posted by organizer: gamato || 270 views || tracked by 2 users: [display]

Learning from Scarce Data 2022 : CBMI Special Session: Learning from scarce data challenges in the media domain


When Sep 14, 2022 - Sep 16, 2022
Where Graz, Austria
Submission Deadline Apr 10, 2020
Categories    artificial intelligence   learning from scarce data

Call For Papers

Special session on "Learning from scarce data challenges in the media domain"
(in conjunction with CBMI 2022, September 14-16, Graz, Austria)

Contact: Hannes Fassold, JOANNEUM RESEARCH,
Paper deadline: April 10, 2022

Deep learning-based algorithms for multimedia content analysis need a large amount of annotated data for effective training, e.g., for image classification on the ImageNet dataset, each class comprises several thousand annotated samples. Having a dataset of insufficient size for training usually leads to a model which is prone to overfitting and performs poorly in practice. But in many real-world applications in multimedia content analysis, it is not possible or not viable to gather and annotate such a large training data. This may be due to the prohibitive cost of human annotation, ownership/copyright issues of the data, or simply not having enough media content of a certain kind available.

To address this issue, a lot of research has been performed in recent years on learning from scarce data/learning from limited data. There are a variety of ways to work around the problem of data scarcity like using transfer learning, domain transfer or few-shot learning.

The special session on “Learning from scarce data” aims to provide a forum for novel approaches on learning from scarce data for multimedia content analysis, with a focus on the media domain.

The topics of interest include, but are not limited to:

-Transfer learning
-Synthetic data generation
-Domain transfer/adaptation
-Semi-supervised and self-supervised learning, e.g. to take advantage of large amounts of unlabeled media archive content
-Few-shot learning (classification, object detection etc.), which is useful e.g. for adding new object classes to an automatic tagging engine for media archive content.
-Benchmarking and evaluation frameworks for content from the media domain
-Open resources, e.g., software tools for learning from scarce data in the media domain

Session Organisers:
-Dr. Giuseppe Amato, CNR-ISTI, Pisa
-Prof. Bogdan Ionescu, AI Multimedia Lab, Politehnica University of Bucharest, Romania
-Hannes Fassold, JOANNEUM RESEARCH, Graz

Related Resources

MLDM 2023   18th International Conference on Machine Learning and Data Mining
ICDM 2022   22nd IEEE International Conference on Data Mining
IEEE SSCI 2023   2023 IEEE Symposium Series on Computational Intelligence
CFMAI 2022   2022 4th International Conference on Frontiers of Mathematics and Artificial Intelligence (CFMAI 2022)
Smart Cities 2022   Smart Cities: Urban Profiling with Artificial Intelligence and Big Data
FAIML 2022   2022 International Conference on Frontiers of Artificial Intelligence and Machine Learning (FAIML 2022)
IncrLearn 2022   Incremental classification and clustering, concept drift, novelty detection, active learning in big/fast data context
EI-CFAIS 2022   2022 International Conference on Frontiers of Artificial Intelligence and Statistics (CFAIS 2022)
MDPI mathematics 2022   From Edge Devices to Cloud Computing and Datacenters: Emerging Machine Learning Applications, Algorithms, and Optimizations
IEEE Big Data - MMBD 2022   IEEE Big Data 2022 Workshop on Multimodal Big Data