The DVU development, testing datasets, and 2022 Queries are now available (please submit the data agreement to access testing dataset)
Deep video understanding is a difficult task which requires systems to develop a deep analysis and understanding of the relationships between different entities in video, to use known information to reason about other, more hidden information, and to populate a knowledge graph (KG) representation with all acquired information. To work on this task, a system should take into consideration all available modalities (speech, image/video, and in some cases text). The aim of this challenge series is to push the limits of multimodal extraction, fusion, and analysis techniques to address the problem of analyzing long duration videos holistically and extracting useful knowledge to utilize it in solving different types of queries. The target knowledge includes both visual and non-visual elements. As videos and multimedia data are getting more and more popular and usable by users in different domains and contexts, the research, approaches and techniques we aim to be applied in this Grand Challenge will be very relevant in the coming years and near future.
Interested participants are invited to apply their approaches and methods on an extended novel Deep Video Understanding (DVU) dataset being made available by the challenge organizers. The dataset is split into a development data of 14 movies from the 2020-2021 versions of this challenge with a Creative Commons licenses, and a new set of 10 movies licensed from KinoLorberEdu platform. 4 new movies out of the 10 will be added to the 14 movies, while 6 will be chosen as the testing data in 2022. The development data includes: original while videos, segmented scene shots, image examples of main characters and locations, movie-level KG representation of the relationships between main characters, relationships between characters key-locations, scene-level KG representation of each scene in a movie (location type, characters, interactions between them, order of interactions, sentiment of scene, and a short textual summary), and a global shared ontology of locations, relationships (family, social, work), interactions and sentiments.
The organizers will support evaluation and scoring for a hybrid of main query types, at the overall movie level and at the individual scene level distributed with the dataset. Participants will be given the choice to submit results for either the movie-level or scene-level queries, or both. And for each category, queries are grouped for more flexible submission options (please refer to the dataset webpage for more details):
Example Question types at Overall Movie Level:
Multiple choice question answering on part of Knowledge Graph for selected movies.
Possible path analysis between persons / entities of interest in a Knowledge Graph extracted from selected movies.
Fill in the Graph Space - Given a partial graph, systems will be asked to fill in the graph space.
Example Question types at Individual Scene Level:
Find next or previous interaction, given two people, a specific scene, and the interaction between them.
Find a unique scene given a set of interactions and a scene list.
Fill in the Graph Space - Given a partial graph for a scene, systems will be asked to fill in the graph space.
Match between selected scenes and set of scene descriptions written in natural language .
Scene sentiment classification.
A new addition to 2022 challenge is that systems will be asked to submit with their results for some queries a temporal segment from the movie or scene (e.g. using starting/ending timestamps) to act as an evidence for their answers. This requirement will be evaluated independently from the main scoring method and it's objective is to demonstrate if systems can explain their results and if they are submitting their answers for the correct reasons.
Run submission XML files should be emailed directly to Keith Curtis (keith.curtis@nist.gov), and CC to George Awad (george.awad@nist.gov). Please indicate ACMMM Grand Challenge in the subject line. Please refer to the Supported datasets page for XML sample queries, response files and DTD required (Please check regularly for latest updates about submission format) to follow when submitting your results.
Grand Challenge papers will go through a single-blind review process. (Author names and affiliations should be included.) Papers should be limited to 4 pages in length + up to 2 extra pages for references only. Please check the main ACMMM2022 conference website for further details.
Papers should be submitted directly via the main conference submission site: https://openreview.net/group?id=acmmm.org/ACMMM/2022/Track/Grand_Challenges
Each Grand Challenge Submitted paper should be formatted as 4-page short paper and will be included in the main conference proceeding.
DVU development data release: Available from This URL
Testing dataset release : Available now (Each team/group must first sign the data agreement form HERE before given access)
Testing queries release: Available now from THIS LINK (Please consult the README file)
Paper submission deadline: June 25, 2022
Submissions of solutions to organizers: June 28, 2022
Results released back to participants: July 6, 2022
Notification to authors: July 16, 2022
camera-ready submission: July 23, 2022
Grand Challenge at ACM Multimedia: October 12, 2022