no code implementations • 18 Sep 2023 • Shubham Trehan, Udhav Ramachandran, Ruth Scimeca, Sathyanarayanan N. Aakur
Developing reliable computational frameworks for early parasite detection, particularly at the ova (or egg) stage is crucial for advancing healthcare and effectively managing potential public health crises.
no code implementations • 14 Aug 2023 • Shenyuan Liang, Mauricio Pamplona Segundo, Sathyanarayanan N. Aakur, Sudeep Sarkar, Anuj Srivastava
This, in turn, requires optimization over the permutation group, made challenging by differences in nodes (in terms of numbers, locations) and edges (in terms of shapes, placements, and sizes) across objects.
no code implementations • 26 May 2023 • Sathyanarayanan N. Aakur, Sanjoy Kundu, Shubham Trehan
Learning to infer labels in an open world, i. e., in an environment where the target ``labels'' are unknown, is an important characteristic for achieving autonomy.
no code implementations • CVPR 2023 • Sanjoy Kundu, Sathyanarayanan N. Aakur
Current approaches take a generation-by-classification approach where the scene graph is generated through labeling of all possible edges between objects in a scene, which adds computational overhead to the approach.
no code implementations • 30 Nov 2022 • Sanjoy Kundu, Sathyanarayanan N. Aakur
Current approaches take a generation-by-classification approach where the scene graph is generated through labeling of all possible edges between objects in a scene, which adds computational overhead to the approach.
no code implementations • 30 Nov 2022 • Sai Narayanan, Sathyanarayanan N. Aakur, Priyadharsini Ramamurthy, Arunkumar Bagavathi, Vishalini Ramnath, Akhilesh Ramachandran
The emergence of zoonotic diseases from novel pathogens, such as the influenza virus in 1918 and SARS-CoV-2 in 2019 that can jump species barriers and lead to pandemic underscores the need for scalable metagenome analysis.
no code implementations • 31 Mar 2022 • Vishal Pallagani, Priyadharsini Ramamurthy, Vedant Khandelwal, Revathy Venkataramanan, Kausik Lakkaraju, Sathyanarayanan N. Aakur, Biplav Srivastava
This demands a need for better representation of the recipes, overcoming the ambiguity and sparseness that exists in the current textual documents.
no code implementations • 9 Nov 2021 • Sathyanarayanan N. Aakur, Vineela Indla, Vennela Indla, Sai Narayanan, Arunkumar Bagavathi, Vishalini Laguduva Ramnath, Akhilesh Ramachandran
There is an increased need for learning robust representations from metagenome reads since pathogens within a family can have highly similar genome structures (some more than 90%) and hence enable the segmentation and identification of novel pathogen sequences with limited labeled data.
1 code implementation • 9 Nov 2021 • Shubham Trehan, Sathyanarayanan N. Aakur
We formulate an energy-based mechanism that combines predictive learning and reactive control to perform active action localization without rewards, which can be sparse or non-existent in real-world environments.
no code implementations • 21 Jul 2021 • Sathyanarayanan N. Aakur, Sai Narayanan, Vineela Indla, Arunkumar Bagavathi, Vishalini Laguduva Ramnath, Akhilesh Ramachandran
However, there are significant challenges in developing such an approach, the chief among which is to learn self-supervised representations that can help detect novel pathogen signatures with very low amounts of labeled data.
no code implementations • 29 Apr 2021 • Sathyanarayanan N. Aakur, Sudeep Sarkar
We tackle the problem of learning actor-centered representations through the notion of continual hierarchical predictive learning to localize actions in streaming videos without the need for training labels and outlines for the objects in the video.
no code implementations • 16 Sep 2020 • Sathyanarayanan N. Aakur, Sanjoy Kundu, Nikhil Gunti
Building upon the compositional representation offered by Grenander's Pattern Theory formalism, we show that attention and commonsense knowledge can be used to enable the self-supervised discovery of novel actions in egocentric videos in an open-world setting, where data from the observed environment (the target domain) is open i. e., the vocabulary is partially known and training examples (both labeled and unlabeled) are not available.
no code implementations • 24 Jul 2020 • Sai Narayanan, Akhilesh Ramachandran, Sathyanarayanan N. Aakur, Arunkumar Bagavathi
Bovine Respiratory Disease Complex (BRDC) is a complex respiratory disease in cattle with multiple etiologies, including bacterial and viral.
BIG-bench Machine Learning Cultural Vocal Bursts Intensity Prediction +3
no code implementations • ECCV 2020 • Sathyanarayanan N. Aakur, Sudeep Sarkar
It does not require any training annotations in terms of frame-level bounding boxes.
no code implementations • 30 Jan 2020 • Sathyanarayanan N. Aakur, Arunkumar Bagavathi
Egocentric perception has grown rapidly with the advent of immersive computing devices.
no code implementations • 6 Sep 2019 • Sathyanarayanan N. Aakur, Sudeep Sarkar
We find that large amounts of training data are necessary, both for pre-training as well as fine-tuning to a task, for the models to perform well on the designated task.
1 code implementation • CVPR 2019 • Sathyanarayanan N. Aakur, Sudeep Sarkar
We also show that the proposed approach is able to learn highly discriminative features that help improve action recognition when used in a representation learning paradigm.
no code implementations • 11 Aug 2017 • Sathyanarayanan N. Aakur, Fillipe DM de Souza, Sudeep Sarkar
Through extensive experiments, we show that the use of commonsense knowledge from ConceptNet allows the proposed approach to handle various challenges such as training data imbalance, weak features, and complex semantic relationships and visual scenes.