Title: | Robust and Computationally Efficient Image Co-Segmentation |
Speaker: | Prof Subhasis Chaudhuri, Department of Electrical Engineering, Indian Institute of Technology Bombay, India |
Time/Place: | 16:30 - 17:30 (Preceded by Reception at 4:00pm) SCT909, Science Tower, HSH Campus, Hong Kong Baptist University |
Abstract: |
If one is given a large number (N) of images sourced from various
places and under different contexts, but having at least "something"
in common, then the extraction of the object common in all these
images is known as co-segmentation. The first part of the talk
will explain how this can be solved using the concept of maximum
common subgraph (MCS) matching. This problem becomes very challenging
if only an unknown number (say M‹N) of these images contain
the co-segmentable common object. This is quite natural as not
everyone in the crowd is looking at the same object. Unfortunately,
MCS cannot be applied to co-segment this outlier-ridden image
set. We introduce a new concept called maximally occurring common
subgraph (MOCS) matching, which is capable of handling such outliers
in the data. Unfortunately the search becomes prohibitive. We
provide a greedy solution to MOCS matching problem by defining
an intermediate graphical representation called latent class
graph. This requires only O(N) matching operations and ensures
globally consistent matching of the common object regions across
images.
In the second part of the talk, we shall discuss how the same problem can also be solved using statistical mode detection in the multi-dimensional feature space of all super-pixel segments in the image set. We assume that the dominant mode and its neighbors in the feature space correspond to the image segments that partially constitute the common object in every image. We obtain the complete objects using an LDA based region growing of the partial object regions. We shall present the details of these methods in the talk and shall illustrate the efficacy of the proposed solutions in solving the co-segmentation problem. |
Title: | Higher Education in India: A Challenge |
Speaker: | Prof Subhasis Chaudhuri, Department of Electrical Engineering, Indian Institute of Technology Bombay, India |
Time/Place: | 16:30 - 17:30 (Preceded by Reception at 4:00pm) SCT909, Science Tower, HSH Campus, Hong Kong Baptist University |
Abstract: | Despite being regarded as having a very long history of education and scholarship, India has always struggled to provide universal access to education - more so, at the higher education level. Since the independence, the Government has been working very hard in providing quality education to all. However, the challenges are too many - the sheer number of students, the cost of providing education, societal structure, remoteness of places, certain disconnect with the industry, etc. Nonetheless skilling of its citizen is a must for a country in today's world. In this talk, we plan to discuss various aspects of challenges that India faces and where we must find appropriate solutions. |
We organize conferences and workshops every year. Hope we can see you in future.
Learn MoreProf. M. Cheng, Dr. Y. S. Hon, Dr. K. F. Lam, Prof. L. Ling, Dr. T. Tong and Prof. L. Zhu have been awarded research grants by Hong Kong Research Grant Council (RGC) — congratulations!
Learn MoreFollow HKBU Math