ImageCLEF

Multimedia Retrieval in CLEF https://lnkd.in/dWPcdbzb:
(new) medical dialogue topic classification and summarization https://lnkd.in/dXXKFmY8
(new) visual question/question location answering, and generation in colonoscopy images https://lnkd.in/ddiTvtfj
(new) traceability of training data in synthetic medical image generation with GANs https://lnkd.in/dgeKRtBW
(7th edition) concept detection and caption prediction https://lnkd.in/deVKs4kP
(new) meaningful and diverse recommendations of articles and editorials from Europeana data https://lnkd.in/dMve8N6V
(3rd edition) automatic classification of photographic social media user profiles in unintended scenarios https://lnkd.in/diyS6aUG
(2nd edition) late fusion mechanisms and ensembling in interestingness prediction, search results diversification, and image captioning https://lnkd.in/d2PVWZri
is due May 10, 2023 --- AI4Media Universitatea POLITEHNICA din București AIMultimediaLab HES-SO.

special session on "Learning from scarce data challenges in the media domain" https://cbmi2022.org/call-for-special-session-papers/ -from-scarce-data @ 19th International Conference on Content-based Multimedia Indexing (CBMI 2022) AI4Media. Papers are due 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.