skip to main content

Search for: All records

Creators/Authors contains: "Sarkar, S."

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. Avidan, S. ; Brostow, G. ; Cissé, M ; Farinella, G.M. ; Hassner, T. (Ed.)
    Event perception tasks such as recognizing and localizing actions in streaming videos are essential for scaling to real-world application contexts. We tackle the problem of learning actor-centered representations through the notion of continual hierarchical predictive learning to localize actions in streaming videos without the need for training labels and outlines for the objects in the video. We propose a framework driven by the notion of hierarchical predictive learning to construct actor-centered features by attention-based contextualization. The key idea is that predictable features or objects do not attract attention and hence do not contribute to the action of interest. Experiments on three benchmark datasets show that the approach can learn robust representations for localizing actions using only one epoch of training, i.e., a single pass through the streaming video. We show that the proposed approach outperforms unsupervised and weakly supervised baselines while offering competitive performance to fully supervised approaches. Additionally, we extend the model to multi-actor settings to recognize group activities while localizing the multiple, plausible actors. We also show that it generalizes to out-of-domain data with limited performance degradation.
    Free, publicly-accessible full text available October 23, 2023
  2. Avidan, S. ; Brostow, G. ; Cissé, M. ; Farinella. G.M. ; Hassner, T. (Ed.)
    Graph-based representations are becoming increasingly popular for representing and analyzing video data, especially in object tracking and scene understanding applications. Accordingly, an essential tool in this approach is to generate statistical inferences for graphical time series associated with videos. This paper develops a Kalman-smoothing method for estimating graphs from noisy, cluttered, and incomplete data. The main challenge here is to find and preserve the registration of nodes (salient detected objects) across time frames when the data has noise and clutter due to false and missing nodes. First, we introduce a quotient-space representation of graphs that incorporates temporal registration of nodes, and we use that metric structure to impose a dynamical model on graph evolution. Then, we derive a Kalman smoother, adapted to the quotient space geometry, to estimate dense, smooth trajectories of graphs. We demonstrate this framework using simulated data and actual video graphs extracted from the Multiview Extended Video with Activities (MEVA) dataset. This framework successfully estimates graphs despite the noise, clutter, and missed detections.
    Free, publicly-accessible full text available November 4, 2023
  3. The paradigm of differentiable programming has significantly enhanced the scope of machine learning via the judicious use of gradient-based optimization. However, standard differentiable programming methods (such as autodiff) typically require that the machine learning models be differentiable, limiting their applicability. Our goal in this paper is to use a new, principled approach to extend gradient-based optimization to functions well modeled by splines, which encompass a large family of piecewise polynomial models. We derive the form of the (weak) Jacobian of such functions and show that it exhibits a block-sparse structure that can be computed implicitly and efficiently. Overall, we show that leveraging this redesigned Jacobian in the form of a differentiable" layer''in predictive models leads to improved performance in diverse applications such as image segmentation, 3D point cloud reconstruction, and finite element analysis. We also open-source the code at\url {https://github. com/idealab-isu/DSA}.
  4. Complex analyses involving multiple, dependent random quantities often lead to graphical models—a set of nodes denoting variables of interest, and corresponding edges denoting statistical interactions between nodes. To develop statistical analyses for graphical data, especially towards generative modeling, one needs mathematical representations and metrics for matching and comparing graphs, and subsequent tools, such as geodesics, means, and covariances. This paper utilizes a quotient structure to develop efficient algorithms for computing these quantities, leading to useful statistical tools, including principal component analysis, statistical testing, and modeling. We demonstrate the efficacy of this framework using datasets taken from several problem areas, including letters, biochemical structures, and social networks.
  5. Abstract Factors thought to influence deep cycle turbulence in the equatorial Pacific are examined statistically for their predictive capacity using a 13-year moored record that includes microstructure measurements of the turbulent kinetic energy dissipation rate. Wind stress and mean current shear are found to be most predictive of the dissipation rate. Those variables, together with the solar buoyancy flux and the diurnal mixed layer thickness, are combined to make a pair of useful parameterizations. The uncertainty in these predictions is typically 50% greater than the uncertainty in present-day in situ measurements. To illustrate the use of these parameterizations, the record of deep cycle turbulence, measured directly since 2005, is extended back to 1990 based on historical mooring data. The extended record is used to refine our understanding of the seasonal variation of deep cycle turbulence.
  6. This paper covered progress on tackling COVID-19 in India, a country with the second highest number of reported infections and fourth highest number of reported deaths in the world.