Crossmodal Learning and Application

To contribute to the understanding of cross-modal technologies, we invite original articles in relevant topics, which include but are not limited to

• Multi modal representation/feature learning
• Cross-modal retrieval
• Data alignment across modalities, e.g., synchronising motion sensor with video
• Data translation, e.g., visually indicated sound
• Learning using side information, e.g., modality hallucination
• Knowledge transfer across modalities, e.g., zero-shot/few-shot learning
• Applications with cross-modal data inlcuding IoT (Internet of Things), operation and maintenance, surveillance, public transportation, logistics, health care, task-oriented dialog, human-robot interaction with vision and audio, user/product/job search and recommendation, social media retrieval and analysis etc.

We encourage submissions of both long and short papers.

Accepted long andshort papers will be designated as oral presentations and posters, respectively