Rohrbach, Anna
[Author]
;
Schiele, Bernt
[Contributor]
Generation and grounding of natural language descriptions for visual data ; Die Erstellung und Lokalisierung natürlicher Sprachbeschreibungen für visuelle Daten
You can manage bookmarks using lists, please log in to your user account for this.
Media type:
Doctoral Thesis;
Electronic Thesis;
E-Book
Title:
Generation and grounding of natural language descriptions for visual data ; Die Erstellung und Lokalisierung natürlicher Sprachbeschreibungen für visuelle Daten
Contributor:
Rohrbach, Anna
[Author]
Published:
Scientific publications of the Saarland University (UdS), 2017-06-02
Footnote:
Diese Datenquelle enthält auch Bestandsnachweise, die nicht zu einem Volltext führen.
Description:
Generating natural language descriptions for visual data links computer vision and computational linguistics. Being able to generate a concise and human-readable description of a video is a step towards visual understanding. At the same time, grounding natural language in visual data provides disambiguation for the linguistic concepts, necessary for many applications. This thesis focuses on both directions and tackles three specific problems. First, we develop recognition approaches to understand video of complex cooking activities. We propose an approach to generate coherent multi-sentence descriptions for our videos. Furthermore, we tackle the new task of describing videos at variable level of detail. Second, we present a large-scale dataset of movies and aligned professional descriptions. We propose an approach, which learns from videos and sentences to describe movie clips relying on robust recognition of visual semantic concepts. Third, we propose an approach to ground textual phrases in images with little or no localization supervision, which we further improve by introducing Multimodal Compact Bilinear Pooling for combining language and vision representations. Finally, we jointly address the task of describing videos and grounding the described people. To summarize, this thesis advances the state-of-the-art in automatic video description and visual grounding and also contributes large datasets for studying the intersection of computer vision and computational linguistics. ; Die Erstellung natürlicher Sprachbeschreibungen für visuelle Daten verbindet Computer Vision und Computerlinguistik. Die Fähigkeit eine prägnante und menschlich lesbare Beschreibung eines Videos zu produzieren, ist ein Schritt zum visuellen Verständnis. Gleichzeitig ermöglicht Lokalisierung der natürlichen Sprache in visuellen Daten die Disambiguierung der sprachlichen Konzepte. Diese Dissertation konzentriert sich auf beide Richtungen wie folgt. Zuerst entwickeln wir Methoden, um komplexe Kochaktivitäten in Videos zu verstehen und für ...