Learn More
We propose a multi-expert restoration scheme to address the model drift problem in online tracking. In the proposed scheme, a tracker and its historical snapshots constitute an expert ensemble, where the best expert is selected to restore the current tracker when needed based on a minimum entropy criterion, so as to correct undesirable model updates. The(More)
We propose Hierarchical Space-Time Segments as a new representation for action recognition and localization. This representation has a two level hierarchy. The first level comprises the root space-time segments that may contain a human body. The second level comprises multi-grained space-time segments that contain parts of the root. We present an(More)
Tracking-by-detection is a widely used paradigm for multi-person tracking but is affected by variations in crowd density, obstacles in the scene, varying illumination, human pose variation, scale changes, etc. We propose an improved tracking-by-detection framework for multi-person tracking where the appearance model is formulated as a template ensemble(More)
Input SO AMC HS SIA HC FT Ours GT Figure 1: Sample saliency maps of several state-of-the-art methods (SO [39], AMC [15], HS [34] and SIA [6]) and methods with fast speed (HC [5], FT [1] and ours). Our method runs at about 80 FPS using a single thread, and produces saliency maps of high quality. Previous methods with similar speed, like HC and FT, usually(More)
We aim to model the top-down attention of a Convolutional Neural Network (CNN) classifier for generating task-specific attention maps. Inspired by a top-down human visual attention model, we propose a new backpropagation scheme, called Excitation Backprop, to pass along top-down signals downwards in the network hierarchy via a proba-bilistic Winner-Take-All(More)
To better understand splicing regulation, we used a cell-based screen to identify ten diverse motifs that inhibit splicing from introns. Motifs were validated in another human cell type and gene context, and their presence correlated with in vivo splicing changes. All motifs exhibited exonic splicing enhancer or silencer activity, and grouping these motifs(More)
We introduce a new problem domain for activity recognition: the analysis of children's social and communicative behaviors based on video and audio data. We specifically target interactions between children aged 1–2 years and an adult. Such interactions arise naturally in the diagnosis and treatment of developmental disorders such as autism. We introduce a(More)