Okay. So next task, next topic is motion database. So the work we introduce here is a retrieval and visualization of human motion data via stick figures. The motivation here is that there is a large motion database, motion capture database available. So you have lots of human motion captured, lots of them. So by combining them you can. Create interesting animation very easily. However, the problem is that it's very, very difficult to find desired motion. Two problems, it's very difficult to see what's in the database already, so browsing can be difficult. Another problem is that it's very difficult to search. You may want to search for specific motion, but specifying desired motion is not easy. So that’s a problem. And our approach is to use comic visualization or stick figure visualization. Stick figures for both visualization and search, so for visualization giving us image or motion capture data system automatically generates this kind of comic strip like representation. So in this way you can get a motion just by watching a static representation and then you get the idea of the motion. And then another is sketch based search. So you quickly sketch the desired motion and then the system automatically retrieves it. And what's interesting here is that not only user draws a pose. But user can also specify the motion, trajectory, or individual joint to find the target motion, efficiently. So, let me show you a video. So here is a visualization, so taking this 3D motion as input. The system generates this kind of comic strip representation. So by looking at this comics you can understand the content of the motion. And this is stick figure sketch based search. On the left you draw a query and the system continuously shows the search result given this user input. So first we show the generation of stick figure comic strip from motion. So this is input, animation. And then we analyze the speed, and then we get the key poses, this way. And then we select the most effective viewing angle, and then render the results. And as a result You get a very effective representation. Here is a couple of examples. Here as you see in addition to the pose itself, the system also shows the most dynamic, most position- motion trajectory. To provide more information. [BLANK_AUDIO] So this is an example of database browsing. So usually in order to browse this kind of database, you have to watch individual motions one by one. But here you can quickly see what's going on by looking at the global view. So our next part is the search. So, on the left side you draw, sketch the desired shape as a stick figure. So head, and leg, and body, and as you see the system continuously provides feedback about the matching result. [BLANK_AUDIO] Now interesting here is that in addition to the pose itself user can draw this kind of trajectory speed lines. So this specifies our movement direction. So here in this way you can move the, identify the shape that raise the hands this way. So this can filter out motion from top to down. And here is the opposite motion. So we found that this kind of speed lines is very useful for specifying specific motion. [BLANK_AUDIO] User can retrieve longer sequence by sketching multiple sequences like fast kick, next punch. And then do something next, then you got the system searches for a motion clip that satisfies this request. Okay, so let me briefly describe the algorithm. The first is visualization, and next is search. So visualizations, the one question to answer is what, which pose to use? You know, you have long sequence, so many poses, and they have to pick couple of important key poses. So here in this system, we've used a scene where the character changes its motion, movement direction or when the motion is stopped. But here, you see here the direction suddenly changes, so we picked it as an important pose. And after picking important poses next question is which viewing angle to use. There are many ways to render specific 3D shape. In 2D, so in order to identify a most effective view, we use a perpendicular, the view direction which is perpendicular to the movement direction. So here an example, when the, this character is making a kicking motion, we believe that this motion, side view, is better than this front view because you can see the motion of the leg. So we compute the trajectory of the joint, most moving joint, and then we get a direction most perpendicular to the prominent motion. And search. So for search, one key observation we got is, joint, specific XY coordinate or, joint locations are not very accurate. Because in user's informal sketch, you know, joint range changes so much, and is so unstable. So we cannot rely on joint location, or specific positions. However, we observed that the orientation of joint angle, is relatively stable. Even in informal user sketch. So we, we decided to use a 2D direction, orientation of each joint, or each bone, as a key for the search. Another important thing is that there are multiple matching possibilities, so we consider all possibilities in the search. For example, you now, if user sketch, this kind of character. The user draws only one arm and one leg. So there are so many possibilities. This can represent left leg or right leg. And this can represent right arm or left arm. So we just consider all the possibilities and then return all the matched results of these priorities. Okay. So here is a summary. So we presented a efficient access to large motion capture database. So we presented comic based visualization, and sketch based search. And we discussed identifi- identification key poses and viewing directions. And also we mentioned that we use bone direction for the search. So to learn more, original paper is called Retrieval and Visualization of Human Motion Data by- via stick figures. And comic-strip visualization, we get idea from a Comic Chat system, which takes a chat communication sequence. And then automatically generates comic strips representing the chat conversation. And also there's a paper on 3D shape retrieval, using sketching as input, and this is called search engine for 3D models and this can be interesting little paper to look at. And finally, posing. Character posing by stick figure was already explored in a paper called sketching interface for articulated figure animation. So they take 2D stick figure illustration and then generate smooth 3D animation by drawing multiple, stick figures. But they did not use motion capture. Okay, so this is a summary of this week. So in this week we discussed deformation and animation. So instead of taking care of a rigid 3D shape. We discussed how to control articulated character and also deformable shapes. And we discussed clothing manipulation, how to put clothing on our character. And the layer operations, how to swap layers in stacked clothing or ropes. And we discussed spatial key framing to make smooth animation of our articulated characters. And procedural deformation is to generate animation of jelly fishes and worms. And then finally we discussed how to efficiently access motion capture database. So, thank you.