|
|
|
| e-Pub |
Previous | 
Home
Section: Partnerships and Cooperations
International Initiatives
NSFC Project: Using transfer learning to understand visual objects and their relationships
Participant : Miaojing Shi.
Duration: 2 years, start in Jan 2019
Partners: Tongji University, China
This project is supported by China National Joint Research Fund for Overseas Chinese Scholars. Machine Perception tasks have flourished since the advent of deep learning techniques. Next key problem lies on visual scene understanding. To make sense of visual scenes, we need to rely on the visual object relationships inside. The challenge for this task is that 1) the training data is limited, on particular those unusual seen objects/object relationships; 2) visual relationships become complicated and diverse with an increase of object numbers. This research shall employ the transfer learning methods to transfer available knowledge of visual relationships to new objects with unknown relationships. The significance of this research is not just to enhance the machine perception ability; it allows us to leverage a relatively small amount of expensively annotated images to detect new objects and their relationships in a much larger dataset without or with only cheap image-level labels.
Inria International Partners
Informal International Partners
Participation in Other International Programs
-
STIC-AMSUD Project : TRANSFORM
Participants : Simon Malinowski, Guillaume Gravier, Laurent Amsaleg.
TRANSFORM is a research project that involves Linkmedia Team, PUC Minas, Brazil and Univ. of Chile. It aims at studying complex transformations of multimedia data in order to facilitate its manipulation. TRANSFORM focuses on transforming multimedia data into compact representations that are suited for indexing and retrieval purposes.
-
Participants : Vincent Claveau, Ewa Kijak, Clément Dalloux.
FIGTEM is a research project that involves STL-CNRS, CHU Rennes, PUC Parana, Curitiba and led by LinkMedia. This project aims at developing natural language processing methods, including information extraction and indexing, dedicated to the clinical trial domain. The goal is to populate a formal representation of patients (via their electronic patient records) and clinical trial data in different languages (French, English, Portuguese).
-
NSFC Project : Perception and self-learning of service robot in dynamic scenarios
Participant : Miaojing Shi.
This project is the Key Program of National Natural Science Foundation of China, which involves Miaojing Shi from Linkmedia and is led by Tongji University. It aims at improving the perception of service robot in dynamic scenarios through self-learning.