arXiv subjects

Mingliang Xu

Publications and source records attributed to Mingliang Xu.

97 records · Page 6Linked to original sources

arXiv2018

Efficiently Disassemble-and-Pack for Mechanism

In this paper, we present a disassemble-and-pack approach for a mechanism to seek a box which contains total mechanical parts with high space utilization. Its key feature is that mechanism contains not only geometric shapes but also internal motion structures which can be calculated to adjust geometric shapes of the mechanical parts. Our system consists of two steps: disassemble mechanical object into a group set and pack them within a box efficiently. The first step is to create a hierarchy of possible group set of parts which is generated by disconnecting the selected joints and adjust motion structures of parts in groups. The aim of this step is seeking total minimum volume of each group. The second step is to exploit the hierarchy based on breadth-first-search to obtain a group set. Every group in the set is inserted into specified box from maximum volume to minimum based on our packing strategy. Until an approximated result with satisfied efficiency is accepted, our approach finish exploiting the hierarchy.

cs.CG↗

arXiv2017

Learning Correspondence Structures for Person Re-identification

This paper addresses the problem of handling spatial misalignments due to camera-view changes or human-pose variations in person re-identification. We first introduce a boosting-based approach to learn a correspondence structure which indicates the patch-wise matching probabilities between images from a target camera pair. The learned correspondence structure can not only capture the spatial correspondence pattern between cameras but also handle the viewpoint or human-pose variation in individual images. We further introduce a global constraint-based matching process. It integrates a global matching constraint over the learned correspondence structure to exclude cross-view misalignments during the image patch matching process, hence achieving a more reliable matching score between images. Finally, we also extend our approach by introducing a multi-structure scheme, which learns a set of local correspondence structures to capture the spatial correspondence sub-patterns between a camera pair, so as to handle the spatial misalignments between individual images in a more precise way. Experimental results on various datasets demonstrate the effectiveness of our approach.

cs.CV↗

arXiv2017

A Tube-and-Droplet-based Approach for Representing and Analyzing Motion Trajectories

Trajectory analysis is essential in many applications. In this paper, we address the problem of representing motion trajectories in a highly informative way, and consequently utilize it for analyzing trajectories. Our approach first leverages the complete information from given trajectories to construct a thermal transfer field which provides a context-rich way to describe the global motion pattern in a scene. Then, a 3D tube is derived which depicts an input trajectory by integrating its surrounding motion patterns contained in the thermal transfer field. The 3D tube effectively: 1) maintains the movement information of a trajectory, 2) embeds the complete contextual motion pattern around a trajectory, 3) visualizes information about a trajectory in a clear and unified way. We further introduce a droplet-based process. It derives a droplet vector from a 3D tube, so as to characterize the high-dimensional 3D tube information in a simple but effective way. Finally, we apply our tube-and-droplet representation to trajectory analysis applications including trajectory clustering, trajectory classification & abnormality detection, and 3D action recognition. Experimental comparisons with state-of-the-art algorithms demonstrate the effectiveness of our approach.

cs.CV↗

arXiv2016

Representation Learning with Deconvolution for Multivariate Time Series Classification and Visualization

We propose a new model based on the deconvolutional networks and SAX discretization to learn the representation for multivariate time series. Deconvolutional networks fully exploit the advantage the powerful expressiveness of deep neural networks in the manner of unsupervised learning. We design a network structure specifically to capture the cross-channel correlation with deconvolution, forcing the pooling operation to perform the dimension reduction along each position in the individual channel. Discretization based on Symbolic Aggregate Approximation is applied on the feature vectors to further extract the bag of features. We show how this representation and bag of features helps on classification. A full comparison with the sequence distance based approach is provided to demonstrate the effectiveness of our approach on the standard datasets. We further build the Markov matrix from the discretized representation from the deconvolution to visualize the time series as complex networks, which show more class-specific statistical properties and clear structures with respect to different labels.

cs.LG↗

arXiv2015

Tree-based Visualization and Optimization for Image Collection

The visualization of an image collection is the process of displaying a collection of images on a screen under some specific layout requirements. This paper focuses on an important problem that is not well addressed by the previous methods: visualizing image collections into arbitrary layout shapes while arranging images according to user-defined semantic or visual correlations (e.g., color or object category). To this end, we first propose a property-based tree construction scheme to organize images of a collection into a tree structure according to user-defined properties. In this way, images can be adaptively placed with the desired semantic or visual correlations in the final visualization layout. Then, we design a two-step visualization optimization scheme to further optimize image layouts. As a result, multiple layout effects including layout shape and image overlap ratio can be effectively controlled to guarantee a satisfactory visualization. Finally, we also propose a tree-transfer scheme such that visualization layouts can be adaptively changed when users select different "images of interest". We demonstrate the effectiveness of our proposed approach through the comparisons with state-of-the-art visualization techniques.

cs.MM↗

arXiv2015

Person Re-identification with Correspondence Structure Learning

This paper addresses the problem of handling spatial misalignments due to camera-view changes or human-pose variations in person re-identification. We first introduce a boosting-based approach to learn a correspondence structure which indicates the patch-wise matching probabilities between images from a target camera pair. The learned correspondence structure can not only capture the spatial correspondence pattern between cameras but also handle the viewpoint or human-pose variation in individual images. We further introduce a global-based matching process. It integrates a global matching constraint over the learned correspondence structure to exclude cross-view misalignments during the image patch matching process, hence achieving a more reliable matching score between images. Experimental results on various datasets demonstrate the effectiveness of our approach.

cs.CV↗

arXiv2014

Keeping speed and distance for aligned motion

The cohesive collective motion (flocking, swarming) of autonomous agents is ubiquitously observed and exploited in both natural and man-made settings, thus, minimal models for its description are essential. In a model with continuous space and time we find that if two particles arrive symmetrically in a plane at a large angle, then (i) radial repulsion and (ii) linear self-propelling toward a fixed preferred speed are sufficient for them to depart at a smaller angle. For this local gain of momentum explicit velocity alignment is not necessary, nor are adhesion/attraction, inelasticity or anisotropy of the particles, or nonlinear drag. With many particles obeying these microscopic rules of motion we find that their spatial confinement to a square with periodic boundaries (which is an indirect form of attraction) leads to stable macroscopic ordering. After varying the density of particles at constant system size and varying the size of the system with constant particle density we predict that in the infinite system size (or density) limit the hysteresis loop disappears and the transition becomes continuous. We note that animals, humans, drones, etc. tend to move asynchronously and are often more responsive to motion than positions. Thus, for them velocity-based continuous models can provide higher precision than coordinate-based models. An additional characteristic and realistic feature of the model is that convergence to the ordered state is fastest at a finite density, which is in contrast to models applying (discontinuous) explicit velocity alignments and discretized time. In summary, we find that the investigated model can provide a minimal description of flocking.

cond-mat.stat-mech↗