no code implementations • 11 Apr 2024 • Anant Khandelwal
In this study, we explicitly address this problem by employing class-aware prototype alignment weighted by mean class probabilities obtained for the test sample and filtered augmented views.
no code implementations • 24 Oct 2023 • Anant Khandelwal
Inspired by the ability of the diffusion model to generate photorealistic images from the given conditional guidance, we propose recurrent pose alignment to provide pose-aligned texture features as conditional guidance.
no code implementations • 24 Oct 2023 • Anant Khandelwal
To address the long-tail issue of visual relationships, we propose correlation debiasing and a label correlation-based loss to learn unbiased relation representations for long-tailed classes.
no code implementations • 10 Aug 2023 • Anant Khandelwal
To address this problem we propose SegDA module to enhance transfer performance of UDA methods by learning the maximum separable segment representation.
no code implementations • 22 Jul 2023 • Anant Khandelwal
When these are combined with injected attention features, it becomes feasible to query the source contents and scale edited concepts along with the injection of unedited parts.
no code implementations • 1 Jun 2023 • Anant Khandelwal, Happy Mittal, Shreyas Sunil Kulkarni, Deepak Gupta
In a popular e-commerce store, we have deployed our models for 1000s of (product-type, attribute) pairs.
no code implementations • 4 May 2023 • Anant Khandelwal
Existing Question Answering (QA) systems limited by the capability of answering questions from unseen domain or any out-of-domain distributions making them less reliable for deployment to real scenarios.
no code implementations • 8 Apr 2023 • Anant Khandelwal
We propose the idea of concept factorization explaining the collapsed features for base session classes in terms of concept basis and use these to induce classifier simplex for few shot classes.
no code implementations • ACL (dialdoc) 2021 • Anant Khandelwal
An intelligent dialogue system in a multi-turn setting should not only generate the responses which are of good quality, but it should also generate the responses which can lead to long-term success of the dialogue.
no code implementations • 15 Jul 2020 • Anant Khandelwal
Due to widely available social media platforms and increased usage caused the data to be available in huge amounts. The manual methods to process such large data is costly and time-taking, so there has been an increased attention to process and verify such content automatically for the presence of rumors.
Ranked #1 on Stance Classification on SemEval 2019
no code implementations • 15 Jan 2020 • Anant Khandelwal, Niraj Kumar
To solve these problems, we have introduced a unified and robust multi-modal deep learning architecture which works for English code-mixed dataset and uni-lingual English dataset both. The devised system, uses psycho-linguistic features and very ba-sic linguistic features.
Ranked #1 on Text Classification on Facebook Media