465 papers with code • 33 benchmarks • 55 datasets
Person Re-Identification is a computer vision task in which the goal is to match a person's identity across different cameras or locations in a video or image sequence. It involves detecting and tracking a person and then using features such as appearance, body shape, and clothing to match their identity in different frames. The goal is to associate the same person across multiple non-overlapping camera views in a robust and efficient manner.
In this paper we describe a new mobile architecture, MobileNetV2, that improves the state of the art performance of mobile models on multiple tasks and benchmarks as well as across a spectrum of different model sizes.
Simple Online and Realtime Tracking (SORT) is a pragmatic approach to multiple object tracking with a focus on simple, effective algorithms.
By exploiting metric space distances, our network is able to learn local features with increasing contextual scales.
Our approach is directly inspired by the theory on domain adaptation suggesting that, for effective domain transfer to be achieved, predictions must be made based on features that cannot discriminate between the training (source) and test (target) domains.
We introduce an extremely computation-efficient CNN architecture named ShuffleNet, which is designed specially for mobile devices with very limited computing power (e. g., 10-150 MFLOPs).
In the past few years, the field of computer vision has gone through a revolution fueled mainly by the advent of large datasets and the adoption of deep convolutional neural networks for end-to-end learning.