We demonstrate four novel multimodal methods for efficient video summarization and comprehensive cross-cultural news video understanding. First, For video quick browsing, we demonstrate a multimedia event recounting system. Based on nine people-oriented design principles, it summarizes YouTube-like videos into short visual segments (812sec) and textual words (less than 10 terms). In the 2013 Trecvid Multimedia Event Recounting competition, this system placed first in recognition time efficiency, while remaining above average in description accuracy. Secondly, we demonstrate the summarization of large amounts of online international news videos. In order to understand an international event such as Ebola virus, AirAsia Flight 8501 and Zika virus comprehensively, we present a novel and efficient constrained tensor factorization algorithm that first represents a video archive of multimedia news stories concerning a news event as a sparse tensor of order 4. The dimensions correspond to extracted visual memes, verbal tags, time periods, and cultures. The iterative algorithm approximately but accurately extracts coherent quad-clusters, each of which represents a significant summary of an important independent aspect of the news event. We give examples of quad-clusters extracted from tensors with at least 108 entries derived from international news coverage. We show the method is fast, can be tuned to give preferences to any subset of its four dimensions, and exceeds three existing methods in performance. Thirdly, noting that the co-occurrence of visual memes and tags in our summarization result is sparse, we show how to model cross-cultural visual meme influence based on normalized PageRank, which more accurately captures the rates at which visual memes are reposted in a specified time period in a specified culture. Lastly, we establish the correspondences of videos and text descriptions in different cultures by reliable visual cues, detect culture-specific tags for visual memes and then annotate videos in a cultural settings. Starting with any video with less text or no text in one culture (say, US), we select candidate annotations in the text of another culture (say, China) to annotate US video. Through analyzing the similarity of images annotated by those candidates, we can derive a set of proper tags from the viewpoints of another culture (China). We illustrate cultural-based annotation examples by segments of international news. We evaluate the generated tags by cross-cultural tag frequency, tag precision, and user studies.

Thesis (Ph. D.)--University of Missouri-Columbia, 2001. / Typescript. Vita. Includes bibliographical references (leaves 238-247). Also available on the Internet.

Thesis (Ph. D.)--University of Missouri-Columbia, 2001. / Typescript. Vita. Includes bibliographical references (leaves 238-247). Also available on the Internet.

Thesis (M,A.)--University of Missouri-Columbia, 2007. / The entire dissertation/thesis text is included in the research.pdf file; the official abstract appears in the short.pdf file (which also appears in the research.pdf); a non-technical general description, or public abstract, appears in the public.pdf file. Title from title screen of research.pdf file (viewed on November 12, 2007) Includes bibliographical references.

Thesis (Ph. D.)--University of Missouri-Columbia, 2008. / The entire dissertation/thesis text is included in the research.pdf file; the official abstract appears in the short.pdf file (which also appears in the research.pdf); a non-technical general description, or public abstract, appears in the public.pdf file. Title from title screen of research.pdf file (viewed on June 11, 2009) Vita. Includes bibliographical references.

Thesis (Ph. D.)--University of Missouri-Columbia, 2002. / Typescript. Vita. Includes bibliographical references (leaves 228-237). Also available on the Internet.

Thesis (Ph. D.)--University of Missouri-Columbia, 2002. / Typescript. Vita. Includes bibliographical references (leaves 228-237). Also available on the Internet.

Thesis (M.A.)--Georgia State University, 2005. / Title from title screen. Merrill Morris, committee chair; Marian Meyers, Douglas Barthlow, committee members. Electronic text (98 p.) : digital, PDF file. Description based on contents viewed June 21, 2007. Includes bibliographical references (p. 89-96).

Este trabalho investiga a atuação do repórter de TV, profissional que, apesar de ser o principal narrador das histórias retratadas na televisão, se encontra à margem das pesquisas em telejornalismo. O objetivo foi mapear um estilo do repórter sob uma perspectiva histórica, buscando identificar diferenças e permanências nos elementos visuais da passagem, termo que no jargão jornalístico se refere ao momento em que o repórter aparece na reportagem. Como referencial teórico, utiliza-se o conceito de habitus de Bourdieu (2011), estudos de performance e dramaturgia de Goffman (1985), Coutinho (2012) e Gutmann (2012), entre outros autores, como Vizeu (2005), Benjamin (1996), Abreu e Lima (2010) e Mota (2001). Foram analisadas 72 reportagens das primeiras décadas do telejornalismo brasileiro e 73 reportagens contemporâneas, totalizando 145 passagens. Os resultados apontam um aumento no uso de movimentos de câmera, assim como o repórter também está se movimentando mais durante a passagem. O enquadramento mais utilizado é o plano americano, mas o plano geral, em que o repórter aparece de corpo inteiro, se tornou mais usual. O tempo médio da passagem aumentou, a formalidade do figurino está sendo deixada de lado e o grafismo surge como elemento visual auxiliar do repórter. O trabalho ainda reafirma a importância do papel do repórter de TV, figura que conduz a narrativa, confere credibilidade ao relato e estabelece um elo com a audiência. / This paper investigates the performance of the TV reporter, a professional that, despite being the main narrator of the stories on television, is excluded of researches in television journalism. The goal was to map a reporter style from a historical perspective in order to identify differences and continuities in the visual elements of the piece to camera, a term that in the journalistic jargon refers to the moment the reporter appears on TV. As a theoretical framework, we use the concept of habitus of Bourdieu (2011), performance and dramaturgy studies of Goffman (1985), Coutinho (2012) and Gutmann (2012), among others, as Vizeu (2005), Benjamin (1996), Abreu e Lima (2010) and Mota (2001). For this study, we analyzed 73 reports from the first decades of Brazilian television and 72 current reports, totalizing 145 pieces to camera. The results show an increase in the use of camera movements, and the reporter is also moving more during the piece to camera. The most widely used framework is the medium shot, but the wide shot, in which the reporter appears full body, became more common. The average time the reporter is displayed on the vídeo increased, the formality of clothing is being left aside and the graphics appears as a visual element helping the reporter. The study also reaffirms the importance of the TV reporter, that leads the narrative, gives credibility to the report and establishes a link with the audience.

Este trabalho investiga a atuação do repórter de TV, profissional que, apesar de ser o principal narrador das histórias retratadas na televisão, se encontra à margem das pesquisas em telejornalismo. O objetivo foi mapear um estilo do repórter sob uma perspectiva histórica, buscando identificar diferenças e permanências nos elementos visuais da passagem, termo que no jargão jornalístico se refere ao momento em que o repórter aparece na reportagem. Como referencial teórico, utiliza-se o conceito de habitus de Bourdieu (2011), estudos de performance e dramaturgia de Goffman (1985), Coutinho (2012) e Gutmann (2012), entre outros autores, como Vizeu (2005), Benjamin (1996), Abreu e Lima (2010) e Mota (2001). Foram analisadas 72 reportagens das primeiras décadas do telejornalismo brasileiro e 73 reportagens contemporâneas, totalizando 145 passagens. Os resultados apontam um aumento no uso de movimentos de câmera, assim como o repórter também está se movimentando mais durante a passagem. O enquadramento mais utilizado é o plano americano, mas o plano geral, em que o repórter aparece de corpo inteiro, se tornou mais usual. O tempo médio da passagem aumentou, a formalidade do figurino está sendo deixada de lado e o grafismo surge como elemento visual auxiliar do repórter. O trabalho ainda reafirma a importância do papel do repórter de TV, figura que conduz a narrativa, confere credibilidade ao relato e estabelece um elo com a audiência. / This paper investigates the performance of the TV reporter, a professional that, despite being the main narrator of the stories on television, is excluded of researches in television journalism. The goal was to map a reporter style from a historical perspective in order to identify differences and continuities in the visual elements of the piece to camera, a term that in the journalistic jargon refers to the moment the reporter appears on TV. As a theoretical framework, we use the concept of habitus of Bourdieu (2011), performance and dramaturgy studies of Goffman (1985), Coutinho (2012) and Gutmann (2012), among others, as Vizeu (2005), Benjamin (1996), Abreu e Lima (2010) and Mota (2001). For this study, we analyzed 73 reports from the first decades of Brazilian television and 72 current reports, totalizing 145 pieces to camera. The results show an increase in the use of camera movements, and the reporter is also moving more during the piece to camera. The most widely used framework is the medium shot, but the wide shot, in which the reporter appears full body, became more common. The average time the reporter is displayed on the vídeo increased, the formality of clothing is being left aside and the graphics appears as a visual element helping the reporter. The study also reaffirms the importance of the TV reporter, that leads the narrative, gives credibility to the report and establishes a link with the audience.