Grounded Semantic Composition for Visual Scenes
نویسندگان
چکیده
منابع مشابه
Grounded Semantic Composition for Visual Scenes Grounded Semantic Composition for Visual Scenes
We present a visually-grounded language understanding model based on a study of how people verbally describe objects in scenes. The emphasis of the model is on the combination of individual word meanings to produce meanings for complex referring expressions. The model has been implemented, and it is able to understand a broad range of spatial referring expressions. We describe our implementatio...
متن کاملGrounded Semantic Composition for Visual Scenes
We present a visually-grounded language understanding model based on a study of how people verbally describe objects in scenes. The emphasis of the model is on the combination of individual word meanings to produce meanings for complex referring expressions. The model has been implemented, and it is able to understand a broad range of spatial referring expressions. We describe our implementatio...
متن کاملGrounded Semantic Composition for Visual Scenes DRAFT - Do not cite
We present a study on how people verbally describe objects in visual scenes. The emphasis of our analysis lies on the combination of individual word meanings to produce meanings for complex referring expressions. Based on this study, we propose a computational model of visually-grounded spatial language understanding. We have implemented the model, and it is able to understand a broad range of ...
متن کاملParafoveal semantic processing of emotional visual scenes.
The authors investigated whether emotional pictorial stimuli are especially likely to be processed in parafoveal vision. Pairs of emotional and neutral visual scenes were presented parafoveally (2.1 degrees or 2.5 degrees of visual angle from a central fixation point) for 150-3,000 ms, followed by an immediate recognition test (500-ms delay). Results indicated that (a) the first fixation was mo...
متن کاملSemantic categorization precedes affective evaluation of visual scenes.
We compared the primacy of affective versus semantic categorization by using forced-choice saccadic and manual response tasks. Participants viewed paired emotional and neutral scenes involving humans or animals flashed rapidly in extrafoveal vision. Participants were instructed to categorize the targets by saccading toward the location occupied by a predefined target scene. The affective task i...
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: Journal of Artificial Intelligence Research
سال: 2004
ISSN: 1076-9757
DOI: 10.1613/jair.1327