Records |
Author ![sorted by Author field, ascending order (up)](img/sort_asc.gif) |
Xavier Roca; X. Binefa; Jordi Vitria |
Title |
Multiscale Structure Extraction using Morphological Tools. Applications to Edge Detection and to Depth Perception. |
Type |
Miscellaneous |
Year |
1993 |
Publication |
Technical Workshop on Mathematical Morphology and its Applications to Signal Processing. |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
|
Keywords |
|
Abstract |
|
Address |
Barcelona |
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
|
Notes |
OR;ISE;MV |
Approved |
no |
Call Number |
BCNPCL @ bcnpcl @ RBV1993 |
Serial |
247 |
Permanent link to this record |
|
|
|
Author ![sorted by Author field, ascending order (up)](img/sort_asc.gif) |
Xose M. Pardo; Petia Radeva; Juan J. Villanueva |
Title |
Self-Training Statistic Snake for Image Segmentation and Tracking. |
Type |
Miscellaneous |
Year |
1999 |
Publication |
|
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
|
Keywords |
|
Abstract |
|
Address |
Venice |
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
|
Notes |
MILAB |
Approved |
no |
Call Number |
BCNPCL @ bcnpcl @ PRV1999 |
Serial |
26 |
Permanent link to this record |
|
|
|
Author ![sorted by Author field, ascending order (up)](img/sort_asc.gif) |
Y. Patel; Lluis Gomez; Raul Gomez; Marçal Rusiñol; Dimosthenis Karatzas; C.V. Jawahar |
Title |
TextTopicNet-Self-Supervised Learning of Visual Features Through Embedding Images on Semantic Text Spaces |
Type |
Miscellaneous |
Year |
2018 |
Publication |
Arxiv |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
|
Keywords |
|
Abstract |
The immense success of deep learning based methods in computer vision heavily relies on large scale training datasets. These richly annotated datasets help the network learn discriminative visual features. Collecting and annotating such datasets requires a tremendous amount of human effort and annotations are limited to popular set of classes. As an alternative, learning visual features by designing auxiliary tasks which make use of freely available self-supervision has become increasingly popular in the computer vision community.
In this paper, we put forward an idea to take advantage of multi-modal context to provide self-supervision for the training of computer vision algorithms. We show that adequate visual features can be learned efficiently by training a CNN to predict the semantic textual context in which a particular image is more probable to appear as an illustration. More specifically we use popular text embedding techniques to provide the self-supervision for the training of deep CNN. |
Address |
|
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
|
Notes |
DAG; 600.084; 601.338; 600.121 |
Approved |
no |
Call Number |
Admin @ si @ PGG2018 |
Serial |
3177 |
Permanent link to this record |
|
|
|
Author ![sorted by Author field, ascending order (up)](img/sort_asc.gif) |
Zhong Jin; Franck Davoine |
Title |
Orthogonal ICA Representation Of Images |
Type |
Miscellaneous |
Year |
2004 |
Publication |
8th International Conference on Control, Automation, Robotics and Vision, 369–374 |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
|
Keywords |
|
Abstract |
|
Address |
Kunming (China) |
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
|
Notes |
|
Approved |
no |
Call Number |
Admin @ si @ JiD2004 |
Serial |
499 |
Permanent link to this record |
|
|
|
Author ![sorted by Author field, ascending order (up)](img/sort_asc.gif) |
Zhong Jin; Franck Davoine; Zhen Lou |
Title |
An Effective EM Algorithm for PCA Mixture Model |
Type |
Miscellaneous |
Year |
2004 |
Publication |
Structural and Statistical Pattern Recognition, Lecture Notes in Computer Science, 3138:626–634 |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
|
Keywords |
|
Abstract |
|
Address |
Lisbon, Portugal |
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
|
Notes |
|
Approved |
no |
Call Number |
Admin @ si @ JDL2004 |
Serial |
482 |
Permanent link to this record |
|
|
|
Author ![sorted by Author field, ascending order (up)](img/sort_asc.gif) |
Zhong Jin; Franck Davoine; Zhen Lou |
Title |
Facial expression analysis by using KPCA |
Type |
Miscellaneous |
Year |
2003 |
Publication |
IEEE International Conference on Robotics, Intelligent Systems and Signal Processing (IEEE RISSP 2003), pp736–741 |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
|
Keywords |
|
Abstract |
|
Address |
Changsha, Hunan, China |
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
|
Notes |
|
Approved |
no |
Call Number |
Admin @ si @ JDL2003 |
Serial |
431 |
Permanent link to this record |
|
|
|
Author ![sorted by Author field, ascending order (up)](img/sort_asc.gif) |
Zhong Jin; Jing-Yu Yang; Zhen Lou |
Title |
A luminance-conditional distribution model of skin color information |
Type |
Miscellaneous |
Year |
2005 |
Publication |
2005 Beijing International Conference on Imaging: Technology and Applications for the 21th Century, 280–281 |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
|
Keywords |
|
Abstract |
|
Address |
Beijing (China) |
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
|
Notes |
|
Approved |
no |
Call Number |
Admin @ si @ JYL2005 |
Serial |
628 |
Permanent link to this record |
|
|
|
Author ![sorted by Author field, ascending order (up)](img/sort_asc.gif) |
Zhong Jin; Zhen Lou; Jing-Yu Yang; Quan-sen Sun |
Title |
Face detection using template matching and skin color information |
Type |
Miscellaneous |
Year |
2005 |
Publication |
International Conference on Intelligent Computing, 636–645 |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
|
Keywords |
|
Abstract |
|
Address |
Hefei (China) |
Corporate Author |
|
Thesis |
|
Publisher |
|
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
|
Notes |
|
Approved |
no |
Call Number |
Admin @ si @ JLY2005 |
Serial |
627 |
Permanent link to this record |