640 research outputs found
Special issue on 3-D image analysis and modeling.
No full textIn the recent days, Three-dimensional (3-D) images are widely used for a lot of applications, and recent advances in computer performances have extremely extended the range of applicability. This vitality is witnessed by the increasing number of papers presented in past conferences and by the number of research projects related to 3-D images. Three- dimensional data are inherently more informative, in geomet- rical terms, than simply optical data, but also pose difficult problems that should be faced to obtain a reliable processing framework. Range resolution, type of noise, surface material are all aspects that should be considered in relationship with the sensing device and the application domain
3-D image analysis and modeling - Editorial
No full textEditorial on the special issue on 3D image analysis and modellin
Multi-view Common Space Learning for Emotion Recognition in the Wild
No full textIt is a very challenging task to recognize emotion in the wild. Recently, combining information from various views or modalities has attracted more attention. Cross modality features and features extracted by different methods are regarded as multi-view information of the sample. In this paper, we propose a method to analyse multi-view features of emotion samples and automatically recognize the expression as part of the fourth Emotion Recognition in the Wild Challenge (EmotiW 2016). In our method, we first extract multi-view features such as BoF, CNN, LBP-TOP and audio features for each expression sample. Then we learn the corresponding projection matrices to map multi-view features into a common subspace. In the meantime, we impose l(2,1)-norm penalties on projection matrices for feature selection. We apply both this method and PLSR to emotion recognition. We conduct experiments on both AFEW and HAPPEI datasets, and achieve superior performance. The best recognition accuracy of our method is 55.31% on the AFEW dataset for video based emotion recognition in the wild. The minimum RMSE for group happiness intensity recognition is 0.9525 on HAPPEI dataset. Both of them are much better than that of the challenge baseline.CPCI-S(ISTP)[email protected]; [email protected]; [email protected]
A structural analysis of neighborhood and school effects on immigrant children's academic performance:
No full textImmigrant children are influenced by a variety of contexts, including their family, peer groups, neighborhood, and institutions such as school and the workplace. To gauge how immigrant children fare in education, it is extremely important to understand whether, and how, these contexts affect their academic performance. This dissertation’s theoretical framework is heavily grounded in theories dealing with the impact of neighborhood and school on children’s academic performance. Analyzing nationally representative data from The National Longitudinal Study of Adolescent Health (Add Health), this study investigates whether, and how, two of these contexts--neighborhood and school characteristics--influence non-Hispanic White, non-Hispanic Black, Hispanic, and Asian immigrant students’ academic performance. Comparison analysis, hierarchical linear modeling, and fixed-effect modeling are used to test six hypotheses. The comparison analysis found that, generally speaking, neighborhood and school conditions are better for non-immigrant than for immigrant students. Specifically, neighborhood and school conditions are better for Asian immigrants than for Hispanic immigrants, and significantly better for immigrant non-Hispanic Whites than for immigrant non-Hispanic Blacks. Multilevel regression analysis found that both neighborhood and school characteristics affect immigrant students’ GPA, while neighborhood-school involvement characteristics do not (neither do they affect non-immigrant students’ GPA). Neighborhood SES and neighborhood immigrant composition affect immigrant students’ GPA. Furthermore, the results show that school socioeconomic status (SES), school climate, and school location affect immigrant students’ GPA. Large class size and school type are associated with non-immigrant students’ GPA. The results of the study imply that both neighborhood and school characteristics influence academic performance of immigrant students more than that of non-immigrant students. Compared to the neighborhood, the school, as an institutional resource, plays a crucial role in immigrant students’ academic performance and their assimilation processes.Ph.D.Includes bibliographical references (p. 154-168)by Peijia Zha, M.A
Anomaly Detection via Local Coordinate Factorization and Spatio-Temporal Pyramid
No full textAnomaly detection, which aims to discover anomalous events, defined as having a low likelihood of occurrence, from surveillance videos, has attracted increasing interest and is still a challenge in computer vision community. In this paper, we propose an efficient anomaly detection approach which can perform both real-time and multi-scale detection. Our approach can handle the change of background. Specifically, Local Coordinate Factorization is utilized to tell whether a spatio-temporal video volume (STV) belongs to an anomaly, which can effectively detect spatial, temporal and spatio-temporal anomalies. And we employ Spatio-temporal Pyramid (STP) to capture the spatial and temporal continuity of an anomalous event, enabling our approach to handle multi-scale and complicated events. We also propose an online method to update the local coordinates, which makes our approach self-adaptive to background change which typically occurs in real-world setting. We conduct extensive experiments on several publicly available datasets for anomaly detection, and the results showthat our approach can outperform state-of-the-art approaches, which verifies the effectiveness of our approach.EICPCI-S(ISTP)[email protected]; [email protected]; [email protected]; [email protected]
A Study of the Protagonist in Ne Zha: I Am The Destiny from the Perspective of Karen Horney’s Psychoanalysis
No full textNe Zha: I Am The Destiny is an animated movie with excellent public reputation in china and international market. Setting in traditional Chinese mythology, the leading character, Ne Zha, undergoes a life full of twists and turns. The author analyzes the movie under the guide of the representative of new Freudian, Karen Horney. In the light of Karen Horney’s theory, Ne Zha bears the tendency of neurotic personality from the phenomenon of moving toward people, moving against people and moving away from people. However Ne Zha ultimately achieve self-actualization and transcendence through the appeal of mastery, the appeal of love as well as the appeal of freedom. The movie exerts far-reaching and profound significance to the people in the present world.
Multiple Models Fusion for Emotion Recognition in the Wild
No full textEmotion recognition in the wild is a very challenging task. In this paper, we propose a multiple models fusion method to automatically recognize the expression in the video clip as part of the third Emotion Recognition in the Wild Challenge (EmotiW2015). In our method, we first extract dense SIFT, LBP-TOP and audio features from each video clip. For dense SIFT features, we use the bag of features (BoF) model with two different encoding methods (locality-constrained linear coding and group saliency based coding) to further represent it. During the classification process, we use partial least square regression to calculate the regression value of each model. By learning the optimal weight of each model based on the regression value, we fuse these models together. We conduct experiments on the given validation and test datasets, and achieve superior performance. The best recognition accuracy of our fusion method is 52:50% on the test dataset, which is 13:17% higher than the challenge baseline accuracy of 39:33%.EICPCI-S(ISTP)[email protected]; [email protected]; [email protected]
Also By The Same Author: AKTiveAuthor, a Citation Graph Approach to Name Disambiguation
No full textThe desire for definitive data and the semantic web drive for inference over heterogeneous data sources requires co-reference resolution to be performed on those data. In particular, name disambiguation is required to allow accurate publication lists, citation counts and impact measures to be determined. This paper describes a graph-based approach to author disambiguation on large-scale citation networks. Using self-citation, co-authorship and document source analyses, AKTiveAuthor clusters papers, achieving precision of 0.997 and recall of 0.818 over a test group of eight surname clusters
Learning to Detect Anomalies in Surveillance Video
No full textDetecting anomalies in surveillance videos, that is, finding events or objects with low probability of occurrence, is a practical and challenging research topic in computer vision community. In this paper, we put forward a novel unsupervised learning framework for anomaly detection. At feature level, we propose a Sparse Semi-nonnegative Matrix Factorization (SSMF) to learn local patterns at each pixel, and a Histogram of Nonnegative Coefficients (HNC) can be constructed as local feature which is more expressive than previously used features like Histogram of Oriented Gradients (HOG). At model level, we learn a probability model which takes the spatial and temporal contextual information into consideration. Our framework is totally unsupervised requiring no human-labeled training data. With more expressive features and more complicated model, our framework can accurately detect and localize anomalies in surveillance video. We carried out extensive experiments on several benchmark video datasets for anomaly detection, and the results demonstrate the superiority of our framework to state-of-the-art approaches, validating the effectiveness of our framework.National Key Basic Research Project of China (973Program) [2011CB302400]; National Nature Science Foundation of China under NSFC [61071156, 61131003]SCI(E)[email protected]; [email protected]; [email protected]
- …
