TRECVID - IBM Team Response
- Subject: TRECVID - IBM Team Response
- From: "Belle L Tseng" <belle@us.ibm.com>
- Date: Fri, 15 Mar 2002 17:17:04 -0500
- Content-type: text/plain; charset=us-ascii
- Importance: Normal
Dear TRECVID,
On behalf of the IBM Team, I am posting our response to the following
issues.
>1) MPEG-1: At the workshop at TREC 2001 several groups indicated they
strongly
>preferred that the data be in MPEG-1, even if this meant transcoding from
e.g.,
>MPEG-2.
>
>===> Which groups feel this way?
>
>===> Does anyone object to an MPEG-1 only test collection? (Possibly with
> MPEG-2 available for display to humans.)
MPEG-1 is preferrable for us. We suggest that the TREC benchmark be
specified to operate on MPEG-1 only.
>2) Common shot definition:
>
>===> Does any one object strongly to using a common set of shot boundaries
for
> the search task?
>
>===> Which groups would volunteer to submit such a set for the total
search
> collection? NIST would blend these to form the final common set.
A common set of shot boundaries would allow for better comparison across
different retrieval systems.
We would be willing to volunteer our shot boundary results and make them
available for the retrieval track. However, we would like to clarify the
following timeline:
1) submission of volunteered shot boundary results for retrieval (date?)
2) availability of NIST common set of shot boundaries (date?)
3) submission of final boundaries for shot boundary detection track
(August?)
>3) Data distribution: Right now we see shipping IDE disk drives as the
only
>practical way of sending 90GBs. We could create a pool of at least 4 and
perhaps
>more drives, which we could FedEx to participants, who would copy the data
and
>return the disk. Alternatively, participants could send us an IDE drive,
which
>we could fill and return. Of course we have have some problems with drives
due
>to shipping...
>
>===> Anyone have a better idea?
>
>===> Assuming we use the IDE drives, how many current participants
>think they would ship us a drive to fill?
We have downloaded the available content via FTP already.
The IBM Team
Belle L. Tseng, Ph.D.
I.B.M. Watson Research Center
19 Skyline Drive
Hawthorne, NY 10532
(914) 784-7441 (voice)
(914) 784-7455 (fax)
belle@us.ibm.com
Date Index |
Thread Index |
Problems or questions? Contact list-master@nist.gov