Conventional neural networks have been demonstrated to be a powerful framework for
background subtraction in video acquired by static cameras. Indeed, the well-known Self …

To reduce the significant redundancy in deep Convolutional Neural Networks (CNNs), most
existing methods prune neurons by only considering the statistics of an individual layer or …

We introduce a generic framework that reduces the computational cost of object detection
while retaining accuracy for scenarios where objects with varied sizes appear in high …

Target detection is one of the most important research directions in computer vision.
Recently, a variety of target detection algorithms have been proposed. Since the targets …

Target detection based on deep learning is develo** rapidly. However, small target
detection is still a challenge. In this paper, a simple and efficient network for small target …

This paper provides a method to understand the underlying semantics of Bharatnatyam
dance motion and classifies it. Each dance performance is audio-driven and spans over …

We tackle the challenge of understanding voice queries posed against the Comcast Xfinity
X1 entertainment platform, where consumers direct speech input at their" voice remotes" …

Global warming is predicted to profoundly impact ocean ecosystems. Fish behavior is an
important indicator of changes in such marine environments. Thus, the automatic …

Although in recent years there has been a trend to incorporate data-driven models to
automate the task of video surveillance, there remains a shortage of learning-based …

US11295140B2 - Methods and systems for determining object activity within a region of interest
- Google Patents US11295140B2 - Methods and systems for determining object activity within …