Yuanzhe Chen

Finding Coherent Motions and Semantic Regions in Crowd Scenes: A Diffusion and Clustering Approach

This paper addresses the problem of detecting coherent motions in crowd scenes and subsequently constructing semantic regions for activity recognition. We first introduce a coarse-to-fine thermal-diffusion-based approach. It processes input motion fields (e.g., optical flow fields) and produces a coherent motion filed, named as thermal energy field. The thermal energy field is able to capture both motion correlation among particles and the motion trends of individual particles which are helpful to discover coherency among them. We further introduce a two-step clustering process to construct stable semantic regions from the extracted time-varying coherent motions. Finally, these semantic regions are used to recognize activities in crowded scenes. Experiments on various videos demonstrate the effectiveness of our approach.

Visual Analytics in Urban Computing: An Overview

Nowadays, various data collected in urban context provide unprecedented opportunities for building a smarter city through urban computing. However, due to heterogeneity, high complexity and large volumes of these urban data, analyzing them is not an easy task, which often requires integrating human perception in analytical process, triggering a broad use of visualization. In this survey, we first summarize frequently used data types in urban visual analytics, and then elaborate on existing visualization techniques for time, locations and other properties of urban data. Furthermore, we discuss how visualization can be combined with automated analytical approaches. Existing work on urban visual analytics is categorized into two classes based on different outputs of such combinations: 1) For data exploration and pattern interpretation, we describe representative visual analytics tools designed for better insights of different types of urban data. 2) For visual learning, we discuss how visualization can help in three major steps of automated analytical approaches (i.e., cohort construction; feature selection & model construction; result evaluation & tuning) for a more effective machine learning or data mining process, leading to sort of artificial intelligence, such as a classifier, a predictor or a regression model. Finally, we outlook the future of urban visual analytics, and conclude the survey with potential research directions.

PeakVizor: Visual Analytics of Peaks in Video Clickstreams from Massive Open Online Courses.

Massive open online courses (MOOCs) aim to facilitate open-access and massive-participation education. These courses have attracted millions of learners recently. At present, most MOOC platforms record the Web log data of learner interactions with course videos. Such large amounts of multivariate data pose a new challenge in terms of analyzing online learning behaviors. Previous studies have mainly focused on the aggregate behaviors of learners from a summative view; however, few attempts have been made to conduct a detailed analysis of such behaviors. To determine complex learning patterns in MOOC video interactions, this paper introduces a comprehensive visualization system called PeakVizor. This system enables course instructors and education experts to analyze the “peaks” or the video segments that generate numerous clickstreams. The system features three views at different levels: the overview with glyphs to display valuable statistics regarding the peaks detected; the flow view to present spatio-temporal information regarding the peaks; and the correlation view to show the correlation between different learner groups and the peaks. Case studies and interviews conducted with domain experts have demonstrated the usefulness and effectiveness of PeakVizor, and new findings about learning behaviors in MOOC platforms have been reported.

A New Network-Based Algorithm for Human Activity Recognition in Videos

In this paper, a new network-transmission-based (NTB) algorithm is proposed for human activity recognition in videos. The proposed NTB algorithm models the entire scene as an error-free network. In this network, each node corresponds to a patch of the scene and each edge represents the activity correlation between the corresponding patches. Based on this network, we further model people in the scene as packages, while human activities can be modeled as the process of package transmission in the network. By analyzing these specific package transmission processes, various activities can be effectively detected. The implementation of our NTB algorithm into abnormal activity detection and group activity recognition are described in detail in this paper. Experimental results demonstrate the effectiveness of our proposed algorithm.

Intra-and-Inter-Constraint-Based Video Enhancement Based on Piecewise Tone Mapping

Video enhancement plays an important role in various video applications. In this paper, we propose a new intra-and-inter-constraint-based video enhancement approach aiming to: 1) achieve high intraframe quality of the entire picture where multiple regions-of-interest (ROIs) can be adaptively and simultaneously enhanced, and 2) guarantee the interframe quality consistencies among video frames. We first analyze features from different ROIs and create a piecewise tone mapping curve for the entire frame such that the intraframe quality can be enhanced. We further introduce new interframe constraints to improve the temporal quality consistency. Experimental results show that the proposed algorithm obviously outperforms the state-of-the-art algorithms.

DropoutSeer: Visualizing learning patterns in Massive Open Online Courses for dropout reasoning and prediction

Aiming at massive participation and open access education, Massive Open Online Courses (MOOCs) have attracted millions of learners over the past few years. However, the high dropout rate of learners is considered to be one of the most crucial factors that may hinder the development of MOOCs. To tackle this problem, statistical models have been developed to predict dropout behavior based on learner activity logs. Although predictive models can foresee the dropout behavior, it is still difficult for users to understand the reasons behind the predicted results and further design interventions to prevent dropout. In addition, with a better understanding of dropout, researchers in the area of predictive modeling in turn can improve the models. In this paper, we introduce DropoutSeer, a visual analytics system which not only helps instructors and education experts understand the reasons for dropout, but also allows researchers to identify crucial features which can further improve the performance of the models. Both the heterogeneous data extracted from three different kinds of learner activity logs (i.e., clickstream, forum posts and assignment records) and the predicted results are visualized in the proposed system. Case studies and expert interviews have been conducted to demonstrate the usefulness and effectiveness of DropoutSeer.

Improved human head and shoulder detection with local main gradient and tracklets-based feature

In this paper, a new approach is proposed which extracts local main gradients and tracklet-based features for describing human head-and-shoulders. Firstly, local main gradient is extracted for each sliding window such that only gradient features fitting a reasonable orientation are detected as candidate head-and-shoulders. Secondly, given that the shape of head-and-shoulder satisfies a specific curve, we model head-and-shoulder shapes as the combination of short trajectories (tracklets) and utilize the statistics of tracklets to describe head-and-shoulder shapes. Experiments show that by the introduction of our new features, we can achieve better detection results than existing head-and-shoulder detection methods.

A new package-group-transmission-based algorithm for human activity recognition in videos

In this paper, a new package-group-transmission-based algorithm is proposed for human activity recognition in videos. The proposed algorithm first models the entire scene as a network where each node in the network corresponds to a segmentation of the scene. Based on this network, we further model people in the scene as groups of packages. Thus, various human activities can be modeled as the process of “package group transmission” in the network and these activities can be efficiently recognized by suitably analyzing the “package transmission” process. Our proposed algorithm can not only detect activities under the challenging multiple camera scenario, but also be able to recognize various complex group activities among people. Experimental results demonstrate the effectiveness of our proposed algorithm.

Sequence Synopsis: Optimize Visual Summary of Temporal Event Data

Event sequences analysis plays an important role in many application domains such as customer behavior analysis, electronic health record analysis and vehicle fault diagnosis. Real-world event sequence data is often noisy and complex with high event cardinality, making it a challenging task to construct concise yet comprehensive overviews for such data. In this paper, we propose a novel visualization technique based on the minimum description length (MDL) principle to construct a coarse-level overview of event sequence data while balancing the information loss in it. The method addresses a fundamental trade-off in visualization design: reducing visual clutter vs. increasing the information content in a visualization. The method enables simultaneous sequence clustering and pattern extraction and is highly tolerant to noises such as missing or additional events in the data. Based on this approach we propose a visual analytics framework with multiple levels-of-detail to facilitate interactive data exploration. We demonstrate the usability and effectiveness of our approach through case studies with two real-world datasets. One dataset showcases a new application domain for event sequence visualization, i.e., fault development path analysis in vehicles for predictive maintenance. We also discuss the strengths and limitations of the proposed method based on user feedback.

A network-based algorithm for recognizing group activities with multiple people and crowded scenes

In this paper, a network-based algorithm is proposed for group activity recognition with multiple people/objects and crowded scenes. This algorithm models the entire scene as an error-free network. With this network, we model objects in the scene as packages while activities as package transmission in the network. By analyzing these “package transmission” processes, activities can be detected. Based on the proposed network-based algorithm, we also propose two implementations to deal with the scenarios of group activities with multiple people/objects and crowded scenes. Experimental results demonstrate the effectiveness of our proposed algorithm.