

Graduate Level Course
Worked as a Teaching Assistant in my final year for the Machine Learning course offered by Dr. Saket Anand in Fall 2019.
Responsibilities: Preparing and grading assignments, grading sheets, doubt-clearing sessions and office hours.

Contact

Please feel free to reach to me for any query or interesting collaborations.

  • shagun16088 [at] iiitd [dot] ac [dot] in