Bowen Zhang

Affiliations

University of Southern California

papers

3,141

total citations

papers (20)

MetaPortrait: Identity-Preserving Talking Head Generation With Fast Personalized Adaptation

CVPR 2023arXiv

citations

MetaDiff: Meta-Learning with Conditional Diffusion for Few-Shot Learning

AAAI 2024arXiv

citations

Dynamic Token Pruning in Plain Vision Transformers for Semantic Segmentation

ICCV 2023arXiv

citations

Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Pre-training Framework

CVPR 2024arXiv

citations

STIV: Scalable Text and Image Conditioned Video Generation

ICCV 2025arXiv

citations

Dynamic Neural Representational Decoders for High-Resolution Semantic Segmentation

NEURIPS 2021arXiv

citations

MMEgo: Towards Building Egocentric Multimodal LLMs for Video QA

ICLR 2025

citations

Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis

ICCV 2025arXiv

citations

MOFI: Learning Image Representations from Noisy Entity Annotated Images

ICLR 2024arXiv

citations

Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Models

ICLR 2025arXiv

citations

Adapting to Observation Length of Trajectory Prediction via Contrastive Learning

CVPR 2025

citations

WildlifeMapper: Aerial Image Analysis for Multi-Species Detection and Identification

CVPR 2024

citations

Core Knowledge Learning Framework for Graph

AAAI 2025arXiv

citations

Amodal Scene Analysis via Holistic Occlusion Relation Inference and Generative Mask Completion

AAAI 2024

citations

Bowen Zhang

Affiliations

papers (20)

FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling

Ferret: Refer and Ground Anything Anywhere at Any Granularity

Structured 3D Latents for Scalable and Versatile 3D Generation

StyleSwin: Transformer-Based GAN for High-Resolution Image Generation

ZegCLIP: Towards Adapting CLIP for Zero-Shot Semantic Segmentation

SegViT: Semantic Segmentation with Plain Vision Transformers

MetaPortrait: Identity-Preserving Talking Head Generation With Fast Personalized Adaptation

MetaDiff: Meta-Learning with Conditional Diffusion for Few-Shot Learning

Dynamic Token Pruning in Plain Vision Transformers for Semantic Segmentation

Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Pre-training Framework

STIV: Scalable Text and Image Conditioned Video Generation

Dynamic Neural Representational Decoders for High-Resolution Semantic Segmentation

MMEgo: Towards Building Egocentric Multimodal LLMs for Video QA

Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis

MOFI: Learning Image Representations from Noisy Entity Annotated Images

Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Models

Adapting to Observation Length of Trajectory Prediction via Contrastive Learning

WildlifeMapper: Aerial Image Analysis for Multi-Species Detection and Identification

Core Knowledge Learning Framework for Graph

Amodal Scene Analysis via Holistic Occlusion Relation Inference and Generative Mask Completion

papers (20)

FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling

Ferret: Refer and Ground Anything Anywhere at Any Granularity

Structured 3D Latents for Scalable and Versatile 3D Generation

StyleSwin: Transformer-Based GAN for High-Resolution Image Generation

ZegCLIP: Towards Adapting CLIP for Zero-Shot Semantic Segmentation

SegViT: Semantic Segmentation with Plain Vision Transformers

MetaPortrait: Identity-Preserving Talking Head Generation With Fast Personalized Adaptation

MetaDiff: Meta-Learning with Conditional Diffusion for Few-Shot Learning

Dynamic Token Pruning in Plain Vision Transformers for Semantic Segmentation

Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Pre-training Framework

STIV: Scalable Text and Image Conditioned Video Generation

Dynamic Neural Representational Decoders for High-Resolution Semantic Segmentation

MMEgo: Towards Building Egocentric Multimodal LLMs for Video QA

Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis

MOFI: Learning Image Representations from Noisy Entity Annotated Images

Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Models

Adapting to Observation Length of Trajectory Prediction via Contrastive Learning

WildlifeMapper: Aerial Image Analysis for Multi-Species Detection and Identification

Core Knowledge Learning Framework for Graph

Amodal Scene Analysis via Holistic Occlusion Relation Inference and Generative Mask Completion