Jianhua Zou

Zhihao Shen, Wan Du, Xi Zhao et al.

Retrieving similar trajectories from a large trajectory dataset is important for a variety of applications, like transportation planning and mobility analysis. Unlike previous works based on fine-grained GPS trajectories, this paper investigates the feasibility of identifying similar trajectories from cellular data observed by mobile infrastructure, which provide more comprehensive coverage. To handle the large localization errors and low sample rates of cellular data, we develop a holistic system, cellSim, which seamlessly integrates map matching and similar trajectory search. A set of map matching techniques are proposed to transform cell tower sequences into moving trajectories on a road map by considering the unique features of cellular data, like the dynamic density of cell towers and bidirectional roads. To further improve the accuracy of similarity search, map matching outputs M trajectory candidates of different confidence, and a new similarity measure scheme is developed to process the map matching results. Meanwhile, M is dynamically adapted to maintain a low false positive rate of the similarity search, and two pruning schemes are proposed to minimize the computation overhead. Extensive experiments on a large-scale dataset and real-world trajectories of 1701 km reveal that cellSim provides high accuracy (precision 62.4% and recall of 89.8%).

Xiangyu Zhang, Jianhua Zou, Kaiming He et al.

This paper aims to accelerate the test-time computation of convolutional neural networks (CNNs), especially very deep CNNs that have substantially impacted the computer vision community. Unlike previous methods that are designed for approximating linear filters or linear responses, our method takes the nonlinear units into account. We develop an effective solution to the resulting nonlinear optimization problem without the need of stochastic gradient descent (SGD). More importantly, while previous methods mainly focus on optimizing one or two layers, our nonlinear method enables an asymmetric reconstruction that reduces the rapidly accumulated error when multiple (e.g., >=10) layers are approximated. For the widely used very deep VGG-16 model, our method achieves a whole-model speedup of 4x with merely a 0.3% increase of top-5 error in ImageNet classification. Our 4x accelerated VGG-16 model also shows a graceful accuracy degradation for object detection when plugged into the Fast R-CNN detector.

Xiangyu Zhang, Jianhua Zou, Xiang Ming et al.

This paper aims to accelerate the test-time computation of deep convolutional neural networks (CNNs). Unlike existing methods that are designed for approximating linear filters or linear responses, our method takes the nonlinear units into account. We minimize the reconstruction error of the nonlinear responses, subject to a low-rank constraint which helps to reduce the complexity of filters. We develop an effective solution to this constrained nonlinear optimization problem. An algorithm is also presented for reducing the accumulated error when multiple layers are approximated. A whole-model speedup ratio of 4x is demonstrated on a large network trained for ImageNet, while the top-5 error rate is only increased by 0.9%. Our accelerated model has a comparably fast speed as the "AlexNet", but is 4.7% more accurate.