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 entertainment, surveillance or medicine. Video search is a way to address a user’s information need, that is expressed as a query in textual or visual 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 retrieval, and technologies to understand how retrieval systems meet or fail to address the information needs, such as explainability of components of the retrieval system, active learning, etc. This workshop also addresses a specific application area of the emerging topic of fairness and explainability 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. Systems need to be able to understand these textual queries and retrieve videos within a database that satisfy these queries.

– Image/video queries can be used to find videos that contain similar scenes to the given image/video.

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

– Comparative analysis of performance of search systems on different datasets

– Fusion of computer vision, text/language processing and audio analysis for video search

– Evaluation protocols and metrics for assessing the impact of specific components of retrieval systems

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

– Failure analysis of query types, dataset characteristics, metrics, and system architectures

– Integrating user interaction in search systems and their impact on performance

– 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 datasets prepared by the workshop organizers, or on any available external datasets (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 period of 5 years. This amounts to 464 hours of video, and has available 230 instance search queries (visual examples of needed results) and the ground truth.

3. The new V3C1 Vimeo internet collection contains 1000 hours of video and is being used at the annual TRECVID international content-based video retrieval 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 given high priority with the goal to identify which methods work and which don’t, and why. Examples of such failure modes include, but are not limited to: easy vs hard queries, dataset characteristics, training data characteristics and its effect on solving easy/hard queries, behaviour of machine-learning based components, system architecture (e.g NN depth and attributes).

Submission

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

By submitting a manuscript to ICCV, authors acknowledge that it has not been 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 will be submitted to this or another conference, workshop, or journal during the review period. A publication, for the purposes of this policy, is defined 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 formal proceedings or whether the organizers declare that such work “counts as a publication”.

All submissions will be handled electronically via EasyChair: https://easychair.org/conferences/?conf=viral21

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)