IRC log of mmsem on 2006-07-10

Timestamps are in UTC.

08:17:24 [RRSAgent]
RRSAgent has joined #mmsem
08:17:25 [RRSAgent]
logging to
08:17:54 [JeffP]
zakim, who is on the phone?
08:17:54 [Zakim]
sorry, JeffP, I don't know what conference this is
08:17:56 [Zakim]
On IRC I see RRSAgent, Zakim, JeffP, pasquale, Massimo
08:19:41 [JeffP]
this will be mmsem First F2F
08:20:00 [JeffP]
what conference is this?
08:20:10 [jacco2]
jacco2 has joined #mmsem
08:20:13 [JeffP]
zakim, this will be mmsem First F2F
08:20:13 [Zakim]
I do not see a conference matching that name scheduled near this time, JeffP
08:21:25 [raphael]
raphael has joined #mmsem
08:22:22 [jacco2]
zakim, list conferences
08:22:22 [Zakim]
I see INC_MMSEM(F2F)3:00AM active and no others scheduled near this time
08:22:50 [jacco2]
zakim, this is INC_MMSEM(F2F)
08:22:50 [Zakim]
ok, jacco2; that matches INC_MMSEM(F2F)3:00AM
08:23:02 [yannis]
yannis has joined #mmsem
08:24:00 [raphael]
08:24:32 [raphael]
Chair: raphael
08:24:41 [raphael]
Scribe: jacco2
08:25:27 [raphael]
zakim, who is here?
08:25:27 [Zakim]
On the phone I see Jeff_Pan, ??P1
08:25:28 [Zakim]
On IRC I see yannis, raphael, jacco2, RRSAgent, Zakim, JeffP, pasquale, Massimo
08:25:37 [raphael]
zakim, ??P1 is CWI
08:25:37 [Zakim]
+CWI; got it
08:26:04 [raphael]
zakim, CWI is meeting_room
08:26:04 [Zakim]
+meeting_room; got it
08:28:47 [jacco2]
people on IRC: you can connect by phone too!
08:29:01 [jacco2]
See phone number in the agenda
08:29:11 [pasquale]
sorry, for now i can only irc
08:29:19 [jacco2]
Chair opens the meeting and welcomes all participants
08:29:54 [jacco2]
start with role call
08:30:36 [jacco2]
Yioannis, athens, greece
08:30:46 [jacco2]
, feature extraction
08:30:46 [JeffP]
I cannot hear very good
08:31:26 [jacco2]
Vassilis, ITI, Greece, research interest SemWeb technologies and mm annotation
08:32:01 [jacco2]
Giovanni, DBin project, DBin is p2p metadata exchange
08:32:36 [jacco2]
Christioan, PhD student, also from Ancona
08:32:52 [jacco2]
08:33:26 [jacco2]
Thomas, Koblenz, also in k-space and aceMedia - mediator role
08:34:02 [jacco2]
thierry, DFKI, aslo in k-space. Member of ISO group on language resources
08:34:28 [jacco2]
George, CWI, PhD student, also in k-space
08:34:47 [jacco2]
Lynda, CWI, k-space
08:35:24 [jacco2]
Jacco, CWI, Semantic Media Interfaces
08:35:50 [jacco2]
Jeff Pann, chair of XG, semantic web languages, reasoning
08:36:42 [jacco2]
Officially, we now have 21 members
08:37:05 [JeffP]
08:37:24 [jacco2]
Vassilis of NTUA is AC Rep for k-space members
08:37:47 [jacco2]
Giovanni, membership is pending via Italian W3C office
08:38:22 [jacco2]
We also have Suzanne Boll as an invited expert
08:38:29 [anadioti]
anadioti has joined #mmsem
08:38:42 [jacco2]
08:39:08 [Zakim]
08:39:10 [VassilisTzouv]
VassilisTzouv has joined #mmsem
08:39:47 [raphael]
hi Vassilis, do you plan to join on the phone ?
08:39:50 [VassilisTzouv]
Hello all
08:40:01 [JeffP]
Hi Vassilis
08:40:03 [VassilisTzouv]
Yes I will join on the phone
08:40:04 [rtroncy]
rtroncy has joined #mmsem
08:41:05 [thristo]
thristo has joined #mmsem
08:41:48 [jacco2]
Vassilis and Yiannis connect by phone & IRC, have send slides which will be presented later
08:42:04 [Thomas]
Thomas has joined #mmsem
08:42:29 [jacco2]
zakim, who is here
08:42:29 [Zakim]
jacco2, you need to end that query with '?'
08:42:35 [Zakim]
08:42:41 [jacco2]
zakim, who is here?
08:42:41 [Zakim]
On the phone I see Jeff_Pan, meeting_room
08:42:42 [Zakim]
On IRC I see Thomas, thristo, raphael, VassilisTzouv, anadioti, yannis, jacco2, RRSAgent, Zakim, JeffP, pasquale, Massimo
08:42:56 [lynda]
lynda has joined #mmsem
08:43:33 [jacco]
jacco has joined #mmsem
08:43:59 [jacco]
Chair introduces W3C processes
08:44:41 [jacco]
Explains about zakim and RRSagent: all members, please lookup the short explanations on the W3C website
08:45:09 [jacco]
topic: W3C process 101
08:45:56 [jacco]
each member will be asked to scribe
08:46:32 [jacco]
we will have bi-weekly teleconf, which will be announced on the web page and mailing list
08:46:46 [jacco]
public minutes will be published
08:46:57 [JeffP]
08:47:01 [jacco]
Chair explains goal of the W3C incubators.
08:47:36 [raphael]
Incubator Activity:
08:47:52 [jacco]
Raphael shows slides of Steve
08:49:12 [jacco]
Important: XGs are light-weight, and will finish within one year
08:49:47 [jacco]
Goal is to publish technical report with advice to W3C about potential Recommendation track followup
08:50:22 [jacco]
We are the second XG within W3C
08:51:07 [JeffP]
08:51:29 [cgi-irc]
cgi-irc has joined #mmsem
08:52:18 [jacco]
jeff: xg is new way to prepare a new activity, with much better infrastructure as before
08:53:19 [IoannisPratikakis]
IoannisPratikakis has joined #mmsem
08:53:26 [jacco]
jeff: OWL was based on member submission on DAML+OIL, but it took still 2 years to get the OWL REC out, which is not that much difference
08:53:53 [jacco]
With the XG we have a better infrastructure to do the ground work of the preparation
08:54:37 [jacco]
So later during this F2F we should discuss if we want to try to setup a Working Group
08:54:56 [jacco]
... after the charter of the XG ends
08:55:53 [jacco]
Raphael: the Content Labeling XG was the first XG, labeling content for parental guidance etc
08:56:30 [jacco]
We plan to work closely with this XG, invite all members to follow the work of this XG
08:57:23 [jacco]
This XG is the second XG, last week the 3rd XG started on "GEO", geo-tagging etc
08:57:29 [raphael]
Topic: 1. Charter Overview / Objectives
08:57:34 [jacco]
Raphael shows charter
08:58:14 [jacco]
Explain history of the MM taskforce of the SWBPD group
08:58:58 [jacco]
Goal 1 of this XG: show how semweb can be used to achieve mm metadata interoperability
08:59:16 [jacco]
Non-goal: create new MM metadata standards
08:59:53 [jacco]
Goal 2: show added value of formal semantics by describing practical applications and examples
09:00:15 [jacco]
Goal 3: provide best practices based on the above
09:00:54 [jacco]
Open questions: the modalities do we address, what standards, etc
09:00:58 [Zakim]
+ +1.646.722.aaaa
09:01:41 [jacco]
zakim, +1.646.722.aaaa is massimo
09:01:41 [Zakim]
+massimo; got it
09:02:36 [jacco]
Intro of Massimo: I'm from CNR Pisa, multimedia understanding, Semantic Web and XML-based languages
09:04:46 [jacco]
Yioannis:W3C lives too much in its own world, need to talk to other bodies more. In addition, related standards like mpeg-7 have not yet finished. So we need to communicate to these bodies
09:04:56 [jacco]
So how will this happen?
09:05:16 [giovannit]
giovannit has joined #mmsem
09:05:36 [jacco]
Raphael: I agree, best way is to have representatives from these other bodies in this XG as a member or invited expert
09:05:56 [jacco]
But I do not know who could best represent the MPEG-7 community
09:06:08 [jacco]
Yioannis: we could recommend a view names
09:06:26 [Zakim]
09:07:43 [jacco]
Yionannis: I think interoperability is the key issue, we would focus on automatic annotation
09:07:55 [JeffP]
Can people say their names before they speak please?
09:08:21 [Zakim]
09:09:54 [jacco]
Vassilis (ITI): I agree with previous speaker. Not only focus on the RDF-level, also OWL, Rules or extensions.
09:10:03 [JeffP]
09:10:23 [jacco]
Modalities: we could start with images and then try to extend later
09:11:03 [jacco]
jeff: agrees with Vassilis
09:11:44 [Zakim]
09:11:46 [JeffP]
Jeff: ... and OWL and rules are also considered in the charter explicitly
09:11:47 [jacco]
Raphael: MMTF of the SWBPD only did images, maybe do this again is not a good idea
09:13:01 [jacco]
Giovanni: Wnats to stress the importance of real use cases, not focus on theory & formalisation side
09:13:10 [jacco]
09:14:29 [jacco]
Giovanni: I've tried the music-oriented sites, often felt lost. We could find good use cases in this area. Content-based identification is important, once we have a URI there is a lot we can do
09:15:00 [jacco]
What do we identify? Melody, wave signal, midi or mp3 file, etc
09:16:28 [jacco]
Raphael: what is CDDB using? Giovanni: its based on a fingerprint of the recording, not very robust on for example other versions of the same track on a different album etc
09:16:41 [Zakim]
09:17:58 [jacco]
action: Giovanni to coordinate write up of a use case on music
09:18:55 [jacco]
Christian: Agree with Giovanni, real use case in a distributed may also need to address right management
09:20:00 [jacco]
Giovanni: not everybody want all metadatato be open and free
09:21:16 [jacco]
Raphael: Does the group care about rights management?
09:23:08 [jacco]
Yionnis: addressing MPEG-21 is also part of the interoperability issue. Doing music means we expand from images to audio?
09:24:39 [jacco]
Thomas: different use cases with different modalities
09:25:26 [jacco]
SemWeb could be a good opportunity to also show high-level metadata intergrating multiple modalities.
09:26:03 [jacco]
For example, using flickr annotations and than connecting it using semweb technology could be a good basis for a suse case
09:26:03 [Zakim]
09:26:15 [jacco]
09:26:49 [jacco]
Flickr is agood example to show how easy things can be
09:27:08 [jacco]
s/agood/a good
09:28:28 [jacco]
Thomas: our group is interested in combining modalities, like image + audio
09:29:51 [jacco]
Thierry: I'm not a specialist on multimedia. Analysis of lyrics or speach transcripts could be used for this use case
09:30:25 [jacco]
rrsagent, pointer
09:30:25 [RRSAgent]
09:30:57 [jacco]
rrsagent, make logs public
09:31:50 [jacco]
Thierry: we could also look at other projects for good use cases
09:32:30 [jacco]
A use case from, for example, the MESH project, could be on news.
09:33:02 [jacco]
Giovanni: MUSCLE is working on music use cases
09:33:23 [jacco]
AXMEDIS is a big player in this
09:33:41 [jacco]
Massimo, could you say something on MUSCLE
09:33:44 [jacco]
09:33:45 [giovannit]
09:35:18 [jacco]
within the MPEG-7 standard actually using the description schemes is really difficult
09:36:22 [jacco]
action: thierry to write up limitations of MPEG-7 description schemes
09:36:49 [jacco]
George: also wants to focus on real use cases, like the tagging example mentioned by Thomas
09:37:04 [Massimo]
in MUSCLE we are developing an infrastructure to manage multimedia metadata (images, audio, video). We started using the MPEG-7 standard.
09:37:26 [JeffP]
shall we have a use case for tagging?
09:37:27 [raphael]
Massimo, do you have concrete use cases written in MUSCLE ?
09:37:36 [raphael]
About MUSIC ?
09:37:50 [VassilisTzouv]
VassilisTzouv has joined #mmsem
09:37:52 [jacco]
george: blogging could be another use case, with different modalities
09:37:59 [Massimo]
I think we should remember the use cases of the Semantic Web: eg: catalogs of personal photos,
09:38:25 [Massimo]
systems able to recognize persons' faces
09:38:42 [jacco]
george: DRM: I can see the concern, but it is a hard issue that will not be solved by this group
09:39:08 [Massimo]
and then a thing we haven't still seen that is about processed needed to obtain multimedia objects
09:39:42 [jacco]
giovannni: need to align social/human tagging with formal/machine tagging
09:40:44 [jacco]
Raphael: was a workshop on this topic at WWW conference, this community starts to pick this up.
09:41:07 [lynda]
jacco: images too limited, so include other modalities
09:41:21 [lynda]
bridge gap between formal ontologies and tagging
09:42:08 [Massimo]
about music thinking of the semweb use case the personal catalog and the catalog of groups (sorry i can't hear i don't want to break who is talking)
09:43:02 [jacco]
action: george to write up a use case around tagging
09:45:00 [jacco]
raphael: summary: focus on practical use cases like music combined with lyrics analysis and lower level feature extraction, use case on social tagging and semantic web
09:46:05 [jacco]
Yioannis: our features are not limited to the ones defined by MPEG-7
09:48:03 [jacco]
Giovanni: when you use additional features, there is no incentive to go through all the pain of a standardized serialization, becuase there is no aother tool which can read it anyway
09:49:21 [jacco]
Giovanni: this is related to the fact that MPEG-7 semantics is described in informal English only, not machine readable version.
09:49:36 [jacco]
SemWeb approach could help here
09:50:37 [giovannit]
jacco: well not really english only , there is structuring among the decriptors, but the meaning of each one is then in english
09:51:32 [jacco]
Yioannis:mpeg-7 is discussing support transformation matrices to transform labels
09:52:05 [Zakim]
09:52:27 [raphael]
Nikolaos_Simou is Vassilis
09:52:46 [Zakim]
09:52:54 [jacco]
Vasilis: want to raise the question if we are interested in ontologicalization of low level features?
09:53:25 [Zakim]
09:53:40 [VassilisTzouv]
Nikolaos_Simou is Vassilis
09:53:49 [jacco]
zakim, Nikolaos_Simou is Vassilis
09:53:49 [Zakim]
+Vassilis; got it
09:54:41 [jacco]
Raphael: for what do you need a semantic interpretation of the low level descriptors?
09:55:36 [jacco]
yioannis: we need both numeric and symbolic features in various levels
09:57:32 [jacco]
action: Yioanis to write up use case showing the need for semantic interpretation of low level features
09:59:14 [jacco]
yioannis: in the "fused" model all modalities are used to improve the automatic annotation
09:59:51 [jacco]
action: Raphael to write up use case in the news domain
10:01:26 [jacco]
IPTC standardizes NewsML, now doing version 2 of NewsML
10:01:48 [jacco]
CWI works with IPTC in the context of K-Space
10:02:35 [jacco]
NewsML will likely be in the spirit of RDF, but based on an XML syntax
10:03:12 [jacco]
A representative of IPTC is expected to join the XG in the near future
10:05:36 [jacco]
Raphael: there are different sources of metadata: from the camera, from the photographer's (manual) annotation tool, news agency will add more metadata, etc
10:07:26 [jacco]
jacco has changed the topic to: W3C Multimedia Semantics Incubator Group: First Face to face meeting, CWI, Amsterdam
10:07:35 [Massimo]
(trying not to break the conversation..) i think we have to remember two more things about use cases: (1) the "Image annotation on the Semantic Web" note (, Jacco is one of the editors and (2) Algorithms (processed) to obtain multimedia objects
10:08:24 [jacco]
URL of last version of the note is at
10:08:38 [Massimo]
(...processeS /)
10:09:16 [jacco]
Giovanni: we could think about form interfaces generated by local event ontologies
10:10:26 [jacco]
massimo, what do you mean with 'obtain multimedia objects'? Object tracking & recognition?
10:11:12 [Massimo]
i think there could be systems able to reconstruct multimedia objects
10:11:18 [jacco]
Raphael: should we provide some demo web service for mm annotation?
10:12:06 [Massimo]
a set of steps to re-obtain an object
10:12:44 [jacco]
Giovanni:, yes, if we can pinpoint to a basic feature like identification, that crosses all use cases
10:13:06 [Massimo]
thinking of images for example if an image is obtained after having applied some algorithms then we can repeat the same steps to do it again
10:13:27 [rellero_]
rellero_ has joined #mmsem
10:13:36 [jacco]
Maybe there will be an XG on identification as a followup of the Workshop at WWW2006 on this topic
10:14:33 [jacco]
Raphael: Repeats things said by Massimo on IRC.
10:14:59 [jacco]
Notes that the "Image annotation on the Semantic Web" will be discussed by Jacco in the afternoon
10:15:53 [jacco]
Vasilis: I think massimo refers to the process of analyzing the content automatically
10:15:57 [jacco]
10:16:21 [Massimo]
to analyze and to reproduce the content
10:16:46 [jacco]
For example: To recognize this feature, you should apply this process
10:17:41 [jacco]
Massimo, can you explain about "reproduce the content"
10:17:45 [jacco]
10:18:04 [jacco]
Is this a topic on Muscle?
10:18:15 [jacco]
10:18:20 [Massimo]
yes in Muscle and in the ace Media
10:18:59 [Massimo]
(the call for a common multimedia ontology(
10:19:14 [jacco]
Thierry: Raphael, what is the role of low level features in your NewsML scenario?
10:19:35 [jacco]
Raphael: Currently none...
10:20:13 [jacco]
Massimo, could you write up something about the need for being able to reproducing the content? Could I give you an action point?
10:20:51 [Massimo]
ok, i'm writing it give me some minutes
10:21:13 [jacco]
there is no need to hurry :-)
10:21:23 [Massimo]
10:21:34 [JeffP]
Massimo, for the record, could you send to the public list please?
10:21:57 [jacco]
action: Massimo to write up use case on analysis and reproducing content
10:21:57 [Massimo]
10:22:08 [JeffP]
10:23:25 [jacco]
Raphael: Mentioned that this XG will focus on metadata interoperability, where k-space is doing work on combining low level features
10:23:43 [VassilisTzouv]
10:24:41 [JeffP]
ack me
10:24:43 [jacco]
Vassilis: are we considering cross modality interoperability?
10:25:03 [jacco]
Raphael: yes, we discussed this in the beginning of the meeting
10:26:11 [jacco]
Vassilis: I'm not sure this is in scope for the 1st deliverable?
10:26:44 [jacco]
Raphael: We have not decided about what documents and deliverables we will produce
10:27:48 [jacco]
Vassilis: if it still on the metadata level, it is ok
10:28:11 [jacco]
ack VassilisTzouv
10:29:40 [jacco]
Raphael: summary of morning session: people have shown interest on practical use cases on different modalities and domains, 6 action points to write up use cases
10:30:13 [jacco]
Raphael: use cases will also look at the way RDF, OWL, rules etc will be used to solve the use case problem
10:31:20 [jacco]
Noe first lunch, after lunch we well have time for some demonstrations, after coffee break more discussion about the deliverables of the XG
10:31:28 [jacco]
10:32:25 [Zakim]
10:32:26 [Zakim]
10:32:28 [Zakim]
10:32:29 [Zakim]
INC_MMSEM(F2F)3:00AM has ended
10:32:30 [Zakim]
Attendees were Jeff_Pan, meeting_room, Yannis, massimo, Vassilis
10:32:36 [jacco]
Lunch break!
10:32:54 [jacco]
rrsagent, pointer?
10:32:54 [RRSAgent]
10:34:03 [jacco]
rrsagent, draft minutes
10:34:03 [RRSAgent]
I have made the request to generate jacco
10:36:21 [jacco]
Meeting: MMSEM XG First Face to face meeting in Amsterdam
10:36:32 [jacco]
rrsagent, draft minutes
10:36:32 [RRSAgent]
I have made the request to generate jacco
10:38:56 [jacco]
zakim, list conferences
10:38:56 [Zakim]
I see no active conferences
10:38:57 [Zakim]
scheduled at this time is INC_MMSEM(F2F)3:00AM
10:39:19 [jacco]
zakim, this is INC_MMSEM(F2F)3:00AM
10:39:19 [Zakim]
jacco, I see INC_MMSEM(F2F)3:00AM in the schedule but not yet started. Perhaps you mean "this will be INC_MMSEM(F2F)3:00AM".
10:39:29 [jacco]
zakim, this will be INC_MMSEM(F2F)3:00AM
10:39:29 [Zakim]
ok, jacco; I see INC_MMSEM(F2F)3:00AM scheduled to start 219 minutes ago
11:37:05 [IoannisPratikakis]
IoannisPratikakis has joined #mmsem
11:41:59 [raphael]
zakim, who is here?
11:41:59 [Zakim]
apparently INC_MMSEM(F2F)3:00AM has ended, raphael
11:42:01 [Zakim]
On IRC I see IoannisPratikakis, VassilisTzouv, giovannit, lynda, Thomas, raphael, RRSAgent, Zakim, JeffP, pasquale, Massimo
11:55:43 [jacco]
jacco has joined #mmsem
11:56:18 [jacco]
zakim, this will be INC_MMSEM(F2F)3:00AM
11:56:18 [Zakim]
ok, jacco; I see INC_MMSEM(F2F)3:00AM scheduled to start 296 minutes ago
11:57:00 [jacco]
Topic: MMSEM Background and Demonstrations
11:57:35 [jacco]
zakim, propse scribe
11:57:35 [Zakim]
I don't understand 'propse scribe', jacco
11:57:40 [jacco]
zakim, propose scribe
11:57:40 [Zakim]
I don't understand 'propose scribe', jacco
11:57:49 [Zakim]
INC_MMSEM(F2F)3:00AM has now started
11:57:50 [jacco]
zakim, pick scribe
11:57:50 [Zakim]
I don't understand 'pick scribe', jacco
11:57:56 [Zakim]
11:59:58 [jacco]
zakim, pick a scribe
11:59:58 [Zakim]
Not knowing who is chairing or who scribed recently, I propose ??P0
12:00:02 [jacco]
zakim, pick a scribe
12:00:02 [Zakim]
Not knowing who is chairing or who scribed recently, I propose ??P0
12:00:04 [jacco]
zakim, pick a scribe
12:00:04 [Zakim]
Not knowing who is chairing or who scribed recently, I propose ??P0
12:00:27 [Zakim]
12:00:34 [raphael]
??P0 is meeting_room
12:00:40 [jacco]
zakim, pick a scrib
12:00:40 [Zakim]
I don't understand 'pick a scrib', jacco
12:00:43 [raphael]
zakim, ??P0 is meeting_room
12:00:43 [Zakim]
+meeting_room; got it
12:01:30 [anadioti]
anadioti has joined #mmsem
12:02:39 [IoannisPratikakis]
IoannisPratikakis has joined #mmsem
12:02:59 [thristo]
thristo has joined #mmsem
12:03:04 [giovannit]
jeff: fine with me to start again
12:03:08 [jacco]
scribe: Giovanni
12:03:11 [giovannit]
(practicing the scribing..)
12:03:22 [jacco]
scribenick: giovannit
12:03:25 [giovannit]
i'll attempt my best (-:
12:04:05 [giovannit]
raphael : 10 minute per person presentation
12:04:28 [JeffP]
Are the slides available online?
12:04:49 [jacco]
jeff, we will make the slides available asap
12:04:53 [JeffP]
12:06:35 [Zakim]
12:06:53 [jacco]
Jacco show demo at
12:07:54 [giovannit]
ecoluter applications: converted metadata of a few musiums into rdf and seen how far we get without doing heavy weight alightment
12:11:04 [raphael]
All the slides shwon will be at:
12:12:26 [raphael]
12:12:56 [raphael]
12:29:08 [raphael]
12:29:37 [giovannit]
jaccos'd demo shows a full text search which works recursively on the rdf graph
12:30:11 [giovannit]
basically resources are collected starting from those which have a literal attached matching the query, a number of euristics and settings enable meaningful rating and limiting of the end result
12:31:05 [giovannit]
the whole structure works also fine when generic dataset is loaded, providing an ontology based navigations of the instances and visualization of related metadata. Cool ajax makes it apparently very responsive
12:31:11 [cgi-irc]
cgi-irc has joined #mmsem
12:31:53 [giovannit]
the work is powered by swi prolog. Jacco says they tried doing this in sparql but the expressivity is really not sufficient for the needs of the algorithms used here.
12:32:37 [giovannit]
Ioannis presenting now
12:33:56 [giovannit]
presentation introduces ellogon a general purpose language engineering platform
12:36:35 [giovannit]
CIL: a computational intelligence laboratory, applications are shown in the area of OCR , shape based retrieval, human tracking
12:36:52 [cgi-irc]
cgi-irc has joined #mmsem
12:37:28 [giovannit]
violence detection
12:37:42 [giovannit]
now presenting the BOEMIE project
12:41:17 [giovannit]
low level methodologies are improoving but high level annotation extraction is still difficult, the use of ontologies to drive the information extraction process seem very interesting
12:46:08 [jacco]
BOEMIE is, and other slides will be, published at
12:49:24 [giovannit]
Among the aspects involved in this projects are semantically annotated maps, evolving ontologies and fusion of different aspects of multimedia metadata
12:49:35 [giovannit]
12:52:13 [giovannit]
a use case/query is presented merging all the aspects covered by the project.
12:56:05 [giovannit]
raphael: there are other EU proejcts which have similar goals ,what ar ethe differences?
12:56:56 [giovannit]
ioannis: BOEMIE is concerned with multimodal metadata , to the best of my knowledge there is not much overlap with the other projects
12:58:43 [giovannit]
question: at which level is the fusion actually going to happen
12:59:14 [giovannit]
ioannis: the fusion is going to be supported by reasoning. Mid level concepts will be constructed and reasoning mechanism will take the decisions about the high level concepts
13:01:33 [yannis]
yannis has joined #mmsem
13:01:59 [giovannit]
ioannis: another novel concept is that the semantic extraction is knowledge driven, using an ontology
13:03:33 [giovannit]
vassalis presenting
13:03:54 [giovannit]
13:05:05 [giovannit]
toward a common multimedia ontology framework: initiative started a few months ago , a framework for collecting existing metadata knowledge reppresentation , an approach for harmonization..
13:05:48 [giovannit]
13:08:52 [giovannit]
In the first phase of this initiative, a number of requirements were collected
13:10:24 [giovannit]
reasoning support needs rules and DL based methoodologies but also uncertainty and fuzzyness
13:11:16 [giovannit]
modularization is agreed to be an important feature. Smaller ontologies which are reusable, specific and interoperable
13:13:51 [rellero_]
rellero_ has joined #mmsem
13:15:31 [giovannit]
there is the need of a upper ontology "merging" or "harmonization". In general some practical way for interoperability since people are using different ones.
13:17:10 [giovannit]
a semi automatic image annotation tool is shown. Automatic image segmentation helps a human operator to associate ontology labels (shown as a tree)
13:23:22 [JeffP]
13:24:45 [jacco]
rrsagent, draft minutes
13:24:45 [RRSAgent]
I have made the request to generate jacco
13:25:26 [jacco]
ack jeffp
13:26:00 [jacco]
13:28:18 [Massimo]
about the possible use case on algorithms..
13:28:29 [Massimo]
Currently we have sets of tools to extract features from multimedia objects:
13:28:29 [Massimo]
a set of rules can be defined able to establish which tools could be
13:28:29 [Massimo]
combined and how (e.g. put in a pipeline).
13:28:29 [Massimo]
Considering for example image understanding problems (e.g. segmentation,
13:28:29 [Massimo]
analysis, ...),
13:28:37 [Massimo]
a thesaurus containing related concepts and algorithm could be thought of.
13:28:37 [Massimo]
It would important to represent features on how metadata could be
13:28:37 [Massimo]
extracted so that it could be used at a higher level
13:28:37 [Massimo]
for images and multimedia information handling in general.
13:28:39 [Massimo]
Another important feature would be to take trace of how a specific
13:28:40 [Massimo]
result has been obtained starting from a particular input.
13:28:58 [Massimo]
A specific case of image elaboration:
13:28:58 [Massimo]
it is necessary to apply to the image a series of algorithms to
13:28:58 [Massimo]
calculate a property (region shapes, color distribution)
13:28:58 [Massimo]
The chain of algorithms defines a procedure that resolve the given problem.
13:29:04 [Massimo]
It would be interesting to 'store' the procedure - as an ordered set of
13:29:05 [Massimo]
algorithms - to add 'knowledge'
13:29:05 [Massimo]
to a system for interpretation and analysis.
13:29:10 [Massimo]
Once stored this procedure the knowledge increases and another problem
13:29:10 [Massimo]
could be resolved applying the procedures already inserted.
13:29:10 [Massimo]
Finally, this knowledge could be codified using an ontology that merges
13:29:10 [Massimo]
procedures and problems.
13:29:57 [jacco]
Giovanni: what about a formal cooperation between this XG and the requirements work started by aceMedia
13:30:03 [jacco]
13:30:37 [jacco]
Raphael: yes, we will. Yiannis will become a member.
13:35:02 [jacco]
Vassilis of NTUA presenting slides at via the telephone
13:36:22 [jacco]
Yiannis presenting slides at
13:38:06 [giovannit]
iannis speaking (NTUA) analisys of image and video content for automatic annotaion. A tool is shown for automatic segmentation, and manual region merging
13:38:39 [giovannit]
13:40:02 [jacco]
13:40:42 [jacco]
rrsagent, draft minutes
13:40:42 [RRSAgent]
I have made the request to generate jacco
13:44:16 [chalaschek]
chalaschek has joined #MMSEM
13:45:10 [jacco]
me: hi Chris
13:45:59 [VassilisTzouv]
Hi chris
13:46:30 [chalaschek]
Hi guys...time difference is quite difficult for me :(
13:46:41 [JeffP]
Hi Chris
13:46:42 [raphael]
hi Chris, welcome and thx for joining
13:47:04 [VassilisTzouv]
what time is now in maryland?
13:47:12 [chalaschek]
13:47:49 [chalaschek]
Are you guys on break now?
13:48:04 [jacco]
Show coffee break, start again in 5 minutes with Thomas presentation and DBin
13:49:43 [Zakim]
13:52:35 [rellero__]
rellero__ has joined #mmsem
13:53:24 [rellero__]
rellero__ has joined #mmsem
13:56:04 [jacco]
zakim, [UMD] is Chris Chalaschek
13:56:04 [Zakim]
I don't understand '[UMD] is Chris Chalaschek', jacco
13:56:24 [jacco]
zakim, '[UMD]' is Chris Chalaschek
13:56:24 [Zakim]
I don't understand ''[UMD]' is Chris Chalaschek', jacco
13:56:37 [jacco]
zakim, [UMD] is Chalaschek
13:56:37 [Zakim]
+Chalaschek; got it
13:58:50 [jacco]
Thomas presenting
14:16:01 [jacco]
giovanni presenting slides, will put online later
14:16:16 [JeffP]
14:16:44 [jacco]
slides are on distributed man/macine cooperative mm annotation
14:34:15 [jacco]
Topic: Discussion of "Image annotation on the Semantic Web" note:
14:36:49 [giovannit]
jacco gives an over view of the semantic web best practices and deployment working group
14:37:23 [raphael]
14:38:17 [raphael]
ACTION: ALL give comments on the "Image annotation on the Semantic Web" Working Draft
14:39:48 [yannis]
yannis has joined #mmsem
14:39:48 [raphael]
The deadline for the comments are 24/07/2006 !
14:41:18 [raphael]
schedule: finish this draft and get it published as a Working Group Note by SWBPD in the summer
14:41:27 [raphael]
give your comments now or never :-)
14:41:45 [raphael]
Maintain the resources pages: Overview, Tools, Vocabularies
14:41:56 [raphael]
In charge of this XG !
14:43:50 [jacco]
raphael mentions DOAP as an example of things we could do
14:45:44 [jacco]
Giovanni: what about a wiki?
14:46:17 [JeffP]
14:46:37 [raphael]
ACTION: raphael to see if the W3C wiki can be used to maintain these pages
14:47:29 [raphael]
Giovanni volunteer these pages
14:48:10 [JeffP]
ack me
14:49:28 [raphael]
Topic: Discussion of "Semantic Web Image Annotation Interoperability"
14:51:27 [raphael]
Jacco: this group should explore what is there and what could be improved
14:51:44 [raphael]
... W3C is concerned about what remains to be done in the multimedia domain
14:52:11 [raphael]
... needs for more industrial involvmen
14:52:17 [giovannit]
jacco says w3c is somehow puzzled about multimedia, tradeitionally being an ISO o MPEG-7 topic, but the topic of multimedia semantics is so clearly connected with the SW activity
14:52:22 [giovannit]
so w3c should probably do even more
14:52:26 [raphael]
14:53:00 [raphael]
14:53:13 [Zakim]
14:54:01 [Zakim]
14:57:22 [jacco]
giovanni: metric of what the advantage of using the semantic web is might also involve just lines of code, not only performance etc
14:58:00 [JeffP]
14:58:03 [VassilisTzouv]
14:58:34 [jacco]
Raphael: maybe interoperability deliverable should also be centered around clear use cases, not around the standards as it is now
14:59:18 [jacco]
jeff: are we talking about the deliverables in the charter?
14:59:25 [jacco]
Raphael: yes
14:59:51 [Zakim]
15:00:38 [Zakim]
15:00:46 [jacco]
Raphael: I'm not sure yet how many deliverables we are going to produce and it what order
15:00:51 [JeffP]
zakim, ??P11 is me
15:00:51 [Zakim]
+JeffP; got it
15:01:59 [jacco]
Raphael: The proposal includes to broaden the scope to other modalities, but focus on use cases
15:02:46 [jacco]
Vassilis: I agree to start from use cases, they do the same in RIF
15:03:30 [jacco]
giovanni: list of things we can do (semi) automatically, with some rating on how reliable this is
15:04:59 [Massimo]
i agree to Vassilis starting from use cases
15:05:33 [jacco]
so we know when to connect for example to social tagging for things we cannot do automatic
15:06:16 [jacco]
Ioannis: I think it is better to start from the use cases
15:06:26 [jacco]
Giovanni: but the two are very similar
15:07:06 [VassilisTzouv]
15:07:18 [jacco]
For example, if you have a music scenario, with a request for "similar" music, what do you mean by similar and what types of similarity can you do automatically?
15:08:13 [jacco]
Ioannis: but is a very broad question, use cases might focus discussion
15:09:05 [jacco]
Vassilis: what is the focus? interoperability or the reliability of the extracted metadata?
15:10:51 [jacco]
rrsagent, draft minutes
15:10:51 [RRSAgent]
I have made the request to generate jacco
15:12:12 [jacco]
Ioannis: stick to the existing use cases of the image annotation draft
15:12:30 [jacco]
Jacco: I would like to stick to the use cases discussed in the morning
15:13:43 [JeffP]
15:13:50 [jacco]
Raphael: we will discuss deadlines on the action points tomorrow
15:16:16 [raphael]
zakim, ack VassilisTzouv
15:16:16 [Zakim]
I see JeffP on the speaker queue
15:16:21 [JeffP]
ack me
15:17:33 [jacco]
for use cases discussed in the morning, see action points at
15:18:44 [rellero_]
rellero_ has joined #mmsem
15:20:17 [VassilisTzouv]
15:20:41 [raphael]
zakim, ack VassilisTzouv
15:20:41 [Zakim]
I see no one on the speaker queue
15:26:03 [JeffP]
Restaurant-Café In de Waag, Nieuwmarkt 4, 1012 CR Amsterdam
15:26:57 [chalaschek]
enjoy dinner everyone
15:27:02 [Zakim]
15:27:04 [Zakim]
15:27:08 [Zakim]
15:32:18 [Zakim]
15:32:19 [Zakim]
INC_MMSEM(F2F)3:00AM has ended
15:32:20 [Zakim]
Attendees were Jeff_Pan, meeting_room, Vassilis, Chalaschek, JeffP
15:32:20 [Massimo]
enjoy dinner and Amsterdam everyone !!! "see" you tomorrow
15:34:24 [pasquale]
15:37:45 [rellero_]
rellero_ has left #mmsem
15:38:54 [jacco]
rrsagent, draft minutes
15:38:54 [RRSAgent]
I have made the request to generate jacco
16:05:22 [Massimo]
Massimo has left #mmsem
16:07:05 [pasquale]
pasquale has left #mmsem
19:57:22 [Zakim]
Zakim has left #mmsem