1,721,061 research outputs found
Trend detection in folksonomies
No full textAuch erschienen in: Avrithis, Yannis u.a. (Hrsg.): Semantic multimedia. (Lecture notes in computer science ; 4306). Berlin u.a. : Springer, 2006. S. 56-70. ISBN 3-540-49335-2 = 978-3-540-49335-8 (The original publication is available at www.springerlink.com
News Story Segmentation in Multiple Modalities
Get PDFIn this paper we describe an approach to segmenting news video based on the perceived shift in content using features spanning multiple modalities. We investigate a number of multimedia features, which serve as potential indicators of a change in story in order to determine which are the most effective. The efficacy of our approach is demonstrated by the performance of our prototype, where a number of feature combinations demonstrate an up to 18% improvement in WindowDiff score above that of other state of the art story segmenters. In our investigation, there was no, one, clearly superior feature, rather the best segmentation results occurred when there was
synergy between multiple features.status: Publishe
Exploring and Learning from Visual Data
Get PDFThis manuscript is about a journey. The journey of computer vision and machine learning research from the early years of Gabor filters and linear classifiers to surpassing human skills in several tasks today. The journey of the author's own research, designing representations and matching processes to explore visual data and exploring visual data to learn better representations.Part I addresses instance-level visual search and clustering, building on shallow visual representations and matching processes. The representation is obtained by a pipeline of local features, hand-crafted descriptors and visual vocabularies. Improvements in the pipeline are introduced, including the construction of large-scale vocabularies, spatial matching for geometry verification, representations beyond vocabularies and nearest neighbor search. Applications to exploring photo collections are discussed, including location recognition, landmark recognition and automatic discovery of photos depicting the same scene.Part II addresses instance-level visual search and object discovery, building on deep visual representations and matching processes, focusing on the manifold structure of the feature space. The representation is obtained by deep parametric models learned from visual data. Contributions are made to advancing manifold search over global or regional CNN representations. This process is seen as graph filtering, including spatial and spectral. Spatial matching is revisited with local features detected on CNN activations. Finally, a method is introduced for object discovery from CNN activations over an unlabeled image collection.Part III addresses learning deep visual representations by exploring visual data, focusing on limited or no supervision. It progresses from instance-level to category-level tasks and studies the sensitivity of models to their input. It introduces methods for unsupervised metric learning and semi-supervised learning, based again on the manifold structure of the feature space. It contributes to few-shot learning, studying activation maps and learning multiple layers to convergence for the first time. Finally, it introduces an attack as an attempt to improve upon the visual quality of adversarial examples in terms of imperceptibility.Part IV summarizes more of the author's past and present contributions, reflects on these contributions in the present context and consolidates the ideas exposed in this manuscript. It then attempts to draw a road map of ideas that are likely to come
Integrating image segmentation and classification for fuzzy knowledge-based multimedia indexing
No full text
Going Beyond Counting First Authors in Author Co-citation Analysis
Get PDFThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Get PDF“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Réponse aux questions vidéo avec supervision limitée
No full textLe contenu vidéo a considérablement augmenté en volume et en diversité à l'ère numérique, et cette expansion a souligné la nécessité de technologies avancées de compréhension des vidéos. Poussée par cette nécessité, cette thèse explore la compréhension sémantique des vidéos, en exploitant plusieurs modes perceptuels similaires aux processus cognitifs humains et un apprentissage efficace avec une supervision limitée, semblable aux capacités d'apprentissage humain. Cette thèse se concentre spécifiquement sur la réponse aux questions sur les vidéos comme l'une des principales tâches de compréhension vidéo. Notre première contribution traite de la réponse aux questions sur les vidéos à long terme, nécessitant une compréhension du contenu vidéo étendu. Alors que les approches récentes dépendent de sources externes générées par les humains, nous traitons des données brutes pour générer des résumés vidéo. Notre contribution suivante explore la réponse aux questions vidéo en zéro-shot et en few-shot, visant à améliorer l'apprentissage efficace à partir de données limitées. Nous exploitons la connaissance des modèles à grande échelle existants en éliminant les défis d'adaptation des modèles pré-entraînés à des données limitées. Nous démontrons que ces contributions améliorent considérablement les capacités des systèmes de réponse aux questions vidéo multimodaux, où les données étiquetées spécifiquement annotées par l'homme sont limitées ou indisponibles.Video content has significantly increased in volume and diversity in the digital era, and this expansion has highlighted the necessity for advanced video understanding technologies. Driven by this necessity, this thesis explores semantically understanding videos, leveraging multiple perceptual modes similar to human cognitive processes and efficient learning with limited supervision similar to human learning capabilities. This thesis specifically focuses on video question answering as one of the main video understanding tasks. Our first contribution addresses long-range video question answering, requiring an understanding of extended video content. While recent approaches rely on human-generated external sources, we process raw data to generate video summaries. Our following contribution explores zero-shot and few-shot video question answering, aiming to enhance efficient learning from limited data. We leverage the knowledge of existing large-scale models by eliminating challenges in adapting pre-trained models to limited data. We demonstrate that these contributions significantly enhance the capabilities of multimodal video question-answering systems, where specifically human-annotated labeled data is limited or unavailable
- …
