High quality error-tolerant phrase mining on text corpus

Wang, Jiaying; Shan, Jing; Santos, Odafen Ehiaribho; Bao, Jinling

doi:10.1016/j.eswa.2020.114557

Search citation statements

Order By: Relevance

Paper Sections

Select...

System Mechanism1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2024

Publication Types

Select...

Book2

Article1

Relationship

Self Cite0

Independent3

Authors

Journals

Cited by 3 publications

(1 citation statement)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, we used the pre-trained model CLIP (Radford et al 2021) as an image feature extractor to obtain image features. Second, we use ViT (Dosovitskiy et al 2021), high quality phrases (Wang et al 2021) and image library to build a knowledge base that contains a large number of fine-grained semantic labels, such as "Nordic style" and "soft decoration living room". Finally, we calculate similarity between image features and semantic labels in the knowledge base to get product labels.…”

Section: System Mechanismmentioning

confidence: 99%

Visual Language – Let the Product Say What You Want

Wang,

Hao,

Shan

et al. 2024

AAAI

View full text Add to dashboard Cite

Visual Language is a multitasking on-line system focusing on e-commerce, which involves in generating accurate product descriptions for sellers and providing convenient product retrieval service for customers. To achieve this goal, the system adopts image description technology and multi-modal retrieval technology. By utilizing cross-modal generation technique, we could help sellers on rapid uploading products and customers on rapid retrieval, which could improve the experience of both sellers and customers.

show abstract

Section: System Mechanismmentioning

confidence: 99%