ACM SIGMM Interest List


Options: Use Forum View

Use Monospaced Font
Show Text Part by Default
Show All Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
Martha Larson - EWI <[log in to unmask]>
Reply To:
Martha Larson - EWI <[log in to unmask]>
Mon, 29 Apr 2019 21:36:12 +0000
text/plain (68 lines)
MediaEval 2019: Multimedia Research Challenges
Register now: Data releases are beginning
Last day for regular registration: 30 June

MediaEval (Benchmarking Initiative for Multimedia Evaluation) offers shared-tasks to the multimedia research community involving images, text, video, music and speech. The tasks address cutting-edge multimedia challenges (multimedia mining, retrieval, analysis, access and exploration) with a clear human or social aspect. Our larger aim is to promote reproducible research that makes multimedia a positive force for society.

Further information and the link for registration to participate in the tasks is available at:
Short descriptions of the 2019 tasks are below. 

The MediaEval 2019 Workshop will take place 27-29 October 2019 near Nice, France. (The workshop is scheduled so that participants can combine the workshop with attendance at ACM Multimedia in one trip, if they wish.)

Emotion and Theme recognition in music using Jamendo
Recognize emotions and themes conveyed in music recordings (large-scale data set). 

Eyes and Ears Together: Multimodal coreference resolution
Analyze videos to predict bounding boxes corresponding to nouns and pronouns in the videos’ speech transcripts.

GameStory: Video Game Analytics Challenge
Analyze game streams (including audio and video streams, commentaries, game data and statistics, interaction traces, viewer-to-viewer communication) to carry out synchronization and event detection.

Insight for Wellbeing: Multimodal personal health lifelog data analysis
Analyze lifelogs (lifelog images, user-contributed tags, sensor readings, weather/pollution information) to automatically make well-being related predictions.

Medico Medical Multimedia
Analyze a multimodal dataset (videos, analysis data, study participant data) to make predictions related to sperm quality.

Multimedia Recommender Systems
Participants can choose between one of two tasks that investigate the use of multimedia content for recommendation.

Multimedia Satellite Task: Flood Severity Estimation
Analyze news reports (images/text) and/or satellite images for information important for disaster management.

No-audio Multimodal Speech Detection
Participants receive videos (top view) and sensor readings (acceleration and proximity) of people having conversations in a natural social setting and are required to detect speaking turns.

Pixel Privacy
Participants receive a set of images and are required to enhance them in a way that blocks automatic inference of sensitive information, while preserving image appeal. See:

Predicting Media Memorability
Given a data set of multimedia content (images and/or videos) and associated memorability annotations, automatically train a system to predict memorability.

Scene Change (Brave New Task)
Automatically create fun faux photo’s, composite images that fool you at first, but can be identified as an imitation on closer inspection. 

Sports Video Annotation: Detection of Strokes in Table Tennis (Brave New Task)
Automatically classify strokes in videos of table tennis.

NewsFire: Discovering the triggers for viral news stories (Task force)
Participants receive a large corpus of news stories and social media posts (text and images) and are required to build a system that detects the original triggers of news that spread with a viral or wildfire pattern. 

For more information on the mission of MediaEval check out the videos and proceedings from previous workshops, e.g.,

If you have further questions, please contact: Martha Larson [log in to unmask]