[DBWorld] CfP - International Workshop on Video Retrieval Methods and Their Limits

Call for Papers =


2nd International Workshop on Video Retrieval Methods and Their Limits

at ICCV 2021, October 2021, online

=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D


With the vastly increasing amount of video data being created, searching in=
 video is a common task in many application areas, such as media and entert=
ainment, surveillance or medicine. Video search is a way to address a user=
=E2=80=99s information need, that is expressed as a query in textual or vis=
ual form, which is often only an approximation of the required information.=
 The proposed workshop is calling for contributions in content-based video =
search using different types of queries. Contributions may focus on search =
and retrieval methods, evaluation and benchmarking approaches for video ret=
rieval, and technologies to understand how retrieval systems meet or fail t=
o address the information needs, such as explainability of components of th=
e retrieval system, active learning, etc. This workshop also addresses a sp=
ecific application area of the emerging topic of fairness and explainabilit=
y of AI, in particular related to image/video analysis components.

Two possible types of queries may be:

- Natural language queries describing objects, actions, events, etc. System=
s need to be able to understand these textual queries and retrieve videos w=
ithin a database that satisfy these queries.

- Image/video queries can be used to find videos that contain similar scene=
s to the given image/video.

In this context, contributions related (but not limited) to the following t=
opics are invited.

- Comparative analysis of performance of search systems on different datase=
ts

- Fusion of computer vision, text/language processing and audio analysis fo=
r video search

- Evaluation protocols and metrics for assessing the impact of specific com=
ponents of retrieval systems

- Failure analysis of vision-based components in video search and retrieval=
 systems

- Failure analysis of query types, dataset characteristics, metrics, and sy=
stem architectures

- Integrating user interaction in search systems and their impact on perfor=
mance

- Approaches for measuring and predicting hardness/complexity of queries in=
 a system-independent way


Interested authors are invited to apply their approaches and methods on dat=
asets prepared by the workshop organizers, or on any available external dat=
asets (there is no competition component to the workshop).

The datasets prepared by the workshop organizers include:

1. Internet archives collection (IACC.3), which contains 600 hours of video=
, 90 ad-hoc queries and available ground truth.

2. BBC Eastenders dataset contains episodes of the weekly show over a perio=
d of 5 years. This amounts to 464 hours of video, and has available 230 ins=
tance search queries (visual examples of needed results) and the ground tru=
th.

3. The new V3C1 Vimeo internet collection contains 1000 hours of video and =
is being used at the annual TRECVID international content-based video retri=
eval evaluation benchmark and the video browser showdown beginning in 2019.=
 This dataset includes 50 textual queries and the ground truth.

Failure analysis of system performance is highly encouraged and will be giv=
en high priority with the goal to identify which methods work and which don=
=E2=80=99t, and why. Examples of such failure modes include, but are not li=
mited to: easy vs hard queries, dataset characteristics, training data char=
acteristics and its effect on solving easy/hard queries, behaviour of machi=
ne-learning based components, system architecture (e.g NN depth and attribu=
tes). =



Submission

We invite papers of up to 4 pages length (excluding references, but includi=
ng figures), formatted according to the ICCV template (http://iccv2019.thec=
vf.com/files/iccv2019AuthorKit.zip). Submissions shall be single blind, i.e=
. do not need to be anonymized. The workshop proceedings will be archived i=
n the IEEE Xplore Digital Library and the CVF Open Access.

By submitting a manuscript to ICCV, authors acknowledge that it has not bee=
n previously published or accepted for publication in substantially similar=
 form in any peer-reviewed venue including journal, conference or workshop.=
 Furthermore, no publication substantially similar in content has been or w=
ill be submitted to this or another conference, workshop, or journal during=
 the review period. A publication, for the purposes of this policy, is defi=
ned to be a written work longer than four pages (excluding references) that=
 was submitted for review by peers for either acceptance or rejection, and,=
 after review, was accepted. In particular, this definition of publication =
does not depend upon whether such an accepted written work appears in a for=
mal proceedings or whether the organizers declare that such work =E2=80=9Cc=
ounts as a publication=E2=80=9D.

All submissions will be handled electronically via EasyChair: https://easyc=
hair.org/conferences/?conf=3Dviral21


Important Dates

Workshop paper submission : July 27, 2021

Notification to authors : August 10, 2021

Workshop camera-ready  : August 17, 2021

Workshop date: October, 2021 (during ICCV)
_______________________________________________
Please do not post msgs that are not relevant to the database community at =
large.  Go to www.cs.wisc.edu/dbworld for guidelines and posting forms.
To unsubscribe, go to https://lists.cs.wisc.edu/mailman/listinfo/dbworld