Kai Hu

papers

316

total citations

papers (12)

Text to Image Generation With Semantic-Spatial Aware GAN

CVPR 2022arXiv

160

citations

Enhanced Training of Query-Based Object Detection via Selective Query Recollection

CVPR 2023arXiv

citations

Self-supervised ControlNet with Spatio-Temporal Mamba for Real-world Video Super-resolution

CVPR 2025arXiv

citations

Completing Visual Objects via Bridging Generation and Segmentation

ICML 2024arXiv

citations

Explicit Relational Reasoning Network for Scene Text Detection

AAAI 2025arXiv

citations

Distilling Knowledge from Heterogeneous Architectures for Semantic Segmentation

AAAI 2025arXiv

citations

Contrast and Order Representations for Video Self-Supervised Learning

ICCV 2021

citations

Is normalization indispensable for training deep neural network?

NEURIPS 2020

citations

Kai Hu

papers (12)

Text to Image Generation With Semantic-Spatial Aware GAN

Enhanced Training of Query-Based Object Detection via Selective Query Recollection

M-LLM Based Video Frame Selection for Efficient Video Understanding

Empowering Graph Invariance Learning with Deep Spurious Infomax

Unlocking Deterministic Robustness Certification on ImageNet

Learning Graph Invariance by Harnessing Spuriosity

Self-supervised ControlNet with Spatio-Temporal Mamba for Real-world Video Super-resolution

Completing Visual Objects via Bridging Generation and Segmentation

Explicit Relational Reasoning Network for Scene Text Detection

Distilling Knowledge from Heterogeneous Architectures for Semantic Segmentation

Contrast and Order Representations for Video Self-Supervised Learning

Is normalization indispensable for training deep neural network?

papers (12)

Text to Image Generation With Semantic-Spatial Aware GAN

Enhanced Training of Query-Based Object Detection via Selective Query Recollection

M-LLM Based Video Frame Selection for Efficient Video Understanding

Empowering Graph Invariance Learning with Deep Spurious Infomax

Unlocking Deterministic Robustness Certification on ImageNet

Learning Graph Invariance by Harnessing Spuriosity

Self-supervised ControlNet with Spatio-Temporal Mamba for Real-world Video Super-resolution

Completing Visual Objects via Bridging Generation and Segmentation

Explicit Relational Reasoning Network for Scene Text Detection

Distilling Knowledge from Heterogeneous Architectures for Semantic Segmentation

Contrast and Order Representations for Video Self-Supervised Learning

Is normalization indispensable for training deep neural network?