International Workshop and Competition on Action Recognition with a Large Number of Classes Call for Papers

THUMOS Challenge 2015
International Workshop and Competition on Action Recognition with a
Large Number of Classes
In conjunction with CVPR15, June 11, 2015, Boston, Massachusetts
http://www.thumos.info/
 
**ACTION RECOGNITION IN TEMPORALLY UNTRIMMED VIDEOS**
Automatically recognizing and localizing a large number of action
categories from videos “in the wild” is of significant
importance for video understanding and multimedia event detection. The
THUMOS workshop and challenge aims at exploring new challenges and
approaches for large-scale action recognition with large number of
classes from open source videos in a realistic setting.
 
Most existing action recognition datasets are composed of videos that
have been manually trimmed to bound the action of interest. This has
been identified to be a considerable limitation as it poorly matches
how action recognition is applied in practical settings. Therefore,
similar to last year’s challenge, THUMOS 2015 will conduct the
challenge on temporally untrimmed videos. The participants may train
their methods using trimmed clips but will be required to test their
systems on untrimmed data.
 
A forward-looking dataset composed of the following components will be
made available under this challenge:
 
    Training Set: over 13,000 temporally trimmed videos from 101 action classes.
    Validation Set: Over 2100 temporally untrimmed videos with
    temporal annotations of actions.

    Background Set: Approximately 3000 relevant videos guaranteed to
    not include any instance of the 101 actions.

    Test Set: Over 4000 temporally untrimmed videos with withheld ground truth.
 
All videos are collected from YouTube, and their pre-extracted
lowlevel features (e.g., Dense Trajectory Features, Improved DTF,
STIP, etc.) will be made available. We will evaluate the success of
the proposed methods based on their performance on the new THUMOS 2015
Dataset in two tasks:
 
    Action Classification: this task accepts submissions for
    whole-clip action classification on 101 action classes.
    Temporal Action Localization: this task accepts submissions on
    action recognition and temporal localization on a subset of 20
    action classes.
 
Participants may either submit a notebook paper that briefly describes
their system, or a research paper detailing their approach. All of the
submission results will be summarized during the workshop and included
in the workshop\conference proceedings. Additionally, the top
performers will be invited to give oral presentations, with remaining
entries encouraged to present their work in the poster session.
 
Important Dates:
    Development Kit Release (Training+Validation data, low-level
    features, and evaluation setup): April 2015
    Test Data Release: May 9, 2015
    Submission Deadline: May 23, 2015
    Challenge Results Notifications: May 30, 2015
    Publication date: As per conference schedule
    Workshop date: June 11, 2015
 
More information available at the workshop website: http://www.thumos.info/
 
Program Chairs:
Alexander Gorban, Google Research
Haroon Idrees, UCF
Yu-Gang Jiang, Fudan University
Amir R. Zamir, Stanford University
 
General Chairs:
Ivan Laptev, INRIA
Mubarak Shah, UCF
Rahul Sukthankar, Google Research