Picture for Jiahong Li

Jiahong Li

FlowText: Synthesizing Realistic Scene Text Video with Optical Flow Estimation

Add code
May 05, 2023
Viaarxiv icon

A Large Cross-Modal Video Retrieval Dataset with Reading Comprehension

Add code
May 05, 2023
Viaarxiv icon

ICDAR 2023 Video Text Reading Competition for Dense and Small Text

Add code
Apr 10, 2023
Viaarxiv icon

Audience Expansion for Multi-show Release Based on an Edge-prompted Heterogeneous Graph Network

Add code
Apr 08, 2023
Viaarxiv icon

Real-time End-to-End Video Text Spotter with Contrastive Representation Learning

Add code
Jul 18, 2022
Figure 1 for Real-time End-to-End Video Text Spotter with Contrastive Representation Learning
Figure 2 for Real-time End-to-End Video Text Spotter with Contrastive Representation Learning
Figure 3 for Real-time End-to-End Video Text Spotter with Contrastive Representation Learning
Figure 4 for Real-time End-to-End Video Text Spotter with Contrastive Representation Learning
Viaarxiv icon

Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofing

Add code
Mar 18, 2022
Figure 1 for Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofing
Figure 2 for Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofing
Figure 3 for Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofing
Figure 4 for Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofing
Viaarxiv icon

Contrastive Learning of Semantic and Visual Representations for Text Tracking

Add code
Dec 30, 2021
Figure 1 for Contrastive Learning of Semantic and Visual Representations for Text Tracking
Figure 2 for Contrastive Learning of Semantic and Visual Representations for Text Tracking
Figure 3 for Contrastive Learning of Semantic and Visual Representations for Text Tracking
Figure 4 for Contrastive Learning of Semantic and Visual Representations for Text Tracking
Viaarxiv icon

A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer

Add code
Dec 09, 2021
Figure 1 for A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer
Figure 2 for A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer
Figure 3 for A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer
Figure 4 for A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer
Viaarxiv icon

Consistency Regularization for Deep Face Anti-Spoofing

Add code
Nov 25, 2021
Figure 1 for Consistency Regularization for Deep Face Anti-Spoofing
Figure 2 for Consistency Regularization for Deep Face Anti-Spoofing
Figure 3 for Consistency Regularization for Deep Face Anti-Spoofing
Figure 4 for Consistency Regularization for Deep Face Anti-Spoofing
Viaarxiv icon

Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detection

Add code
Mar 16, 2021
Figure 1 for Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detection
Figure 2 for Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detection
Figure 3 for Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detection
Figure 4 for Frequency-aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detection
Viaarxiv icon