MULWS20
* *Multimodal Learning and Applications
* Classification-aware Semi-supervised Domain Adaptation
* CPARR: Category-based Proposal Analysis for Referring Relationships
* Cross-modal Variational Alignment of Latent Spaces
* Exploring Phrase Grounding without Training: Contextualisation and Extension to Text-Based Image Retrieval
* Improved Active Speaker Detection based on Optical Flow
* Interactive Video Retrieval with Dialog
* Multi-modal Dense Video Captioning
* Quality and Relevance Metrics for Selection of Multimodal Pretraining Data
* Self-Supervised Object Detection and Retrieval Using Unlabeled Videos
10 for MULWS20