Learn More
Recent approaches in depth-based human activity analysis achieved outstanding performance and proved the effectiveness of 3D representation for classification of action classes. Currently available depth-based and RGB+Dbased action recognition benchmarks have a number of limitations, including the lack of training samples, distinct class labels, camera(More)
Matching pedestrians across multiple camera views, known as human re-identification, is a challenging research problem that has numerous applications in visual surveillance. With the resurgence of Con-volutional Neural Networks (CNNs), several end-to-end deep Siamese CNN architectures have been proposed for human re-identification with the objective of(More)
The explosion of the Internet provides us with a tremendous resource of images shared online. It also confronts vision researchers the problem of finding effective methods to navigate the vast amount of visual information. Semantic image understanding plays a vital role towards solving this problem. One important task in image understanding is object(More)
3D action recognition – analysis of human actions based on 3D skeleton data – becomes popular recently due to its succinctness, robustness, and view-invariant representation. Recent attempts on this problem suggested to develop RNN-based learning methods to model the contextual dependency in the temporal domain. In this paper, we extend this idea to(More)
In this paper, we present a home-monitoring oriented human activity recognition benchmark database, based on the combination of a color video camera and a depth sensor. Our contributions are two-fold: 1) We have created a publicly releasable human activity video database (i.e., named as RGBD-HuDaAct), which contains synchronized color-depth video streams,(More)
Behavioral Targeting (BT) is a technique used by online advertisers to increase the effectiveness of their campaigns, and is playing an increasingly important role in the online advertising market. However, it is underexplored in academia when looking at how much BT can truly help online advertising in commercial search engines. To answer this question, in(More)
Matching pedestrians across multiple camera views known as human re-identification (re-identification) is a challenging problem in visual surveillance. In the existing works concentrating on feature extraction , representations are formed locally and independent of other regions. We present a novel siamese Long Short-Term Memory (LSTM) architecture that can(More)
Moroberekan, a japonica rice cultivar with durable resistance to blast disease in Asia, was crossed to the highly susceptible indica cultivar, CO39, and 281 F7 recombinant inbred (RI) lines were produced by single seed descent. The population was evaluated for blast resistance in the greenhouse and the field, and was analyzed with 127 restriction fragment(More)
We consider the problem of target localization by a network of passive sensors. When an unknown target emits an acoustic or a radio signal, its position can be localized with multiple sensors using the time difference of arrival (TDOA) information. In this paper, we consider the maximum likelihood formulation of this target localization problem and provide(More)
The induction of pluripotency or trans-differentiation of one cell type to another can be accomplished with cell-lineage-specific transcription factors. Here, we report that repression of a single RNA binding polypyrimidine-tract-binding (PTB) protein, which occurs during normal brain development via the action of miR-124, is sufficient to induce(More)