Zeming Li

papers

2,667

total citations

papers (18)

HMD-Poser: On-Device Real-time Human Motion Tracking from Scalable Sparse Observations

CVPR 2024arXiv

citations

Rethinking Learnable Tree Filter for Generic Feature Transform

NEURIPS 2020arXiv

citations

Multi-modal Relation Distillation for Unified 3D Representation Learning

ECCV 2024arXiv

citations

Zeming Li

papers (18)

OTA: Optimal Transport Assignment for Object Detection

Distribution Alignment: A Unified Framework for Long-Tail Visual Recognition

Unifying Voxel-based Representation with Transformer for 3D Object Detection

End-to-End Object Detection With Fully Convolutional Network

Generalized Few-Shot Object Detection Without Forgetting

Fully Convolutional Networks for Panoptic Segmentation

Learning Dynamic Routing for Semantic Segmentation

BorderDet: Border Feature for Dense Object Detection

Dense Teacher: Dense Pseudo-Labels for Semi-Supervised Object Detection

Voxel Field Fusion for 3D Object Detection

Real-Time Object Detection for Streaming Perception

IQDet: Instance-Wise Quality Distribution Sampling for Object Detection

MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D Perception

Fine-Grained Dynamic Head for Object Detection

Dynamic Grained Encoder for Vision Transformers

HMD-Poser: On-Device Real-time Human Motion Tracking from Scalable Sparse Observations

Rethinking Learnable Tree Filter for Generic Feature Transform

Multi-modal Relation Distillation for Unified 3D Representation Learning

papers (18)

OTA: Optimal Transport Assignment for Object Detection

Distribution Alignment: A Unified Framework for Long-Tail Visual Recognition

Unifying Voxel-based Representation with Transformer for 3D Object Detection

End-to-End Object Detection With Fully Convolutional Network

Generalized Few-Shot Object Detection Without Forgetting

Fully Convolutional Networks for Panoptic Segmentation

Learning Dynamic Routing for Semantic Segmentation

BorderDet: Border Feature for Dense Object Detection

Dense Teacher: Dense Pseudo-Labels for Semi-Supervised Object Detection

Voxel Field Fusion for 3D Object Detection

Real-Time Object Detection for Streaming Perception

IQDet: Instance-Wise Quality Distribution Sampling for Object Detection

MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D Perception

Fine-Grained Dynamic Head for Object Detection

Dynamic Grained Encoder for Vision Transformers

HMD-Poser: On-Device Real-time Human Motion Tracking from Scalable Sparse Observations

Rethinking Learnable Tree Filter for Generic Feature Transform

Multi-modal Relation Distillation for Unified 3D Representation Learning