Self-Supervised Video Similarity Learning
AdaCC: cumulative cost-sensitive boosting for imbalanced classification
VICTOR: Visual Incompatibility Detection with Transformers and Fashion-specific contrastive pre-training
Leveraging Large-scale Multimedia Datasets to Refine Content Moderation Models
Multimodal Quasi-AutoRegression: Forecasting the visual popularity of new fashion products
pygrank: A Python package for graph node ranking
COVID-Related Misinformation Migration to BitChute and Odysee
A survey on bias in visual datasets
DnS: Distill-and-select for efficient and accurate video indexing and retrieval
Novel Paradigms of Human-Fashion Interaction