Grounding Action Descriptions in Videos
نویسندگان
چکیده
منابع مشابه
Grounding Action Descriptions in Videos
Recent work has shown that the integration of visual information into text-based models can substantially improve model predictions, but so far only visual information extracted from static images has been used. In this paper, we consider the problem of grounding sentences describing actions in visual information extracted from videos. We present a general purpose corpus that aligns high qualit...
متن کاملInterprofessional Education Conference: Grounding Action in Theory
This article has no abstract.
متن کاملGrounding Language in Descriptions of Scenes
The problem of how abstract symbols, such as those in systems of natural language, may be grounded in perceptual information presents a significant challenge to several areas of research. This paper presents the GLIDES model, a neural network architecture that shows how this symbol-grounding problem can be solved through learned relationships between simple visual scenes and linguistic descript...
متن کاملGrounding Relations in Action
This paper describes an attempt to ground the meaning of relational concepts in the sensory-motor dynamics resulting from our active interaction with the world. It is suggested that relations are encoded by executing or mentally simulating actions which are constrained by the environment and the specifics of our physical bodies. The virtues of the approach are demonstrated by a computational si...
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: Transactions of the Association for Computational Linguistics
سال: 2013
ISSN: 2307-387X
DOI: 10.1162/tacl_a_00207