Two Talks Today at Queens College

-----

Talk #1:

Time: 1pm-2pm, Wednesday, May 25, 2011
Place: CS Department Conference Room 225, Science Building, Queens College, CUNY
Speaker: Min-Hsuan Tsai (UIUC)
Title: Content-based image retrieval with ontology

Abstract:

In this work, we explore the novel possibility on image 
understanding applied to semantic image search. We exploited web 
resources to obtain links from images to keywords and a semantic ontology 
constituting human general knowledge. The former maps visual content 
to related text in contrast to the traditional way of associating images 
with surrounding text; the latter provides relations between concepts for 
machines to understand to what extent and in what sense an image is close 
to the image search query. With the aid of these two tools, the resulting 
image search system is thus content-based and moreover, organized. The 
returned images are ranked and organized such that semantically similar 
images are grouped together and given a rank based on the semantic 
closeness to the input query. The novelty of the system is
twofold: first, images are retrieved not only based on text cues but their 
actual contents as well; second, the grouping is different from pure 
visual similarity clustering. More specifically, the inferred concepts of 
each image in the group are examined in the context of a huge concept 
ontology  to determine their true relations with what people have in mind 
when doing image search.

Bio:

Min-Hsuan Tsai received the B.S. and M.S. degrees in Structural 
Engineering from National Taiwan University, Taipei, Taiwan, R.O.C. and 
the M.S. degree in Operations Research from Stanford University, Palo 
Alto. He is currently a PhD candidate in Electrical and Computer 
Engineering at University of Illinois at Urbana-Champaign.His research 
interests include the application of machine  learning and optimization to 
information retrieval and multimedia signal processing, and cloud 
computing.

-----

Talk #2:

Time: 2pm-3pm, Wednesday, May 25, 2011
Place: CS Department Conference Room 225, Science Building, Queens College, CUNY
Speaker: Guojun Qi (UIUC)
Title: Towards Semantic Knowledge Propagation from Text Corpus to Web Images

Abstract:

In this talk, we study the problem of transfer learning from text to images in 
the context of network data in which link based bridges are available to 
transfer the knowledge between the different domains. The problem of classification 
of image data is often much more challenging than text data because of the 
following two reasons: (a) Labeled text data is very widely available for 
classification purposes. On the other hand, this is often not the case for image 
data, in which a lot of images are available from many sources, but many of them 
are often not labeled. (b) The image features are not directly related to 
semantic concepts inherent in class labels. On the other hand, since text data 
tends to have natural semantic interpretability (because of their human origins), 
they are often more directly related to class labels. The semantic challenges of 
image features are glaringly evident, when we attempt to recognize complex 
abstract concepts, and the visual features often fail to discriminate such 
concepts. However, the copious availability of bridging relationships between 
text and images in the context of web and social network data can be used in 
order to design for effective classifiers for image data. The relationships 
between the images and text features (which may be derived from such web-centered 
bridges) provide additional hints for the classification process in terms of the 
image feature transformations which provide the most effective results. One of 
our goals is to develop a mathematical model for the functional relationships 
between text and image features, so as to indirectly transfer semantic knowledge 
through feature transformations. This feature transformation is accomplished by 
mapping instances from different domains into a common space of unspecified 
topics. This is used as a bridge to semantically connect the two heterogeneous 
spaces. We evaluate our knowledge transfer techniques on an image classification 
task with labeled text corpora and show the effectiveness with respect to 
competing algorithms.

Bio:

Guo-Jun Qi is a PhD candidate with Department of Electrical and Computer 
Engineering and Beckman Institute of the University of Illinois at 
Urbana-Champaign, advised by Professor Thomas S. Huang. His current research 
interests include pattern recognition, machine learning and computer vision, 
especially on heterogeneous networks with cross-domain data. He is the recipent 
of the best paper award on the 15th ACM International Conference on Multimedia 
(ACM SIGMM), as well as the IBM PhD fellowship award from 2011-2012.

-----