Call for Papers
The integration of Computer Vision (CV) and Natural Language Processing (NLP) is
significantly transforming the field of AI. The combination of LLM and CV is paving the way for AI systems to
understand and generate multi-modal content. Text-guided multi-modal generation is one of
the areas that has been significantly advanced thanks to the evolution of both LLM and CV,
where the core challenge of the text-guided generation is the visual-language (VL) alignment.
This is the 1st TMMG workshop to be held in conjunction with ICME 2024 in Niagra Falls, Canada.
We aim to bring together researchers from the fields of image, video,
audio generations as well as NLP to facilitate discussions and progress at
the intersection of the LLMs/LMMs and multi-modal content generation.
We aim to invite a diverse set of experts to discuss their recent research results
and future directions for the text-guided multi-modal generation, with a particular focus on improving the visual-language alignment in text-
guided generation.
We warmly welcome contributions concerning text-guided generation,
LLMs/LMMs for multi-modal generation, and visual-language alignment analysis.
The topics of interest include (but are not limited to):
-
Advances in text-guided image/video/audio/multi-modal generation
-
Visual-language alignment analysis
-
LLM/LMM and text-guided generation
-
Self-supervised learning with generative models
-
Adversarial attacks and defenses with generative models
-
Novel evaluation metrics and methods
-
Benchmark datasets
-
Ethical considerations and bias in text-guided visual generation
-
Augmented and virtual reality applications
-
Accessibility in multimedia content
-
Impact of multi-modal generation on media and Journalism
Paper Submission
Authors should prepare their manuscript according to the Guide for Authors of ICME available at Author Information and Submission Instructions.
Submission address: https://cmt3.research.microsoft.com/ICME2024W
Workshop Track: TMMG
Submit link
