1. Call for Papers

The ability to craft and understand stories is a crucial cognitive tool used by humans for communication. According to computational linguists, narrative theorists and cognitive scientists, story understanding is a good proxy to measure the readers' intelligence. Readers can understand a story as a way of problem-solving in which, for example, they keep focusing on how main characters overcome certain obstacles throughout the story. Readers need to make inferences both in prospect and in retrospect about the causal relationships between different events in the story.

Video story data such as TV shows and movies can serve as an excellent testbed to evaluate human-level AI algorithms from two points of view. First, video data has different modalities such as a sequence of images, audio (including dialogue, sound effects and background music) and text (subtitles or added comments). Second, video data shows various cross-sections of everyday life. Therefore, understanding video stories can be thought of as a significant challenge to current AI technology, which involves analyzing and simulating human vision, language, thinking, and behavior.

This workshop aims to invite experts from various fields, including vision, language processing, multimedia, and speech recognition, to provide their perspective on existing research, and initiate discussion on future challenges in data-driven video understanding. To assess current state-of-the-art methodologies and encourage rapid progress in the field, we will also host a challenge based on the DramaQA dataset, which encourages story-centered video question answering. Topics of interest include but are not limited to:

  • Deep learning architectures for multi-modal video story representation
  • Question answering for video stories
  • Summarization and retrieval from long story video contents
  • Scene description generation for video understanding
  • Activity/event recognition from video
  • Character identification & interaction modeling in video
  • Scene graph generation and relationship detection from video
  • Emotion recognition in video
  • Novel tasks about video understanding and challenge dataset

  • This workshop will invite leading researchers from various fields. Also, we encourage submissions of papers as archival and non-archival tracks. All accepted papers will be presented as posters during the workshop and listed on the website. Additionally, a small number of accepted papers will be selected to be presented as contributed talks.


    Submission Instructions

    Note that we provide both an archival and non-archival tracks. All submissions will be handled through CMT, at this CMT link.

  • Archival full paper track (up to 14 pages excluding references): The submission must be no longer than 14 pages (excluding references). All submissions must be in pdf format as a single file (incl. supplementary materials) using this ECCV’20 template. Accepted papers in this track will be published in the ECCV’20 workshop proceedings. The review process is single-round and double-blind. All submissions in this track have to be anonymized.
  • Non-archival short paper track (up to 4 pages including references) : The submission must be no longer than 4 pages (including references). All submissions must be in pdf format as a single file (incl. supplementary materials) using this ECCV’20 template. Accepted papers in this track will not be published in the ECCV’20 workshop proceedings. Also, non-archival short paper submissions can share contents with a paper under review for ECCV’20 (or any other conference). That is, this track will not conflict with the dual submission policy of ECCV’20. The review process is single-round and double-blind. All submissions in this track have to be anonymized.
  • Non-archival long paper track (for published papers from previous conferences) : This track is only for previously published papers, or papers set to appear in the main ECCV’20 conference. There is no page limit and no submission template. Accepted papers in this track will not be published in ECCV workshop proceedings. All submissions in this track do not need to be anonymized.

  • 2. Challenge: DramaQA Challenge

    Please see the challenge page for details.


    3. Important Dates

  • Signup to receive updates: Link
  • Paper submission deadline: July 10, 2020 at 11:59pm (PST)
  • Notification to authors: July 22, 2020
  • Camera-Ready Paper submission deadline: August 12, 2020 at 11:59pm (PST)
  • Workshop date: August 28, 2020 (Full day)


  • 4. Organizers

    person
    Yu-Jung Heo
    Seoul National University
    person
    Seongho Choi
    Seoul National University
    person
    Kyoung-Woon On
    Seoul National University
    person
    Minsu Lee
    Seoul National University
    person
    Vicente Ordonez
    University of Virginia
    person
    Leonid Sigal
    University of British Columbia
    person
    Chang Dong Yoo
    KAIST
    person
    Gunhee Kim
    Seoul National University
    person
    Marcello Pelillo
    University of Venice
    person
    Byoung-Tak Zhang
    Seoul National University


    Back to top

    © 2020 Video Intelligence Center @ Seoul National University