Snehesh Shrestha

University of Maryland, College Park | UMD, UMCP, University of Maryland College Park · Department of Computer Science

Musicians delicately control their bodies to generate music. Sometimes, their motions are too subtle to be captured by the human eye. To analyze how they move to produce the music, we need to estimate precise 4D human pose (3D pose over time). However, current state-of-the-art (SoTA) visual pose estimation algorithms struggle to produce accurate mo...

Many of us researchers take extra measures to control for known-unknowns. However, unknown-unknowns can, at best, be negligible, but otherwise, they could produce unreliable data that might have dire consequences in real-life downstream applications. Human-Robot Interaction standards informed by empirical data could save us time and effort and prov...

Haptic sensing can provide a new dimension to enhance people's musical and cinematic experiences. However, designing a haptic pattern is neither intuitive nor trivial. Imagined haptic patterns tend to be different from experienced ones. As a result, researchers use simple step-curve patterns to create haptic stimuli. To this end, we designed and de...

The interactive augmentation of musical instruments to foster self-expressiveness and learning has a rich history. Over the past decades, the incorporation of interactive technologies into musical instruments emerged into a new research field requiring strong collaboration between different disciplines. The workshop "Intelligent Music Interfaces" c...

Video Annotation is a crucial process in computer science and social science alike. Many video annotation tools (VAT) offer a wide range of features for making annotation possible. We conducted an extensive survey of over 59 VAT and interviewed interdisciplinary researchers to evaluate the usability of the VAT. Our findings suggest that most curren...

Echo State Networks (ESN) are a class of recurrent neural networks that can learn to regress on or classify sequential data by keeping the recurrent component random and training only on a set of readout weights, which is of interest to the current edge computing and neuromorphic community. However, they have struggled to perform well with regressi...

Pose Estimation techniques rely on visual cues available through observations represented in the form of pixels. But the performance is bounded by the frame rate of the video and struggles from motion blur, occlusions, and temporal coherence. This issue is magnified when people are interacting with objects and instruments, for example playing the v...

Significance People are constantly exposed to threatening language in mass communication channels, yet we lack tools to identify language about threats and track its impact on human groups. We developed a threat dictionary, a computationally derived linguistic tool that indexes threat levels from texts with high temporal resolution, across media pl...

In many real-world applications, fully-differentiable RNNs such as LSTMs and GRUs have been widely deployed to solve time series learning tasks. These networks train via Backpropagation Through Time, which can work well in practice but involves a biologically unrealistic unrolling of the network in time for gradient updates, are computationally exp...