Picture for Huijia Zhu

Huijia Zhu

DomainGallery: Few-shot Domain-driven Image Generation by Attribute-centric Finetuning

Add code
Nov 07, 2024
Viaarxiv icon

Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding

Add code
Sep 29, 2024
Viaarxiv icon

Stochastic Layer-Wise Shuffle: A Good Practice to Improve Vision Mamba Training

Add code
Aug 30, 2024
Viaarxiv icon

UNER: A Unified Prediction Head for Named Entity Recognition in Visually-rich Documents

Add code
Aug 02, 2024
Figure 1 for UNER: A Unified Prediction Head for Named Entity Recognition in Visually-rich Documents
Figure 2 for UNER: A Unified Prediction Head for Named Entity Recognition in Visually-rich Documents
Figure 3 for UNER: A Unified Prediction Head for Named Entity Recognition in Visually-rich Documents
Figure 4 for UNER: A Unified Prediction Head for Named Entity Recognition in Visually-rich Documents
Viaarxiv icon

DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmark

Add code
May 30, 2024
Viaarxiv icon

Supervised Contrastive Learning for Snapshot Spectral Imaging Face Anti-Spoofing

Add code
May 29, 2024
Viaarxiv icon

Conditional Prototype Rectification Prompt Learning

Add code
Apr 15, 2024
Viaarxiv icon

Boosting Audio-visual Zero-shot Learning with Large Language Models

Add code
Nov 21, 2023
Viaarxiv icon

Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction

Add code
Oct 17, 2023
Viaarxiv icon

ControlCom: Controllable Image Composition using Diffusion Model

Add code
Aug 19, 2023
Viaarxiv icon