Composed image retrieval (CIR) is a new and flexible image retrieval
par...
Multi-modal recommendation systems, which integrate diverse types of
inf...
Emotion distribution learning has gained increasing attention with the
t...
Existing work on Multimodal Sentiment Analysis (MSA) utilizes multimodal...
Dialogue disentanglement aims to detach the chronologically ordered
utte...
Textual response generation is an essential task for multimodal task-ori...
The last decade has witnessed the proliferation of micro-videos on vario...
The booming development and huge market of micro-videos bring new e-comm...
Knowledge Graph (KG), as a side-information, tends to be utilized to
sup...
Recommendation systems make predictions chiefly based on users' historic...
Visual Question Answering (VQA) is fundamentally compositional in nature...
Visual Commonsense Reasoning (VCR), deemed as one challenging extension ...
Recommender systems can automatically recommend users items that they
pr...
Recommending cold-start items is a long-standing and fundamental challen...
Personalized hashtag recommendation methods aim to suggest users hashtag...