In this paper we discuss several forms of spatiotemporal convolutions for video analysis and
study their effects on action recognition. Our motivation stems from the observation that 2D …

When a computational task tolerates a relaxation of its specification or when an algorithm
tolerates the effects of noise in its execution, hardware, system software, and programming …

The availability of vast video collections and the accuracy of ML models has generated
significant interest in video analytics systems. Since naively processing all frames using …

Advanced video analytic systems, including scene classification and object detection, have
seen widespread success in various domains such as smart cities and autonomous …

Deep neural networks (DNNs) are key computational building blocks for emerging classes
of web services that interact in real time with users via voice, images and video inputs …

Neural network (NN) accelerators have been integrated into a wide-spectrum of computer
systems to accommodate the rapidly growing demands for artificial intelligence (AI) and …

Approximate computing (AC) is an emerging computing paradigm suitable for intrinsic error-
tolerant applications to reduce energy consumption and execution time. Different …

Cache capacity and memory bandwidth play critical roles in application performance,
particularly for data-intensive applications from domains that include machine learning …

Current multi-/many-core systems spend large amounts of time and power transmitting data
across on-chip interconnects. This problem is aggravated when data-intensive applications …

In imprecision-tolerant applications such as multimedia and signal processing a slightly
degraded output quality is acceptable, which could lead to significant power reduction. We …