no code implementations • 10 Mar 2024 • Debolena Basak, P. K. Srijith, Maunendra Sankar Desarkar
We propose TICOD, Transformer-based Image Captioning and Object detection model for jointly training both tasks by combining the losses obtained from image captioning and object detection networks.
no code implementations • 28 Dec 2022 • Srinivas Anumasa, Geetakrishnasai Gunapati, P. K. Srijith
Specifically, we propose continuous depth recurrent neural differential equations (CDR-NDE) which generalizes RNN models by continuously evolving the hidden states in both the temporal and depth dimensions.
1 code implementation • 12 Oct 2022 • Suvodip Dey, Maunendra Sankar Desarkar, Asif Ekbal, P. K. Srijith
In this work, we propose DialoGen, a novel encoder-decoder based framework for dialogue generation with a generalized context representation that can look beyond the last-$k$ utterances.
no code implementations • 1 Oct 2022 • Manisha Dubey, P. K. Srijith, Maunendra Sankar Desarkar
We also develop a hypernetwork based continually learning temporal point process for continuous modeling of time-to-event sequences with minimal forgetting.
no code implementations • 16 Sep 2022 • Dupati Srikar Chandra, Sakshi Varshney, P. K. Srijith, Sunil Gupta
However, the continual learning performance of existing hypernetwork based approaches are affected by the assumption of independence of the weights across the layers in order to maintain parameter efficiency.
no code implementations • 29 Dec 2021 • Manisha Dubey, Ragja Palakkadavath, P. K. Srijith
Therefore, we propose a novel point process model, Bayesian Neural Hawkes process (BNHP) which leverages uncertainty modelling capability of Bayesian models and generalization capability of the neural networks to model event occurrence times.
no code implementations • 23 Dec 2021 • Srinivas Anumasa, P. K. Srijith
As $T$ implicitly defines the depth of a NODE, posterior distribution over $T$ would also help in model selection in NODE.
no code implementations • 23 Dec 2021 • Srinivas Anumasa, P. K. Srijith
As $T$ implicitly defines the depth of a NODE, posterior distribution over $T$ would also help in model selection in NODE.
no code implementations • WIT (ACL) 2022 • Maunika Tamire, Srinivas Anumasa, P. K. Srijith
In this work, we propose to use recurrent neural ordinary differential equations (RNODE) for social media post classification which consider the time of posting and allow the computation of hidden representation to evolve in a time-sensitive continuous manner.
no code implementations • 8 Aug 2021 • Kumari Deepshikha, Sai Harsha Yelleni, P. K. Srijith, C Krishna Mohan
We demonstrate the effectiveness of the proposed approach on modeling uncertainty in object detection and segmentation tasks using out-of-distribution experiments.
1 code implementation • 17 Jul 2021 • Ayush Jain, P. K. Srijith, Mohammad Emtiyaz Khan
Deep Gaussian Processes (DGPs) are multi-layer, flexible extensions of Gaussian processes but their training remains challenging.
no code implementations • 4 Jun 2021 • Surya Sai Teja Desu, P. K. Srijith, M. V. Panduranga Rao, Naveen Sivadasan
This paper aims to address the intractability of sparse linear regression with $\ell_0$ norm using adiabatic quantum computing, a quantum computing paradigm that is particularly useful for solving optimization problems faster.
1 code implementation • 14 Dec 2020 • Raghav Gupta, P. K. Srijith, Shantanu Desai
We introduce a continuous depth version of the Residual Network (ResNet) called Neural ordinary differential equations (NODE) for the purpose of galaxy morphology classification.
Instrumentation and Methods for Astrophysics Astrophysics of Galaxies
no code implementations • 12 Dec 2020 • Srinivas Anumasa, P. K. Srijith
Neural ordinary differential equations (NODEs) treat computation of intermediate feature vectors as trajectories of ordinary differential equation parameterized by a neural network.
no code implementations • LREC 2020 • P. Jayashree, P. K. Srijith
With the tremendous success of deep learning models on computer vision tasks, there are various emerging works on the Natural Language Processing (NLP) task of Text Classification using parametric models.
no code implementations • 12 Nov 2019 • P. Jayashree, Ballijepalli Shreya, P. K. Srijith
We propose to learn the Gaussian mixture representation of words using a Kullback-Leibler (KL) divergence based objective function.
no code implementations • 5 Jun 2018 • Vinayak Kumar, Vaibhav Singh, P. K. Srijith, Andreas Damianou
This has hindered the application of DGPs in computer vision tasks, an area where deep parametric models (i. e. CNNs) have made breakthroughs.
no code implementations • LREC 2016 • Daniel Preo{\c{t}}iuc-Pietro, P. K. Srijith, Mark Hepple, Trevor Cohn
Streaming media provides a number of unique challenges for computational linguistics.
no code implementations • 25 Dec 2014 • P. K. Srijith, P. Balamurugan, Shirish Shevade
We provide Gaussian process models based on pseudo-likelihood approximation to perform sequence labeling.