Sort by: Order: Results:

  • Mastan, Indra Deep; Raman, Shanmuganathan (Cornell University Library, 2019-12)
    Recently, there is a vast interest in developing methods which are independent of the training samples such as deep image prior, zero-shot learning, and internal learning. The methods above are based on the common goal of ...
  • Singh, Shubham Kumar; Miyapuram, Krishna P.; Raman, Shanmuganathan (Cornell University Library, 2019-11)
    Person re-identification aims to associate images of the same person over multiple non-overlapping camera views at different times. Depending on the human operator, manual re-identification in large camera networks is ...
  • Kumawat, Sudhakar; Verma, Manisha; Nakashima, Yuta; Raman, Shanmuganathan (Cornell University Library, 2020-07)
    Conventional 3D convolutional neural networks (CNNs) are computationally expensive, memory intensive, prone to overfitting, and most importantly, there is a need to improve their feature learning capabilities. To address ...
  • Kumawat, Sudhakar; Raman, Shanmuganathan (Cornell University Library, 2020-01)
    In this paper, we propose a new convolutional layer called Depthwise-STFT Separable layer that can serve as an alternative to the standard depthwise separable convolutional layer. The construction of the proposed layer is ...

Search Digital Repository


My Account