Haochen Wang

papers

1,841

total citations

papers (18)

Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation

CVPR 2023arXiv

648

citations

JeDi: Joint-Image Diffusion Models for Finetuning-Free Personalized Text-to-Image Generation

CVPR 2024arXiv

citations

Towards Open-Vocabulary Video Instance Segmentation

ICCV 2023arXiv

citations

Pixel Consensus Voting for Panoptic Segmentation

CVPR 2020arXiv

citations

Learning from Future: A Novel Self-Training Framework for Semantic Segmentation

NEURIPS 2022arXiv

citations

Balancing Logit Variation for Long-Tailed Semantic Segmentation

CVPR 2023arXiv

citations

Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness

ICCV 2025arXiv

citations

DropPos: Pre-Training Vision Transformers by Reconstructing Dropped Positions

NEURIPS 2023arXiv

citations

The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer

ICCV 2025arXiv

citations

Object-centric Video Question Answering with Visual Grounding and Referring

ICCV 2025arXiv

citations

Alpha Invariance: On Inverse Scaling Between Distance and Volume Density in Neural Radiance Fields

CVPR 2024arXiv

citations

MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs

NEURIPS 2025arXiv

citations

Holistic Tokenizer for Autoregressive Image Generation

ICCV 2025arXiv

citations

Few-Shot Semantic Segmentation with Democratic Attention Networks

ECCV 2020

citations

Haochen Wang

papers (18)

Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation

Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels

SwiftNet: Real-Time Video Object Segmentation

NFormer: Robust Person Re-Identification With Neighbor Transformer

Hard Patches Mining for Masked Image Modeling

JeDi: Joint-Image Diffusion Models for Finetuning-Free Personalized Text-to-Image Generation

Towards Open-Vocabulary Video Instance Segmentation

Pixel Consensus Voting for Panoptic Segmentation

Learning from Future: A Novel Self-Training Framework for Semantic Segmentation

Balancing Logit Variation for Long-Tailed Semantic Segmentation

Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness

DropPos: Pre-Training Vision Transformers by Reconstructing Dropped Positions

The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer

Object-centric Video Question Answering with Visual Grounding and Referring

Alpha Invariance: On Inverse Scaling Between Distance and Volume Density in Neural Radiance Fields

MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs

Holistic Tokenizer for Autoregressive Image Generation

Few-Shot Semantic Segmentation with Democratic Attention Networks

papers (18)

Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation

Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels

SwiftNet: Real-Time Video Object Segmentation

NFormer: Robust Person Re-Identification With Neighbor Transformer

Hard Patches Mining for Masked Image Modeling

JeDi: Joint-Image Diffusion Models for Finetuning-Free Personalized Text-to-Image Generation

Towards Open-Vocabulary Video Instance Segmentation

Pixel Consensus Voting for Panoptic Segmentation

Learning from Future: A Novel Self-Training Framework for Semantic Segmentation

Balancing Logit Variation for Long-Tailed Semantic Segmentation

Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness

DropPos: Pre-Training Vision Transformers by Reconstructing Dropped Positions

The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer

Object-centric Video Question Answering with Visual Grounding and Referring

Alpha Invariance: On Inverse Scaling Between Distance and Volume Density in Neural Radiance Fields

MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs

Holistic Tokenizer for Autoregressive Image Generation

Few-Shot Semantic Segmentation with Democratic Attention Networks