Long Zhao

Affiliations

Google DeepMind

papers

1,624

total citations

papers (19)

Learning to Learn Single Domain Generalization

CVPR 2020arXiv

517

citations

Are Multimodal Transformers Robust to Missing Modality?

CVPR 2022arXiv

227

citations

Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness

NEURIPS 2020arXiv

185

citations

Knowledge As Priors: Cross-Modal Knowledge Generalization for Datasets Without Superior Knowledge

CVPR 2020arXiv

citations

Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning

ECCV 2022arXiv

citations

Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization

CVPR 2021arXiv

citations

COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality

ECCV 2022arXiv

citations

Learning from Semantic Alignment between Unpaired Multiviews for Egocentric Video Recognition

ICCV 2023arXiv

citations

Taming Self-Training for Open-Vocabulary Object Detection

CVPR 2024arXiv

citations

Distilling Vision-Language Models on Millions of Videos

CVPR 2024arXiv

citations

Generating Enhanced Negatives for Training Language-Based Object Detectors

CVPR 2024arXiv

citations

Unified Visual Relationship Detection with Vision and Language Models

ICCV 2023arXiv

citations

Open-Vocabulary 3D Semantic Segmentation with Text-to-Image Diffusion Models

ECCV 2024arXiv

citations

MINES: Message Intercommunication for Inductive Relation Reasoning over Neighbor-Enhanced Subgraphs

AAAI 2024

citations

Sample-Level Cross-View Similarity Learning for Incomplete Multi-View Clustering

AAAI 2024

citations

Long Zhao

Affiliations

papers (19)

Learning to Learn Single Domain Generalization

Are Multimodal Transformers Robust to Missing Modality?

Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness

Exploiting Unlabeled Data with Vision and Language Models for Object Detection

Improved Transformer for High-Resolution GANs

Global Matching With Overlapping Attention for Optical Flow Estimation

VideoPrism: A Foundational Visual Encoder for Video Understanding

Knowledge As Priors: Cross-Modal Knowledge Generalization for Datasets Without Superior Knowledge

Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning

Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization

COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality

Learning from Semantic Alignment between Unpaired Multiviews for Egocentric Video Recognition

Taming Self-Training for Open-Vocabulary Object Detection

Distilling Vision-Language Models on Millions of Videos

Generating Enhanced Negatives for Training Language-Based Object Detectors

Unified Visual Relationship Detection with Vision and Language Models

Open-Vocabulary 3D Semantic Segmentation with Text-to-Image Diffusion Models

MINES: Message Intercommunication for Inductive Relation Reasoning over Neighbor-Enhanced Subgraphs

Sample-Level Cross-View Similarity Learning for Incomplete Multi-View Clustering

papers (19)

Learning to Learn Single Domain Generalization

Are Multimodal Transformers Robust to Missing Modality?

Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness

Exploiting Unlabeled Data with Vision and Language Models for Object Detection

Improved Transformer for High-Resolution GANs

Global Matching With Overlapping Attention for Optical Flow Estimation

VideoPrism: A Foundational Visual Encoder for Video Understanding

Knowledge As Priors: Cross-Modal Knowledge Generalization for Datasets Without Superior Knowledge

Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning

Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization

COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality

Learning from Semantic Alignment between Unpaired Multiviews for Egocentric Video Recognition

Taming Self-Training for Open-Vocabulary Object Detection

Distilling Vision-Language Models on Millions of Videos

Generating Enhanced Negatives for Training Language-Based Object Detectors

Unified Visual Relationship Detection with Vision and Language Models

Open-Vocabulary 3D Semantic Segmentation with Text-to-Image Diffusion Models

MINES: Message Intercommunication for Inductive Relation Reasoning over Neighbor-Enhanced Subgraphs

Sample-Level Cross-View Similarity Learning for Incomplete Multi-View Clustering