Deep Video Understanding
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.
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. This includes total of 14 movies with a Creative Commons license. The dataset are annotated by human assessors and final ground truth, both at the overall movie level (Ontology of relations, entities, actions & events, Knowledge Graph, and names and images of all main characters), and the individual scene level (Ontology of relationships, interactions, locations, scene sentiments, character emotional states, and scene textual summaries) will be provided for 70% of the dataset to participating researchers for training and development of their systems. 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 (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.
- Classify scene sentiment.