Haifeng Liu

papers

762

total citations

papers (11)

Sparse Fuse Dense: Towards High Quality 3D Detection With Depth Completion

CVPR 2022arXiv

244

citations

CLIP Is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation

CVPR 2023arXiv

189

citations

TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP without Training

AAAI 2024arXiv

citations

TASeg: Temporal Aggregation Network for LiDAR Semantic Segmentation

CVPR 2024arXiv

citations

Semi-supervised 3D Object Detection with PatchTeacher and PillarMix

AAAI 2024arXiv

citations

Boosting Few

AAAI 2024

citations

Haifeng Liu

papers (11)

Sparse Fuse Dense: Towards High Quality 3D Detection With Depth Completion

CLIP Is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation

DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detection

Part-dependent Label Noise: Towards Instance-dependent Label Noise

Lidar Point Cloud Guided Monocular 3D Object Detection

Depth Any Video with Scalable Synthetic Data

Convolutional Embedding Makes Hierarchical Vision Transformer Stronger

TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP without Training

TASeg: Temporal Aggregation Network for LiDAR Semantic Segmentation

Semi-supervised 3D Object Detection with PatchTeacher and PillarMix

Boosting Few

papers (11)

Sparse Fuse Dense: Towards High Quality 3D Detection With Depth Completion

CLIP Is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation

DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detection

Part-dependent Label Noise: Towards Instance-dependent Label Noise

Lidar Point Cloud Guided Monocular 3D Object Detection

Depth Any Video with Scalable Synthetic Data

Convolutional Embedding Makes Hierarchical Vision Transformer Stronger

TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP without Training

TASeg: Temporal Aggregation Network for LiDAR Semantic Segmentation

Semi-supervised 3D Object Detection with PatchTeacher and PillarMix

Boosting Few