Results‎ > ‎

Call for papers


JMLR Special Topic on Gesture Recognition


Third call for papers
Deadline December 15, 2012


The Journal of Machine Learning Research announces a special topic on gesture recognition.
Papers relevant to this topic may be submitted to the journal. Please also send email to the guest Editors with your paper number at  gestureclopinet . com. 

The participants of the CHALEARN Gesture Challenge are strongly encouraged to submit a paper. 

We also invite other contributions relevant to gesture recognition, including:
-    Algorithms for gesture and activity recognition, in particular addressing
    o    Learning from unlabeled or partially labeled data
    o    Learning from few examples per class, and transfer learning.
    o    Continuous gesture recognition and segmentation
    o    Deep learning architectures, including convolutional neural networks
    o    Gesture recognition in challenging scenes, including cluttered/moving backgrounds or moving cameras, or scenes where multiple persons are present.
    o    Integrating information from multiple channels (e.g., position/motion of multiple body parts, hand shape, facial expressions).
-    Data representations
-    Applications pertinent to the workshop topic, such as involving:
    o    Video surveillance
    o    Image or video indexing and retrieval
    o    Recognition of sign languages for the deaf
    o    Emotion recognition and affective computing
    o    Computer interfaces
    o    Virtual reality
    o    Robotics
    o    Ambiant intelligence
    o    Games
-    Datasets and benchmarks

The papers of the special topic of JMLR will also be reprinted as a book in the CiML series of Microtome.

Guest Editors: Isabelle Guyon and Vassilis Athitsos

gestureclopinet . com. 


Recommendations to competitors invited to write a JMLR paper:

JMLR is a very selective publication and your paper will undergo a regular journal review. 

Your chances of acceptance will be increased if:
- You clearly motivate your approach from a practical and theoretical standpoint
- You present a consistent set of experiments (using the development data) showing a significant advantage over other methods
- You cite your final evaluation results in the challenge (which will become available soon)
- You make sure that your paper is well organized, well written, with good references, figures, and tables.

We recommend not to exceed 20 pages.