Difference: MocapStats (1 vs. 10)
Revision 102006-03-15 - albaab01
| Line: 1 to 1 | ||||||||
|---|---|---|---|---|---|---|---|---|
| ||||||||
| Line: 19 to 19 | ||||||||
| In essence, they learn a bunch of different models on a motion database, then test new (perhaps altered) data on those models and measure the results. The entire system seems extrememly dependent on the databse, how good of a sampling it is for "natural" motion and how large it is. Also, it seems to me that they aren't looking for "natural" motion so much as just looking for motion that is similar to what is found in the database. It doesn't make sense to compare it to human surveys of the results, since asking a human if a motion is natural is very different from determining if a motion is similar to that found in some database. - Roey Flor | ||||||||
| Added: | ||||||||
| > > | Using machine learning techniques to learn models based on Mocap data seems an interesting way to use the tools available, however I wonder if the contribution of this paper was merely to see if this could be done, or if a higher goal is achieved. I doubt the idea of 'naturalness' that the authors claim is being tested by these models were their original intention, as a 'un-natural' behavior by some (for eg, a combination of two natural motions) is considered natural by humans but not by these models. - Disha Al Baqui | |||||||
Revision 92006-03-15 - RoeyFlor
| Line: 1 to 1 | ||||||||
|---|---|---|---|---|---|---|---|---|
| ||||||||
| Line: 11 to 11 | ||||||||
| Using local models constructed from a database of human motion at run time to fill in the data for motion not captured by the markers sounds quite promising, but I need some further elaborations on what a heterogeneous database looks like, and why a local model works perfectly well with it while a global model doesn’t. -- Steven Chang | ||||||||
| Deleted: | ||||||||
| < < | This was Michiel's AMoRe paper from November 2, 2005, so he may have a lot to say. 
The idea is a cute one, but again, since it is a database based approach, the quality of the captured animations depends on the heterogenousness of the database. Still though, applications could be realized for games with specific type of motion (e.g., a boxing game would only need a database of boxing type motions). Though not the major contribution of the paper, I like their Motion Analysis (4.1) section that describes the vision algorithm. One thing I wonder is that there seem to be a lot of parameters (alpha = 0.8 for the query metric, epsilon and Delta d for the k-nearest neighbour search, alpha and beta for the convex weights of the energy function). Is there any rhyme and reason for their choices of the values of these parameters? -- KenRose
The initial purpose of motion capture was to implement realistic human motion in animations. Nowadays researchers and practitioners are trying to lower the cost of motion capture by various ways. I’m not surprised by the results of this paper using some novel mathematical approaches in local modeling and dimensionality reduction. What I concern is how to make this kind of system in home use. Seems there is no reason that we need motion capture in our daily life. The technique itself is potential, but I can’t see how it could be used by a common family in which nobody works on computer graphics and animation. --Zhangbo Liu | |||||||
A Data-Driven Approach to Quantifying Natural Human Motion
Comments & Questions:
The issues with the method given in the paper should be similar to the issues normally seen in Shape Recognition using backpropagation in neural networks. Therefore, it could be generally good for serving the purpose. However, the training data is of essence to make whole system work properly. From the result, it shows that SLDS works overall better than the rest, though I think the performances of different models are somehow determined by the complexities of the target motion, that is, motion for both training and testing; certainly, there is always room for improvments. -- Steven Chang | ||||||||
| Changed: | ||||||||
| < < | Reading this paper made me realize that I forgot a lot of statistics. I would definitely appreciate a small review in MoG, HMMs and SLDS. With respect to the paper, the idea seems interesting, but limited for large scale application since "the measures cannot be significantly better than the motion database of positive examples used to train them". This could be used for measuring the effectiveness of other animation systems though (e.g., rate the naturalness of Perlin noise). I like their idea of using a hierarchical group of features since that explicitly imbues semantics into the data that the models are classifying (that is, that this is human motion data and so there are associations between things like the tibia and femur and that this is not just a bunch of numbers). -- KenRose The authors assume that the evaluation of naturalness is an objective criterion. But actually, it is human ourselves who will perceive the motion, not the machine. However, adding subjective criterion imposed by human observer makes this problem much more complicated and can’t have a reasonable answer in a short time. Anyhow, I’m curious on what if they use the measure in this paper to quantify the method described in last paper. That may be interesting.--Zhangbo Liu I am interested to better understand the overfitting problem mentioned in paragraph 4, and also why would a low dimensional space (small set of joints) be difficult to learn. I am missing the definition in the paper of what is “a natural motion” is. For example, I am guessing that a person walking and suddenly catching a ball thrown to him would be considered as unnatural by the method, even though it is perfectly natural. I wonder if machine learning techniques can handle this type of unexpected motion, or would one need to combine different techniques to learn that. -- Hagit Schechter | |||||||
| > > | In essence, they learn a bunch of different models on a motion database, then test new (perhaps altered) data on those models and measure the results. The entire system seems extrememly dependent on the databse, how good of a sampling it is for "natural" motion and how large it is. Also, it seems to me that they aren't looking for "natural" motion so much as just looking for motion that is similar to what is found in the database. It doesn't make sense to compare it to human surveys of the results, since asking a human if a motion is natural is very different from determining if a motion is similar to that found in some database. - Roey Flor | |||||||
Revision 82006-03-15 - HagitSchechter
| Line: 1 to 1 | ||||||||
|---|---|---|---|---|---|---|---|---|
| ||||||||
| Line: 26 to 26 | ||||||||
| The authors assume that the evaluation of naturalness is an objective criterion. But actually, it is human ourselves who will perceive the motion, not the machine. However, adding subjective criterion imposed by human observer makes this problem much more complicated and can’t have a reasonable answer in a short time. Anyhow, I’m curious on what if they use the measure in this paper to quantify the method described in last paper. That may be interesting.--Zhangbo Liu | ||||||||
| Added: | ||||||||
| > > | I am interested to better understand the overfitting problem mentioned in paragraph 4, and also why would a low dimensional space (small set of joints) be difficult to learn. I am missing the definition in the paper of what is “a natural motion” is. For example, I am guessing that a person walking and suddenly catching a ball thrown to him would be considered as unnatural by the method, even though it is perfectly natural. I wonder if machine learning techniques can handle this type of unexpected motion, or would one need to combine different techniques to learn that. -- Hagit Schechter | |||||||
Revision 72006-03-15 - zephyr
| Line: 1 to 1 | ||||||||
|---|---|---|---|---|---|---|---|---|
| ||||||||
| Line: 11 to 11 | ||||||||
| Using local models constructed from a database of human motion at run time to fill in the data for motion not captured by the markers sounds quite promising, but I need some further elaborations on what a heterogeneous database looks like, and why a local model works perfectly well with it while a global model doesn’t. -- Steven Chang | ||||||||
| Added: | ||||||||
| > > | This was Michiel's AMoRe paper from November 2, 2005, so he may have a lot to say.
The idea is a cute one, but again, since it is a database based approach, the quality of the captured animations depends on the heterogenousness of the database. Still though, applications could be realized for games with specific type of motion (e.g., a boxing game would only need a database of boxing type motions). Though not the major contribution of the paper, I like their Motion Analysis (4.1) section that describes the vision algorithm. One thing I wonder is that there seem to be a lot of parameters (alpha = 0.8 for the query metric, epsilon and Delta d for the k-nearest neighbour search, alpha and beta for the convex weights of the energy function). Is there any rhyme and reason for their choices of the values of these parameters? -- KenRose
The initial purpose of motion capture was to implement realistic human motion in animations. Nowadays researchers and practitioners are trying to lower the cost of motion capture by various ways. I’m not surprised by the results of this paper using some novel mathematical approaches in local modeling and dimensionality reduction. What I concern is how to make this kind of system in home use. Seems there is no reason that we need motion capture in our daily life. The technique itself is potential, but I can’t see how it could be used by a common family in which nobody works on computer graphics and animation. --Zhangbo Liu | |||||||
A Data-Driven Approach to Quantifying Natural Human Motion
Comments & Questions:
The issues with the method given in the paper should be similar to the issues normally seen in Shape Recognition using backpropagation in neural networks. Therefore, it could be generally good for serving the purpose. However, the training data is of essence to make whole system work properly. From the result, it shows that SLDS works overall better than the rest, though I think the performances of different models are somehow determined by the complexities of the target motion, that is, motion for both training and testing; certainly, there is always room for improvments. -- Steven Chang | ||||||||
| Added: | ||||||||
| > > | Reading this paper made me realize that I forgot a lot of statistics. I would definitely appreciate a small review in MoG, HMMs and SLDS. With respect to the paper, the idea seems interesting, but limited for large scale application since "the measures cannot be significantly better than the motion database of positive examples used to train them". This could be used for measuring the effectiveness of other animation systems though (e.g., rate the naturalness of Perlin noise). I like their idea of using a hierarchical group of features since that explicitly imbues semantics into the data that the models are classifying (that is, that this is human motion data and so there are associations between things like the tibia and femur and that this is not just a bunch of numbers). -- KenRose The authors assume that the evaluation of naturalness is an objective criterion. But actually, it is human ourselves who will perceive the motion, not the machine. However, adding subjective criterion imposed by human observer makes this problem much more complicated and can’t have a reasonable answer in a short time. Anyhow, I’m curious on what if they use the measure in this paper to quantify the method described in last paper. That may be interesting.--Zhangbo Liu | |||||||
Revision 62006-03-15 - albaab01
| Line: 1 to 1 | ||||||||
|---|---|---|---|---|---|---|---|---|
| ||||||||
| Line: 11 to 11 | ||||||||
| Using local models constructed from a database of human motion at run time to fill in the data for motion not captured by the markers sounds quite promising, but I need some further elaborations on what a heterogeneous database looks like, and why a local model works perfectly well with it while a global model doesn’t. -- Steven Chang | ||||||||
| Deleted: | ||||||||
| < < | This was Michiel's AMoRe paper from November 2, 2005, so he may have a lot to say.
The idea is a cute one, but again, since it is a database based approach, the quality of the captured animations depends on the heterogenousness of the database. Still though, applications could be realized for games with specific type of motion (e.g., a boxing game would only need a database of boxing type motions). Though not the major contribution of the paper, I like their Motion Analysis (4.1) section that describes the vision algorithm. One thing I wonder is that there seem to be a lot of parameters (alpha = 0.8 for the query metric, epsilon and Delta d for the k-nearest neighbour search, alpha and beta for the convex weights of the energy function). Is there any rhyme and reason for their choices of the values of these parameters? -- KenRose | |||||||
A Data-Driven Approach to Quantifying Natural Human Motion
Comments & Questions:
The issues with the method given in the paper should be similar to the issues normally seen in Shape Recognition using backpropagation in neural networks. Therefore, it could be generally good for serving the purpose. However, the training data is of essence to make whole system work properly. From the result, it shows that SLDS works overall better than the rest, though I think the performances of different models are somehow determined by the complexities of the target motion, that is, motion for both training and testing; certainly, there is always room for improvments. -- Steven Chang | ||||||||
| Deleted: | ||||||||
| < < | Reading this paper made me realize that I forgot a lot of statistics. I would definitely appreciate a small review in MoG, HMMs and SLDS. With respect to the paper, the idea seems interesting, but limited for large scale application since "the measures cannot be significantly better than the motion database of positive examples used to train them". This could be used for measuring the effectiveness of other animation systems though (e.g., rate the naturalness of Perlin noise). I like their idea of using a hierarchical group of features since that explicitly imbues semantics into the data that the models are classifying (that is, that this is human motion data and so there are associations between things like the tibia and femur and that this is not just a bunch of numbers). -- KenRose | |||||||
Revision 52006-03-15 - KenRose
| Line: 1 to 1 | ||||||||
|---|---|---|---|---|---|---|---|---|
| ||||||||
| Line: 11 to 11 | ||||||||
| Using local models constructed from a database of human motion at run time to fill in the data for motion not captured by the markers sounds quite promising, but I need some further elaborations on what a heterogeneous database looks like, and why a local model works perfectly well with it while a global model doesn’t. -- Steven Chang | ||||||||
| Added: | ||||||||
| > > | This was Michiel's AMoRe paper from November 2, 2005, so he may have a lot to say.
The idea is a cute one, but again, since it is a database based approach, the quality of the captured animations depends on the heterogenousness of the database. Still though, applications could be realized for games with specific type of motion (e.g., a boxing game would only need a database of boxing type motions). Though not the major contribution of the paper, I like their Motion Analysis (4.1) section that describes the vision algorithm. One thing I wonder is that there seem to be a lot of parameters (alpha = 0.8 for the query metric, epsilon and Delta d for the k-nearest neighbour search, alpha and beta for the convex weights of the energy function). Is there any rhyme and reason for their choices of the values of these parameters? -- KenRose | |||||||
A Data-Driven Approach to Quantifying Natural Human Motion
Comments & Questions:
The issues with the method given in the paper should be similar to the issues normally seen in Shape Recognition using backpropagation in neural networks. Therefore, it could be generally good for serving the purpose. However, the training data is of essence to make whole system work properly. From the result, it shows that SLDS works overall better than the rest, though I think the performances of different models are somehow determined by the complexities of the target motion, that is, motion for both training and testing; certainly, there is always room for improvments. -- Steven Chang | ||||||||
| Added: | ||||||||
| > > | Reading this paper made me realize that I forgot a lot of statistics. I would definitely appreciate a small review in MoG, HMMs and SLDS. With respect to the paper, the idea seems interesting, but limited for large scale application since "the measures cannot be significantly better than the motion database of positive examples used to train them". This could be used for measuring the effectiveness of other animation systems though (e.g., rate the naturalness of Perlin noise). I like their idea of using a hierarchical group of features since that explicitly imbues semantics into the data that the models are classifying (that is, that this is human motion data and so there are associations between things like the tibia and femur and that this is not just a bunch of numbers). -- KenRose | |||||||
Revision 42006-03-15 - changxia
| Line: 1 to 1 | ||||||||
|---|---|---|---|---|---|---|---|---|
| ||||||||
| Line: 9 to 9 | ||||||||
| Comments & Questions: | ||||||||
| Added: | ||||||||
| > > | Using local models constructed from a database of human motion at run time to fill in the data for motion not captured by the markers sounds quite promising, but I need some further elaborations on what a heterogeneous database looks like, and why a local model works perfectly well with it while a global model doesn’t. -- Steven Chang | |||||||
A Data-Driven Approach to Quantifying Natural Human Motion | ||||||||
Revision 32006-03-15 - changxia
| Line: 1 to 1 | ||||||||
|---|---|---|---|---|---|---|---|---|
| ||||||||
| Line: 14 to 14 | ||||||||
| Comments & Questions: | ||||||||
| Added: | ||||||||
| > > | The issues with the method given in the paper should be similar to the issues normally seen in Shape Recognition using backpropagation in neural networks. Therefore, it could be generally good for serving the purpose. However, the training data is of essence to make whole system work properly. From the result, it shows that SLDS works overall better than the rest, though I think the performances of different models are somehow determined by the complexities of the target motion, that is, motion for both training and testing; certainly, there is always room for improvments. -- Steven Chang | |||||||
Revision 22006-03-09 - batty
| Line: 1 to 1 | ||||||||
|---|---|---|---|---|---|---|---|---|
| ||||||||
| Deleted: | ||||||||
| < < | ||||||||
-- MichielVanDePanne - 27 Feb 2006
Statistical Models of Motion | ||||||||
| Changed: | ||||||||
| < < | Paper One | |||||||
| > > | Performance Animation from Low Dimensional Control Signals | |||||||
| Changed: | ||||||||
| < < | This is an example response. To add your own response, click on 'Edit' above. Paragraphs are separated with just a blank line. This paper is interesting because... It is flawed because ... I didn't understand the following bits... Open problems are ... -- Michiel van de Panne | |||||||
| > > | Comments & Questions: | |||||||
| Deleted: | ||||||||
| < < | Another paragraph. Replace this text. | |||||||
| Changed: | ||||||||
| < < | Paper Two | |||||||
| > > | A Data-Driven Approach to Quantifying Natural Human Motion | |||||||
| Changed: | ||||||||
| < < | Another paper. Please add your comments below. | |||||||
| > > | Comments & Questions: | |||||||
Revision 12006-02-27 - MichielVanDePanne
| Line: 1 to 1 | ||||||||
|---|---|---|---|---|---|---|---|---|
| Added: | ||||||||
| > > |
Statistical Models of MotionPaper OneThis is an example response. To add your own response, click on 'Edit' above. Paragraphs are separated with just a blank line. This paper is interesting because... It is flawed because ... I didn't understand the following bits... Open problems are ... -- Michiel van de Panne Another paragraph. Replace this text.Paper TwoAnother paper. Please add your comments below. | |||||||
View topic | History: r10 < r9 < r8 < r7 | More topic actions...
Copyright © 2008-2025 by the contributing authors. All material on this collaboration platform is the property of the contributing authors. Ideas, requests, problems regarding TWiki? Send feedback