2006:2006 Plenary Notes - Revision history

Admin: /* Opening */

2006-10-19T18:45:37Z

‎Opening

Admin: /* Openning */

2006-10-19T18:45:07Z

‎Openning

Xiao at 22:16, 12 October 2006

2006-10-12T22:16:21Z

Xiao at 22:01, 12 October 2006

2006-10-12T22:01:15Z

Xiao at 21:54, 12 October 2006

2006-10-12T21:54:01Z

Xiao at 21:51, 12 October 2006

2006-10-12T21:51:21Z

Xiao at 21:50, 12 October 2006

2006-10-12T21:50:27Z

Xiao at 21:44, 12 October 2006

2006-10-12T21:44:50Z

Xiao at 21:29, 12 October 2006

2006-10-12T21:29:38Z

Xiao at 21:24, 12 October 2006

2006-10-12T21:24:40Z

@@ Line 3: / Line 3: @@
 =Opening=
-Professor Stephen Downie gave the openning remarks:
+Professor Stephen Downie gave the opening remarks:
 *We will present certificates for participants. Feel free to grab yours if you are leaving.

@@ Line 1: / Line 1: @@
 Oct. 12th @ Empress Crystal Hall, Victoria
-=Openning=
+=Opening=
 Professor Stephen Downie gave the openning remarks:

@@ Line 30: / Line 30: @@
 We need new dataset to see if the tuned parameters are good for onseen data.
 Question: comparison to last year results?
-Answer:
+Answer: this year is better because there are multiple parameter tunings.
 ==Evalutron 6000==
@@ Line 76: / Line 76: @@
 Stephen: some of them, yes.
-audience1: please be aware of a work on labelling images? "EST game"? people playing games while labeling image. they went throught the IRB in CMU
+audience1: please be aware of a work on labelling images? "ESP game": people playing games while labeling image. they went throught the IRB in CMU
 audience2:  reaching some conclusions. To get some sense on what makes them different.
@@ Line 86: / Line 86: @@
 audience3: we would like to pay .50$ for each song.
 Stephen: I like this motivation model too, but the copyright is really tricky. we will work towards that. This brings to funding issues.
-Kris:???
+Kris: "unknow" is a bonous to avoid overfitting.
 audience4: let old algorithms run in new years, so as to see their variantions.
-Stephen: I/O changes across years. We will try to make I/O stable
+Stephen: I/O changes across years. We will try to make I/O stable.
-Alexandra Uitdenbogerd: some participants may not want their algrithms to run against new datasets. But stable I/O is really nice.
+Alexandra Uitdenbogerd: some participants may not want their algrithms to run against new datasets. But stable I/O is really nice. Better to make source code accessible for individuals who wants to share their code.
-== Onset detection??? ==
+== Onset detection==
 audience4: having individual results for each entrance? because metrics and statistic tests can change, only raw results last.
-Andy: the raw results are avaible, but the groundtruth is Maarten's (?or Martin??) data.
+Andy: the raw results are avaible, but the groundtruth is  Martin's data.
 ==Audio similarity==
@@ Line 104: / Line 101: @@
 Paul: organizers should attend the Spring meeting and finalize evaluation, better not to change evaluation at last minutes. New modifications can take effect in next year.
 Elias: this is very good, consistency is high
 Stephen: '''precise definition''' of task would help -- what we are going to compare!. A bit worry about variance. I hope we are not getting malicious people.
 Elias: "audio similarity" means too many things, so anyone can give a better name?
@@ Line 119: / Line 115: @@
 ==Score Following==
-Organizer (Diemo Schwarz ?): I am glad we have a framework now. Next year, we will have more participants. Now audio to symbolic, we have high precision after quite a lot hand work.
+Organizer (Diemo Schwarz): I am glad we have a framework now. Next year, we will have more participants. Now audio to symbolic, we have high precision after quite a lot hand work.
 Offline analysis can be another topic.
 next year: augment database, and change the measures.
@@ Line 131: / Line 127: @@
 . Stephen: similarity and metadata like mood, usage, etc.
 . Eric Nicoles: encourage you to keep on the symbolic contests.
-. collaborative filtering: the textual data can be shared by participants and encourage participation.
+. collaborative filtering: the textual data can be shared by participants and encourage participation. Norman in last.fm has much data.
-Audience1:   ???
+Audience1:  We might have the problem on making our data public.
 Kris: connect collaborative filering data to audio
 Stephen: start to think about this NOW! Thank everyone!!!
 Digest MIREX 2006 results; Think about MIREX 2007!

@@ Line 129: / Line 129: @@
 =New tasks=
 . Andy: pitch detection
-. Stephen: metadata like mood, usage, etc.
+. Stephen: similarity and metadata like mood, usage, etc.
 . Eric Nicoles: encourage you to keep on the symbolic contests.

← Older revision		Revision as of 21:54, 12 October 2006
Line 126:		Line 126:
	Stephen: I will lead this contest next year. Get more songs and build larger database		Stephen: I will lead this contest next year. Get more songs and build larger database
	* Folks please post your poster (pdf) onto the wiki.		* Folks please post your poster (pdf) onto the wiki.
		+
		+	=New tasks=
		+	1. Andy: pitch detection
		+	2. Stephen: metadata like mood, usage, etc.
		+	3. Eric Nicoles: encourage you to keep on the symbolic contests.

@@ Line 52: / Line 52: @@
 ==Future MIREX plans==
 =Discussion=
@@ Line 119: / Line 125: @@
 ==Audio Cover Song==
 Stephen: I will lead this contest next year. Get more songs and build larger database
 * Folks please post your poster (pdf) onto the wiki.

@@ Line 96: / Line 96: @@
 ==Audio similarity==
 A link to Elias' paper on this task.
-Paul: organizers should attend the Spring meeting and finalize evaluation, better not to change evaluation at last minutes.
+Paul: organizers should attend the Spring meeting and finalize evaluation, better not to change evaluation at last minutes. New modifications can take effect in next year.
 Elias: this is very good, consistency is high
 Kris: ???
@@ Line 111: / Line 111: @@
 Stephen: we haven't done Friedman test for this contest yet.
 Rainer: more data means more evaluation burden, really depends how much we'd like to do. there is a link on the wiki to my processing results.

← Older revision		Revision as of 21:29, 12 October 2006
Line 86:		Line 86:
	Alexandra Uitdenbogerd: some participants may not want their algrithms to run against new datasets. But stable I/O is really nice.		Alexandra Uitdenbogerd: some participants may not want their algrithms to run against new datasets. But stable I/O is really nice.
	??Better to make source code avaible??		??Better to make source code avaible??
		+
		+	audience5:
		+
		+	audience4: having individual results for each entrance? because metrics and statistic tests can change, only raw results last.
		+	Andy: the raw results are avaible, but the groundtruth is Maarten's (?or Martin??) data.
		+
		+

@@ Line 60: / Line 60: @@
 *submission: robustness, platform, scalability, paralellization
-Kris: call for organizer!
+Kris: call for organizers!
 Alexandra Uitdenbogerd: "similarity" judgment is difficult. It might be easier to make judgment on genres for example.
-audience: How long was need for evaluate one pair?
 Stephen: we have the data, but have not digged into it.
 Bergstra: can you make the contests year around?
-audience: please be aware of a work on labelling images? "EST game"? people playing games while labeling image. they went throught the IRB in CMU
+audience1: please be aware of a work on labelling images? "EST game"? people playing games while labeling image. they went throught the IRB in CMU
 audience2:  reaching some conclusions. To get some sense on what makes them different.
 Stephen: IPM journal will have a special issue on MIREX, I'd like to organize it by contests. There have been a lot of discussions going on on the mailing lists of Audio sim and symbolic melody similarity.
 =Acknowledgement=
 Mellon Foundation