posted by organizer: trecvid || 1761 views || tracked by 3 users: [display]

DVU-Challenge 2020 : Deep Video Understanding - ACM MM Grand Challenge

FacebookTwitterLinkedInGoogle

Link: https://sites.google.com/view/dvuchallenge2020
 
When Oct 12, 2020 - Oct 16, 2020
Where Seattle, USA
Submission Deadline Jul 13, 2020
Notification Due Jul 27, 2020
Final Version Due Aug 10, 2020
Categories    multimedia understanding   computer vision   knowledge graph   multimedia queries
 

Call For Papers

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) 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 new challenge 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, 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.
Challenge Overview:

Interested participants are invited to apply their approaches and methods on a novel High-Level Video Understanding (HLVU) dataset being made available by the challenge organizers. These include 10 movies with a Creative Commons license. The dataset will be annotated by human assessors and ground truth (Ontology of relations, entities, actions & events, names and images of all main characters, and Knowledge Graph for 50% of the movies) provided to participating researchers for training and development of their systems. The organizers will support evaluation and scoring of three main query types distributed with the dataset (please refer to the dataset webpage for more details):

- 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.

Important Dates

HLVU movie dataset available including preliminary annotations: March 31, 2020
Complete HLVU annotations and development data available: April, 24
Testing queries released: May 29, 2020
Run submissions due to organizers: July 13, 2020
Paper submission deadline: July 13, 2020
Results released back to participants: July 27, 2020
Notification to authors: July 27, 2020
Workshop camera-ready submission: August 10, 2020
ACM Multimedia dates: October 12 - 16, 2020

Related Resources

TRECVID 2021   TREC Video Retrieval Evaluation
JCRAI 2021   2021 International Joint Conference on Robotics and Artificial Intelligence (JCRAI 2021)
IEEE COINS 2021   AI ML Big Data Vision Track | Artificial Intelligence | Machine Learning | Deep Learning | Machine Vision | Big Data Analytics | Video Analytics
ICCV 2021   International Conference on Computer Vision
MM 2021   The 29th ACM International Conference on Multimedia
EI-CCVPR 2021   2021 4th International Joint Conference on Computer Vision and Pattern Recognition (CCVPR 2021)
MIUA 2021   MEDICAL IMAGE UNDERSTANDING AND ANALYSIS
MECHATROJ 2021   Mechatronics and Applications: An International Journal (MECHATROJ)
CLIC 2021   CVPR 2021- Workshop and Challenge on Learned Image Compression
MVA 2021   17th International Conference on Machine Vision Applications