Children's visual descriptions
نویسندگان
چکیده
منابع مشابه
Resolving Ambiguous Descriptions through Visual Information
In the context of the SFB (special research group) 360 "Situated Artificial Comunicators" the project "Reference in Discourse" deals with the selection of a specific object from a visual scene in a natural language situation. In the SFB scenario, a robot is instructed by a person to construct a toy airplane. One of the prerequisites to solve this task is the identification of a described object...
متن کاملLearning Hierarchical Linguistic Descriptions of Visual Datasets
We propose a method to learn succinct hierarchical linguistic descriptions of visual datasets, which allow for improved navigation efficiency in image collections. Classic exploratory data analysis methods, such as agglomerative hierarchical clustering, only provide a means of obtaining a tree-structured partitioning of the data. This requires the user to go through the images first, in order t...
متن کاملComposing Complex Behavior from Simple Visual Descriptions
An often-mentioned advantage of rule-based programming languages is that a program can be extended simply by adding a few more rules. In practice however, the rules tend to be dependent on each other and instead of just adding rules, existing rules need to be changed. The unique rules in Cartoonist , a rule-based visual programming environment to build simulations, provides a solution to this p...
متن کاملListen to the graph: Childrens matching of melodies with their visual representations
This paper is a report of matching of melodies with line graphs and music notation by children (aged 10 & 11 years). The study found that children are able to match the up-down contour of melodies with their visual representations, and that matchingtask performance is positively related to mathematical ability in the case of line graphs, and musical ability in the case of music notation. The re...
متن کاملFrom image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions
We propose to use the visual denotations of linguistic expressions (i.e. the set of images they describe) to define novel denotational similarity metrics, which we show to be at least as beneficial as distributional similarities for two tasks that require semantic inference. To compute these denotational similarities, we construct a denotation graph, i.e. a subsumption hierarchy over constituen...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Cognitive Science
سال: 1978
ISSN: 0364-0213
DOI: 10.1016/s0364-0213(78)80058-5