The paper introduces a novel visual tracking algorithm based on a Convolutional Neural Network (CNN) trained using multi-domain learning. The authors pretrain a CNN on a large set of videos with ground-truth tracking data to obtain generic target representations. The network architecture consists of shared layers and multiple branches of domain-specific layers, where each branch is responsible for binary classification in a specific domain. The network is trained iteratively, separating domain-independent information from domain-specific information. During tracking, a new network is constructed by combining the shared layers with a new binary classification layer, which is updated online. The proposed algorithm demonstrates superior performance compared to state-of-the-art methods in two public benchmarks: Object Tracking Benchmark (OTB) and VOT2014. The main contributions include a multi-domain learning framework that captures shared representations effectively and an online tracking framework that adapts to new domains.The paper introduces a novel visual tracking algorithm based on a Convolutional Neural Network (CNN) trained using multi-domain learning. The authors pretrain a CNN on a large set of videos with ground-truth tracking data to obtain generic target representations. The network architecture consists of shared layers and multiple branches of domain-specific layers, where each branch is responsible for binary classification in a specific domain. The network is trained iteratively, separating domain-independent information from domain-specific information. During tracking, a new network is constructed by combining the shared layers with a new binary classification layer, which is updated online. The proposed algorithm demonstrates superior performance compared to state-of-the-art methods in two public benchmarks: Object Tracking Benchmark (OTB) and VOT2014. The main contributions include a multi-domain learning framework that captures shared representations effectively and an online tracking framework that adapts to new domains.