22 citations · 43 across the 8 of their papers we have counts for
8 papers
HIRA: A Human-in-the-Loop Retrieval-Augmented Cascade for Document Classification in Regulated Industries
Shangxuan Tian, Yanhui Chen, Carlos Queiroz
Document classification in regulated industries is constrained by data residency, limited cold-start labels, scarce review capacity, and costly model-governance procedures. We pres…
CPN: Complementary Proposal Network for Unconstrained Text Detection
Longhuang Wu, Shangxuan Tian, Youxin Wang +1
Existing methods for scene text detection can be divided into two paradigms: segmentation-based and anchor-based. While Segmentation-based methods are well-suited for irregular sha…
Center Contrastive Loss for Metric Learning
Bolun Cai, Pengfei Xiong, Shangxuan Tian
Contrastive learning is a major studied topic in metric learning. However, sampling effective contrastive pairs remains a challenge due to factors such as limited batch size, imbal…
Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning
Peng Jin, Jinfa Huang, Pengfei Xiong +5
Contrastive learning-based video-language representation learning approaches, e.g., CLIP, have achieved outstanding performance, which pursue semantic interaction upon pre-defined…
Deep Self-Adaptive Hashing for Image Retrieval
Qinghong Lin, Xiaojun Chen, Qin Zhang +2
Hashing technology has been widely used in image retrieval due to its computational and storage efficiency. Recently, deep unsupervised hashing methods have attracted increasing at…
A pooling based scene text proposal technique for scene text reading in the wild
Dinh NguyenVan, Shijian Lu, Shangxuan Tian +2
Automatic reading texts in scenes has attracted increasing interest in recent years as texts often carry rich semantic information that is useful for scene understanding. In this p…
WeText: Scene Text Detection under Weak Supervision
Shangxuan Tian, Shijian Lu, Chongshou Li
The requiring of large amounts of annotated training data has become a common constraint on various deep learning systems. In this paper, we propose a weakly supervised scene text…
Text Flow: A Unified Text Detection System in Natural Scene Images
Shangxuan Tian, Yifeng Pan, Chang Huang +3
The prevalent scene text detection approach follows four sequential steps comprising character candidate detection, false character candidate removal, text line extraction, and tex…