What person do you want to become in the next 20 years?

I am depressed in these days. So I would like to start a revolution in achieving productivity. The first revolution I had made in the first & second year in undergraduate. It was an exciting period with perfectionism and optimism. Golden days were over. As a consequence, I increased in study achievement, i.e I can determine the orientation for myself, and work without supervision. But the unavoidable effect is those stuff is fading out days by days. My weakness, obviously, is no more than procrastination. This is the time more than ever, I realize this weakness most and desire to start a second revolution to get rid of procrastination in my habit. Simultaneously, I have to re-target my goal in long-run plan instead of bullshit weak plans. Does anybody read the book “Eat that frogs,…” ? There are SEVEN steps to sparkle out a good life:

Step ONE. Decide exactly what you want
Step TWO. Write it down
Step THREE. Set a deadline on your goal
Step FOUR. Make a list of everything that you can think of that you are going to do to achieve your goal.
Step FIVE. Organize the list into a plan ( by priority and sequence)
Step SIX. Take action on your plan immediately
Step SEVEN. Do something every single day (keep moving, do not stop)

These steps are quite obvious for everyone but several people do it and few people execute their plan. If you are curious about the book, you can it the most interesting part from Google Book, or download illegally from RAPIDSHARE.

Return to the list. Let’s take the first step, Decide exact what you want. I got stuck at the first step!!! And I think everyone has the same problem as mine. We get frustrated and do not know what kind of person we do want, why, and how. Hence, the my problem goes beyond procrastination, it’s about my career, the most trivial question that all the student in Vietnam have to encounter with. How to solve it?

Anyone who cares about Computer Science should read the article “You and your research” sometime in his/her life. Finally, I read it after knowing about last year. It’s the good news, indeed. It is 20 page long and you can read it online HERE.

The articles is interesting at various perspectives but in order to answer the career question, I quoted here the most relevant information:

Question: Would you compare research and management?

Hamming: If you want to be a great researcher, you won’t make it being president of the company. If you want to be president of the company, that’s another thing. I’m not against being president of the company. I just don’t want to be. I think Ian Ross does a good job as President of Bell Labs. I’m not against it; but you have to be clear on what you want. Furthermore, when you’re young, you may have picked wanting to be a great scientist, but as you live longer, you may change your mind. For instance, I went to my boss, Bode, one day and said, “Why did you ever become department head? Why didn’t you just be a good scientist?” He said, “Hamming, I had a vision of what mathematics should be in Bell Laboratories. And I saw if that vision was going to be realized, I had to make it happen; I had to be department head.” When your vision of what you want to do is what you can do single-handedly, then you should pursue it. The day your vision, what you think needs to be done, is bigger than what you can do single-handedly, then you have to move toward management. And the bigger the vision is, the farther in management you have to go. If you have a vision of what the whole laboratory should be, or the whole Bell System, you have to get there to make it happen. You can’t make it happen from the bottom very easily. It depends upon what goals and what desires you have. And as they change in life, you have to be prepared to change. I chose to avoid management because I preferred to do what I could do single-handedly. But that’s the choice that I made, and it is biased. Each person is entitled to their choice. Keep an open mind. But when you do choose a path, for heaven’s sake be aware of what you have done and the choice you have made. Don’t try to do both sides.

It seems that a very natural answer for me (but it may not apply to you). Just forget about constantly asking “research and management, which one is better?”. We aske because of matter of money and position. If you are a kind of egoistic person, means that you feel happy if you can do whatever you want, this answer is for you. Cheer.

Computer Vision – two paradigms, one mission

Recently, I think that the difference in process between human brain and current recognition systems is the difference in philosophy. Started from remarkable works of Feild and Oslaushend about receptive fields in cortical cells, vision research community believe (or at least admit) that early vision functions in vision pathway takes an important rule in recognizing objects and events. Products raised from this exploration is well-known concepts such as filter banks, textons, shapelets, movemes, low frequency shapes, weak features and so on. These features then are learnt by a classifier using state-of-the-art models (e.x Boosting, Support Vector Machine, Condition Random Field, Bayesian hierachical model). Depending on learner’s category is parametric or non-parametric, it obtain a parameter set or exemplar set after trained. Having haversted remarkable successes, this paradigm of recognition still gets stuck in problems of recognizing from different view-points, intra variant charateristic of object classes, object occlusion (including self-occlusion), varied appearance, multi-pose (human action). So, is it the rule for future vision system?

In spite of the domination of low-level feature based recognition system, there are still some prospective paradigms that thinks differently. The one that I see is a kind of system having a huge database of examples and a extremely robust image matching engine. How can such a system be built? The most notable research group that are pursuing this paradigm is hold at MIT CSAIL. The most motivated person is Antonio Torralba. His interest is exploiting huge database advantage for recognition. His recent works such as spatial envelope, 80 million tiny images, SIFT flow, have sketched a bright picture about how the second paradigm should be.

Let’s see what he did with SIFT flow. This is an image matching technique that finds similar images in their semantics. From a huge database of topics (e.x street, building, cars, people) SIFT flow can match a given image against the database to find out the correct label for the test image. There are two points for such systems. The first point, database must be prepared carefully and resonable. Instance s in the database should be as many as possible. The second point, the image matcheing engine have to be generalized enough. The more images database contains, the more diversities in appearance. If the matching engine is not generalized enough, we fail the mission. Another point is the engine should be fast otherwise it will take hours to compare many thounsands of images. The obvious disadvantage of sencond paradigm is expensive and unportable. However, machine vision is still far from daily life applications.

From the bests of my knowledge, the learning paradigm has produced a vast body of interesting literatures dedicated for themselves. After the arfiticial neural network phenomenon, artificial intelligence community has lowered their head temperature down. However, the marriage between traditional statistics and AI has inspired a new field: statistical machine learning. After Vapnik invented the Support Vector Machine with the core idea but thereotical VC dimension, Learning Theory was born. Simultaneously, inference techniques in probability also take an important position in the current machine learning literature. Graphical model has inspired reseachers to design fancy models that can express dependencies between object in an image or video. The more tools we have, the more products we can create. But the Great Wall of computer vision still stand there without moving back. How can computer recognize objects from different points of view? How can computer think oak tree and pine tree is in the tree class? Again, people begin to study in deductive transfer learning. So far, multitask learning is still lack of coherence.

On the other side, people tend to forget about pattern recognition. In today famous computer vision conferences, the rate of paper submission in pattern recognition is quite low. Undoubtely, it is a hard topic to cope with. The hard point lies in there is no specific pattern to deal with. Human brain thinks about objects using somehow coarse concepts. These concepts are maintained by a set of informative features or a huge set of exemplars, it is in controversy. But it is worthwhile for us to try all the posibility. Pattern matching also requires seminal works in vision feature. Consequently, whatever paradigms computer vision researchers choose to work with, vision and psychology researchers continue their own works diligently./.

Qui Nhon, Feb 17, 2009

Phong Vo