Manoj Kumar

is this you? claim profile


  • VideoFlow: A Flow-Based Generative Model for Video

    Generative models that can model and predict sequences of future events can, in principle, learn to capture complex real-world phenomena, such as physical interactions. In particular, learning predictive models of videos offers an especially appealing mechanism to enable a rich understanding of the physical world: videos of real-world interactions are plentiful and readily available, and a model that can predict future video frames can not only capture useful representations of the world, but can be useful in its own right, for problems such as model-based robotic control. However, a central challenge in video prediction is that the future is highly uncertain: a sequence of past observations of events can imply many possible futures. Although a number of recent works have studied probabilistic models that can represent uncertain futures, such models are either extremely expensive computationally (as in the case of pixel-level autoregressive models), or do not directly optimize the likelihood of the data. In this work, we propose a model for video prediction based on normalizing flows, which allows for direct optimization of the data likelihood, and produces high-quality stochastic predictions. To our knowledge, our work is the first to propose multi-frame video prediction with normalizing flows. We describe an approach for modeling the latent space dynamics, and demonstrate that flow-based generative models offer a viable and competitive approach to generative modeling of video.

    03/04/2019 ∙ by Manoj Kumar, et al. ∙ 6 share

    read it

  • A New Approach of Improving CFA Image for Digital Camera's

    This paper work directly towards the improving the quality of the image for the digital cameras and other visual capturing products. In this Paper, the authors clearly defines the problems occurs in the CFA image. A different methodology for removing the noise is discuses in the paper for color correction and color balancing of the image. At the same time, the authors also proposed a new methodology of providing denoisiing process before the demosaickingfor the improving the image quality of CFA which is much efficient then the other previous defined. The demosaicking process for producing the colors in the image in a best way is also discuss.

    04/24/2012 ∙ by Manoj Kumar, et al. ∙ 0 share

    read it

  • Design and Implementation of an Improved Carry Increment Adder

    A complex digital circuit comprises of adder as a basic unit. The performance of the circuit depends on the design of this basic adder unit. The speed of operation of a circuit is one of the important performance criteria of many digital circuits which ultimately depends on the delay of the basic adder unit. Many research works have been devoted in improving the delay of the adder circuit. In this paper we have proposed an improved carry increment adder (CIA) that improves the delay performance of the circuit. The improvement is achieved by incorporating carry look adder (CLA) in the design of CIA contrary to the previous design of CIA that employs ripple carry adder (RCA). A simulation study is carried out for comparative analysis. The coding is done in Verilog hardware description language (HDL) and the simulation is carried out in Xilinx ISE 13.1 environment.

    03/10/2016 ∙ by Aribam Balarampyari Devi, et al. ∙ 0 share

    read it

  • Mathematical Foundations of the GraphBLAS

    The GraphBLAS standard ( is being developed to bring the potential of matrix based graph algorithms to the broadest possible audience. Mathematically the Graph- BLAS defines a core set of matrix-based graph operations that can be used to implement a wide class of graph algorithms in a wide range of programming environments. This paper provides an introduction to the mathematics of the GraphBLAS. Graphs represent connections between vertices with edges. Matrices can represent a wide range of graphs using adjacency matrices or incidence matrices. Adjacency matrices are often easier to analyze while incidence matrices are often better for representing data. Fortunately, the two are easily connected by matrix mul- tiplication. A key feature of matrix mathematics is that a very small number of matrix operations can be used to manipulate a very wide range of graphs. This composability of small number of operations is the foundation of the GraphBLAS. A standard such as the GraphBLAS can only be effective if it has low performance overhead. Performance measurements of prototype GraphBLAS implementations indicate that the overhead is low.

    06/18/2016 ∙ by Jeremy Kepner, et al. ∙ 0 share

    read it

  • Parallel Architecture and Hyperparameter Search via Successive Halving and Classification

    We present a simple and powerful algorithm for parallel black box optimization called Successive Halving and Classification (SHAC). The algorithm operates in K stages of parallel function evaluations and trains a cascade of binary classifiers to iteratively cull the undesirable regions of the search space. SHAC is easy to implement, requires no tuning of its own configuration parameters, is invariant to the scale of the objective function and can be built using any choice of binary classifier. We adopt tree-based classifiers within SHAC and achieve competitive performance against several strong baselines for optimizing synthetic functions, hyperparameters and architectures.

    05/25/2018 ∙ by Manoj Kumar, et al. ∙ 0 share

    read it

  • Measuring Conversational Productivity in Child Forensic Interviews

    Child Forensic Interviewing (FI) presents a challenge for effective information retrieval and decision making. The high stakes associated with the process demand that expert legal interviewers are able to effectively establish a channel of communication and elicit substantive knowledge from the child-client while minimizing potential for experiencing trauma. As a first step toward computationally modeling and producing quality spoken interviewing strategies and a generalized understanding of interview dynamics, we propose a novel methodology to computationally model effectiveness criteria, by applying summarization and topic modeling techniques to objectively measure and rank the responsiveness and conversational productivity of a child during FI. We score information retrieval by constructing an agenda to represent general topics of interest and measuring alignment with a given response and leveraging lexical entrainment for responsiveness. For comparison, we present our methods along with traditional metrics of evaluation and discuss the use of prior information for generating situational awareness.

    06/08/2018 ∙ by Victor Ardulov, et al. ∙ 0 share

    read it