Výsledky vyhledávání

Report

Tracking by Animation: Unsupervised Learning of Multi-Object Attentive Trackers

Autor: He, Zhen, Li, Jian, Liu, Daxue, He, Hangen, Barber, David

Online Multi-Object Tracking (MOT) from videos is a challenging computer vision task which has been extensively studied for decades. Most of the existing MOT algorithms are based on the Tracking-by-Detection (TBD) paradigm combined with popular machi

Externí odkaz: http://arxiv.org/abs/1809.03137

Zobrazit plný text záznamu

Report

Wider and Deeper, Cheaper and Faster: Tensorized LSTMs for Sequence Learning

Autor: He, Zhen, Gao, Shaobing, Xiao, Liang, Liu, Daxue, He, Hangen, Barber, David

Long Short-Term Memory (LSTM) is a popular approach to boosting the ability of Recurrent Neural Networks to store longer term temporal information. The capacity of an LSTM network can be increased by widening and adding layers. However, usually the f

Externí odkaz: http://arxiv.org/abs/1711.01577

Zobrazit plný text záznamu

Report

Light Cascaded Convolutional Neural Networks for Accurate Player Detection

Autor: Lu, Keyu, Chen, Jianhui, Little, James J., He, Hangen

Vision based player detection is important in sports applications. Accuracy, efficiency, and low memory consumption are desirable for real-time tasks such as intelligent broadcasting and automatic event classification. In this paper, we present a cas

Externí odkaz: http://arxiv.org/abs/1709.10230

Zobrazit plný text záznamu

Report

Generalized Haar Filter based Deep Networks for Real-Time Object Detection in Traffic Scene

Autor: Lu, Keyu, Li, Jian, An, Xiangjing, He, Hangen

Vision-based object detection is one of the fundamental functions in numerous traffic scene applications such as self-driving vehicle systems and advance driver assistance systems (ADAS). However, it is also a challenging task due to the diversity of

Externí odkaz: http://arxiv.org/abs/1610.09609

Zobrazit plný text záznamu

Report

Visual Saliency Based on Scale-Space Analysis in the Frequency Domain

Autor: Li, Jian, Levine, Martin, An, Xiangjing, Xu, Xin, He, Hangen

Publikováno v: Pattern Analysis and Machine Intelligence, IEEE Transactions on 35.4 (2013): 996-1010

We address the issue of visual saliency from three perspectives. First, we consider saliency detection as a frequency domain analysis problem. Second, we achieve this by employing the concept of {\it non-saliency}. Third, we simultaneously consider t

Externí odkaz: http://arxiv.org/abs/1605.01999

Zobrazit plný text záznamu