Video object detection is a fundamental technology of intelligent video analytics for Internet
of Things (IoT) applications. However, even with extraordinary detection accuracy …

Real-time on-device object detection for video analytics fails to meet the accuracy
requirement due to limited resources of mobile devices while offloading object detection …

Emerging Internet of Things (IoT) and mobile computing applications are expected to
support latency-sensitive deep neural network (DNN) workloads. To realize this vision, the …

To deal with the challenges in video object detection (VOD), such as occlusion and motion
blur, many state-of-the-art video object detectors adopt a feature aggregation module to …

This paper presents the novel idea of generating object proposals by leveraging temporal
information for video object detection. The feature aggregation in modern region-based …

The deep learning technique has recently led to significant improvement in object detection
accuracy. In many applications, object detection is performed on video data consisting of a …

Deep Neural Network (DNN) trained object detec-tors are widely deployed in many mission-
critical systems for real time video analytics at the edge, such as autonomous driving, video …

Recent advances in computer vision and neural networks have made it possible for more
surveillance videos to be automatically searched and analyzed by algorithms rather than …

Adaptive and efficient computer vision systems have been proposed to make computer
vision tasks, eg, object classification and object detection, optimized for embedded boards …

While recent advances in deep neural networks (DNNs) enabled remarkable performance
on various computer vision tasks, it is challenging for edge devices to perform real-time …