Zobrazeno 1 - 10
of 33
pro vyhledávání: '"Gupta, Mithun Das"'
We study visual question answering in a setting where the answer has to be mined from a pool of relevant and irrelevant images given as a context. For such a setting, a model must first retrieve relevant images from the pool and answer the question f
Externí odkaz:
http://arxiv.org/abs/2306.16713
We present a determinantal point process (DPP) inspired alternative to non-maximum suppression (NMS) which has become an integral step in all state-of-the-art object detection frameworks. DPPs have been shown to encourage diversity in subset selectio
Externí odkaz:
http://arxiv.org/abs/2008.11451
In developing countries like India agriculture plays an extremely important role in the lives of the population. In India, around 80\% of the population depend on agriculture or its by-products as the primary means for employment. Given large populat
Externí odkaz:
http://arxiv.org/abs/1906.07573
Autor:
Kumar, Sudhir, Gupta, Mithun Das
We present a conditional generative adversarial model to draw realistic samples from paired fashion clothing distribution and provide real samples to pair with arbitrary fashion units. More concretely, given an image of a shirt, obtained from a fashi
Externí odkaz:
http://arxiv.org/abs/1906.05596
Automatically evaluating the quality of dialogue responses for unstructured domains is a challenging problem. ADEM(Lowe et al. 2017) formulated the automatic evaluation of dialogue systems as a learning problem and showed that such a model was able t
Externí odkaz:
http://arxiv.org/abs/1902.08832
Autor:
Gupta, Mithun Das
Text classification is a fundamental task in NLP applications. Latest research in this field has largely been divided into two major sub-fields. Learning representations is one sub-field and learning deeper models, both sequential and convolutional,
Externí odkaz:
http://arxiv.org/abs/1811.03291
Autor:
Gupta, Mithun Das
In the theory of compressed sensing (CS), the sparsity $\|x\|_0$ of the unknown signal $\mathbf{x} \in \mathcal{R}^n$ is of prime importance and the focus of reconstruction algorithms has mainly been either $\|x\|_0$ or its convex relaxation (via $\|
Externí odkaz:
http://arxiv.org/abs/1605.04657
Autor:
Gupta, Mithun Das
Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2008.
Source: Dissertation Abstracts International, Volume: 69-11, Section: B, page: 7030. Adviser: Thomas S. Huang. Includes bibliographical references (leaves 139-150) Available on mi
Source: Dissertation Abstracts International, Volume: 69-11, Section: B, page: 7030. Adviser: Thomas S. Huang. Includes bibliographical references (leaves 139-150) Available on mi
Autor:
Gupta, Mithun Das, Huang, Thomas S.
We propose a new method for estimating the intrinsic dimension of a dataset by applying the principle of regularized maximum likelihood to the distances between close neighbors. We propose a regularization scheme which is motivated by divergence mini
Externí odkaz:
http://arxiv.org/abs/1203.3483
We study the L1 minimization problem with additional box constraints. We motivate the problem with two different views of optimality considerations. We look into imposing such constraints in projected gradient techniques and propose a worst case line
Externí odkaz:
http://arxiv.org/abs/1010.0141