Journal ArticleDOI
Analyzing the Subject of a Picture: A Theoretical Approach
Reads0
Chats0
TLDR
A theoretical basis for identifying and classifying the kinds of subjects a picture may have is suggested, using previously developed principles of cataloging and classification, and concepts taken from the philosophy of art, from meaning in language, and from visual perception are suggested.Abstract:
This paper suggests a theoretical basis for identifying and classifying the kinds of subjects a picture may have, using previously developed principles of cataloging and classification, and concepts taken from the philosophy of art, from meaning in language, and from visual perception. The purpose of developing this theoretical basis is to provide the reader with a means for evaluating, adapting, and applying presently existing indexing languages, or for devising new languages for pictorial materials; this paper does not attempt to invent or prescribe a particular indexing language.read more
Citations
More filters
Journal ArticleDOI
Framing image description as a ranking task: data, models and evaluation metrics
TL;DR: This paper proposed to frame sentence-based image annotation as the task of ranking a given pool of captions and showed that the importance of training on multiple captions per image, and of capturing syntactic (word order-based) and semantic features of these captions, is emphasized.
Proceedings Article
Framing Image Description as a Ranking Task: Data, Models and Evaluation Metrics (Extended Abstract)
TL;DR: This work proposes to frame sentence-based image annotation as the task of ranking a given pool of captions, and introduces a new benchmark collection, consisting of 8,000 images that are each paired with five different captions which provide clear descriptions of the salient entities and events.
Proceedings Article
Content-Based Image Retrieval
Malek Adjouadi,Marie L. Lucas,Emanuel L. Pozo,Hien Nguyen,Kevin Maynard,Stacey Thomas,Armando Barreto,Scott Graham,Naphtali Rishe +8 more
TL;DR: A survey of CBIR systems is provided and the fundamental properties and techniques used in these systems are explained, including text-based information retrieval and why it does not work for searching through collections of images.
Proceedings ArticleDOI
Misleading Online Content: Recognizing Clickbait as "False News"
TL;DR: Methods for recognizing both textual and non-textual clickbaiting cues are surveyed, leading to the suggestion that a hybrid approach may yield best results.
References
More filters
Journal ArticleDOI
A theory of pictorial perception
TL;DR: Words and symbols (including graphic symbols and geometrical drawings) are essential for learning about properties, variables, groups, classes, Classes, and universals.
Journal ArticleDOI
Computer-Assisted Construction of a Thematic Catalog of Primary and Secondary Subject Matter
Journal ArticleDOI
The Archive for Research in Archetypal Symbolism
TL;DR: The products of imagination are always in essence visual, their forms must, from the outset, have the character of images and moreover of typical images, which is why I call them "atchetypes".