InfoBehavior: Self-supervised Representation Learning for Ultra-long Behavior Sequence via Hierarchical Grouping

no code implementations • 13 Jun 2021 • Runshi Liu, Pengda Qin, Yuhong Li, Weigao Wen, Dong Li, Kefeng Deng, Qiang Wu

Typically, the risk can be identified by jointly considering product content (e. g., title and image) and seller behavior.

feature selection Management +1

TVDIM: Enhancing Image Self-Supervised Pretraining via Noisy Text Data

no code implementations • 3 Jun 2021 • Pengda Qin, Yuhong Li, Kefeng Deng, Qiang Wu

Among ubiquitous multimodal data in the real world, text is the modality generated by human, while image reflects the physical world honestly.

Contrastive Learning Image Classification +1