Grounding action descriptions in videos
M Regneri, M Rohrbach, D Wetzel, S Thater… - Transactions of the …, 2013 - direct.mit.edu
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 …
substantially improve model predictions, but so far only visual information extracted from …
Shopping behavior recognition using a language modeling analogy
Automatic understanding and recognition of human shopping behavior has many potential
applications, attracting an increasing interest in the marketing domain. The reliability and …
applications, attracting an increasing interest in the marketing domain. The reliability and …
Event structures in knowledge, pictures and text
M Regneri - 2013 - publikationen.sulb.uni-saarland.de
This thesis proposes new techniques for mining scripts. Scripts are essential pieces of
common sense knowledge that contain information about everyday scenarios (like going to …
common sense knowledge that contain information about everyday scenarios (like going to …
Combining visual recognition and computational linguistics: linguistic knowledge for visual recognition and natural language descriptions of visual content
M Rohrbach - 2014 - publikationen.sulb.uni-saarland.de
Extensive efforts are being made to improve visual recognition and semantic understanding
of language. However, surprisingly little has been done to exploit the mutual benefits of …
of language. However, surprisingly little has been done to exploit the mutual benefits of …
[PDF][PDF] Combining Visual Recognition and Computational Linguistics
M Rohrbach - 2014 - core.ac.uk
Extensive efforts are being made to improve visual recognition and semantic understanding
of language. However, surprisingly little has been done to exploit the mutual benefits of …
of language. However, surprisingly little has been done to exploit the mutual benefits of …