Abstract Online tracking is complex and users find it challenging to protect themselves from it. While the academic community has extensively studied systems for practices, link between data protection regulations, websites’ practices of presenting privacy-enhancing technologies (PETs), how learn about PETs practice them not clear. This paper takes a multidimensional approach such link. We cond...

Sports competition is one of the most popular programs for many audiences. Tracking players in sports game videos from broadcasts a nontrivial challenge computer vision researchers. In videos, direction an athlete’s movement changes quickly and unpredictably. Mutual occlusion between athletes also more frequent team competitions. However, rich temporal contexts among adjacent frames have been e...

We introduce an online learning approach to produce discriminative part-based appearance models (DPAMs) for tracking multiple humans in real scenes by incorporating association based and category free tracking methods. Detection responses are gradually associated into tracklets in multiple levels to produce final tracks. Unlike most previous multi-target tracking approaches which do not explici...

This paper describes a new online convex optimization method which incorporates a family of candidate dynamical models and establishes novel tracking regret bounds that scale with the comparator’s deviation from the best dynamical model in this family. Previous online optimization methods are designed to have a total accumulated loss comparable to that of the best comparator sequence, and exist...

We propose an online visual tracking algorithm by learning discriminative saliency map using Convolutional Neural Network (CNN). Given a CNN pre-trained on a large-scale image repository in offline, our algorithm takes outputs from hidden layers of the network as feature descriptors since they show excellent representation performance in various general visual recognition problems. The features...