E-print Articles

E-print Articles

 

Recent Submissions

  • Singh, Prajwal; Sadekar, Kaustubh; Raman, Shanmuganathan (Cornell University Library, 2021-10)
    Point cloud is an efficient way of representing and storing 3D geometric data. Deep learning algorithms on point clouds are time and memory efficient. Several methods such as PointNet and FoldingNet have been proposed for ...
  • Kayal, Pratik; Anand, Mrinal; Desai, Harsh; Singh, Mayank (Cornell University Library, 2021-05)
    Tables present important information concisely in many scientific documents. Visual features like mathematical symbols, equations, and spanning cells make structure and content extraction from tables embedded in research ...
  • Desai, Harsh; Kayal, Pratik; Singh, Mayank (Cornell University, 2021-05)
    Information Extraction (IE) from the tables present in scientific articles is challenging due to complicated tabular representations and complex embedded text. This paper presents TabLeX, a large-scale benchmark dataset ...
  • Malaviya, Jayesh (Cornell University Library, 2021-04)
    The event sequence of many diverse systems is represented as a sequence of discrete events in a continuous space. Examples of such an event sequence are earthquake aftershock events, financial transactions, e-commerce ...
  • Sadasivan, Vinu Sankar; Dasgupta, Anirban (Cornell University Library, 2021-02)
    Curriculum learning is a training strategy that sorts the training examples by some measure of their difficulty and gradually exposes them to the learner to improve the network performance. In this work, we propose two ...
  • Misra, Neeldhara; Sonar, Chinmay; Vaidyanathan, P. R.; Vaish, Rohit (Cornell University Library, 2021-01)
    We study fair resource allocation under a connectedness constraint wherein a set of indivisible items are arranged on a path and only connected subsets of items may be allocated to the agents. An allocation is deemed fair ...
  • Sadekar, Kaustubh; Singh, Prajwal; Raman, Shanmuganathan (Cornell University Library, 2021-01)
    Handwritten document image binarization is a challenging task due to high diversity in the content, page style, and condition of the documents. While the traditional thresholding methods fail to generalize on such challenging ...
  • Chhaya, Rachit; Choudhari, Jayesh; Dasgupta, Anirban; Shit, Supratim (Cornell University Library, 2020-12)
    We present algorithms that create coresets in an online setting for clustering problems according to a wide subset of Bregman divergences. Notably, our coresets have a small additive error, similar in magnitude to the ...
  • Mastan, Indra Deep; Raman, Shanmuganathan (Cornell University Library, 2020-12)
    We consider the generic deep image enhancement problem where an input image is transformed into a perceptually better-looking image. Recent methods for image enhancement consider the problem by performing style transfer ...
  • Mastan, Indra Deep; Raman, Shanmuganathan (Cornell University Library, 2020-12)
    One of the major challenges of style transfer is the appropriate image features supervision between the output image and the input (style and content) images. An efficient strategy would be to define an object map between ...
  • Sawant, Shriraj P.; Singh, Shruti (Cornell University Library, 2020-12)
    Attention is a complex and broad concept, studied across multiple disciplines spanning artificial intelligence, cognitive science, psychology, neuroscience, and related fields. Although many of the ideas regarding attention ...
  • Jain, Harshil; Patil, Rohit; Mastan, Indra Deep; Raman, Shanmuganathan (Cornell University Library, 2020-11)
    Blind motion deblurring involves reconstructing a sharp image from an observation that is blurry. It is a problem that is ill-posed and lies in the categories of image restoration problems. The training data-based methods ...
  • Mastan, Indra Deep; Raman, Shanmuganathan (Cornell University Library, 2020-11)
    Recently, there is a vast interest in developing image feature learning methods that are independent of the training data, such as deep image prior, InGAN, SinGAN, and DCIL. These methods are unsupervised and are used to ...
  • Srivastava, Vivek; Singh, Mayank (Cornell University Library, 2020-10)
    WhatsApp Messenger is one of the most popular channels for spreading information with a current reach of more than 180 countries and 2 billion people. Its widespread usage has made it one of the most popular media for ...
  • Jain, Harshil; Agarwal, Akshat; Shridhar, Kumar; Kleyko, Denis (Cornell University Library, 2020-10)
    Deep neural networks have demonstrated their superior performance in almost every Natural Language Processing task, however, their increasing complexity raises concerns. In particular, these networks require high expenses ...
  • Chierichetti, Flavio; Dasgupta, Anirban; Kumar, Ravi (Cornell University Library, 2020-10)
  • Gowda, Kishen N.; Lonkar, Aditya; Panolan, Fahad; Patel, Vraj; Saurabh, Saket (Cornell University Library, 2020-09)
  • Harilal, Nidhin; Bhatia, Udit; Singh, Mayank (Cornell University Library, 2020-09)
  • Doshi, Ishita; Sajjalla, Sreekalyan; Choudhari, Jayesh; Bhatt, Rushi; Dasgupta, Anirban (Cornell University Library, 2020-08)
    We address the problem of large scale real time classification of content posted on social networks, along with the need to rapidly identify novel spam types. Obtaining manual labels for user generated content using editorial ...
  • Dhakal, Aditya; Cho, Junguk; Kulkarni, Sameer G.; Ramakrishnan, K. K.; Sharma, Puneet (Cornell University Library, 2020-08)
    GPUs are used for training, inference, and tuning the machine learning models. However, Deep Neural Network (DNN) vary widely in their ability to exploit the full power of high-performance GPUs. Spatial sharing of GPU ...

View more