Pichao Wang

papers

2,182

total citations

papers (15)

TransReID: Transformer-Based Object Re-Identification

ICCV 2021arXiv

1,085

citations

MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation

CVPR 2022arXiv

353

citations

PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation

CVPR 2023arXiv

179

citations

TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation

ECCV 2022arXiv

citations

Making Vision Transformers Efficient From a Token Sparsification View

CVPR 2023arXiv

citations

Audio-Enhanced Text-to-Video Retrieval using Text-Conditioned Feature Alignment

ICCV 2023arXiv

citations

Decoupling and Recoupling Spatiotemporal Representation for RGB-D-Based Motion Recognition

CVPR 2022arXiv

citations

Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation

CVPR 2024arXiv

citations

Revisiting Vision Transformer from the View of Path Ensemble

ICCV 2023arXiv

citations

SparseDiT: Token Sparsification for Efficient Diffusion Transformer

NEURIPS 2025arXiv

citations

EPro-PnP: Generalized End-to-End Probabilistic Perspective-N-Points for Monocular Object Pose Estimation

CVPR 2022arXiv

citations

Zen-NAS: A Zero-Shot NAS for High-Performance Image Recognition

ICCV 2021

citations

Pichao Wang

papers (15)

TransReID: Transformer-Based Object Re-Identification

MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation

PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation

Selective Structured State-Spaces for Long-Form Video Understanding

KVT: k-NN Attention for Boosting Vision Transformers

Text Is MASS: Modeling as Stochastic Embedding for Text-Video Retrieval

TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation

Making Vision Transformers Efficient From a Token Sparsification View

Audio-Enhanced Text-to-Video Retrieval using Text-Conditioned Feature Alignment

Decoupling and Recoupling Spatiotemporal Representation for RGB-D-Based Motion Recognition

Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation

Revisiting Vision Transformer from the View of Path Ensemble

SparseDiT: Token Sparsification for Efficient Diffusion Transformer

EPro-PnP: Generalized End-to-End Probabilistic Perspective-N-Points for Monocular Object Pose Estimation

Zen-NAS: A Zero-Shot NAS for High-Performance Image Recognition

papers (15)

TransReID: Transformer-Based Object Re-Identification

MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation

PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation

Selective Structured State-Spaces for Long-Form Video Understanding

KVT: k-NN Attention for Boosting Vision Transformers

Text Is MASS: Modeling as Stochastic Embedding for Text-Video Retrieval

TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation

Making Vision Transformers Efficient From a Token Sparsification View

Audio-Enhanced Text-to-Video Retrieval using Text-Conditioned Feature Alignment

Decoupling and Recoupling Spatiotemporal Representation for RGB-D-Based Motion Recognition

Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation

Revisiting Vision Transformer from the View of Path Ensemble

SparseDiT: Token Sparsification for Efficient Diffusion Transformer

EPro-PnP: Generalized End-to-End Probabilistic Perspective-N-Points for Monocular Object Pose Estimation

Zen-NAS: A Zero-Shot NAS for High-Performance Image Recognition