Zobrazeno 1 - 10
of 46
pro vyhledávání: '"Jaiswal, Ayush"'
Autor:
Jaiswal, Ayush
We have studied irreducible real (respectively, quaternionic) Lie algebroid connections and prove that the Gauge theoretic moduli space has Hausdorff Hilbert manifold structure. This work generalises some known results about simple semi-connections f
Externí odkaz:
http://arxiv.org/abs/2412.02658
Autor:
Amrutiya, Sanjay, Jaiswal, Ayush
In this article, we will explore the fundamental concepts, including various basic concepts on $d$-complex manifolds, along with several differential operators and examine the relationships between them. A $d$-K\"ahler manifold is a $d$-complex manif
Externí odkaz:
http://arxiv.org/abs/2406.09312
Autor:
Pal, Anwesan, Wadhwa, Sahil, Jaiswal, Ayush, Zhang, Xu, Wu, Yue, Chada, Rakesh, Natarajan, Pradeep, Christensen, Henrik I.
Multi-turn textual feedback-based fashion image retrieval focuses on a real-world setting, where users can iteratively provide information to refine retrieval results until they find an item that fits all their requirements. In this work, we present
Externí odkaz:
http://arxiv.org/abs/2308.10170
Autor:
Amrutiya, Sanjay, Jaiswal, Ayush
Publikováno v:
Proc Math Sci 133, 21 (2023)
We develop the theory of d-holomorphic connections on d-holomorphic vector bundles over a Klein surface by constructing the analogous Atiyah exact sequence for d-holomorphic bundles. We also give a criterion for the existence of d-holomorphic connect
Externí odkaz:
http://arxiv.org/abs/2208.04354
Autor:
Amrutiya, Sanjay, Jaiswal, Ayush
In this article, we study the gauge theoretic aspects of real and quaternionic parabolic bundles over a real curve $(X, \sigma_X)$, where X is a compact Riemann surface and {\sigma}X is an anti-holomorphic involution. For a fixed real or quaternionic
Externí odkaz:
http://arxiv.org/abs/2202.06210
Neural Style Transfer (NST) has quickly evolved from single-style to infinite-style models, also known as Arbitrary Style Transfer (AST). Although appealing results have been widely reported in literature, our empirical studies on four well-known AST
Externí odkaz:
http://arxiv.org/abs/2104.10064
Object detection models perform well at localizing and classifying objects that they are shown during training. However, due to the difficulty and cost associated with creating and annotating detection datasets, trained models detect a limited number
Externí odkaz:
http://arxiv.org/abs/2011.14204
Fake news often involves semantic manipulations across modalities such as image, text, location etc and requires the development of multimodal semantic forensics for its detection. Recent research has centered the problem around images, calling it im
Externí odkaz:
http://arxiv.org/abs/2011.11286
In order to combat the COVID-19 pandemic, society can benefit from various natural language processing applications, such as dialog medical diagnosis systems and information retrieval engines calibrated specifically for COVID-19. These applications r
Externí odkaz:
http://arxiv.org/abs/2007.02461
Autor:
Jaiswal, Ayush, Brekelmans, Rob, Moyer, Daniel, Steeg, Greg Ver, AbdAlmageed, Wael, Natarajan, Premkumar
Supervised machine learning models often associate irrelevant nuisance factors with the prediction target, which hurts generalization. We propose a framework for training robust neural networks that induces invariance to nuisances through learning to
Externí odkaz:
http://arxiv.org/abs/1912.00646