Alert button
Picture for Hongsheng Li

Hongsheng Li

Alert button

3D Object Detection for Autonomous Driving: A Review and New Outlooks

Jun 19, 2022
Jiageng Mao, Shaoshuai Shi, Xiaogang Wang, Hongsheng Li

Figure 1 for 3D Object Detection for Autonomous Driving: A Review and New Outlooks
Figure 2 for 3D Object Detection for Autonomous Driving: A Review and New Outlooks
Figure 3 for 3D Object Detection for Autonomous Driving: A Review and New Outlooks
Figure 4 for 3D Object Detection for Autonomous Driving: A Review and New Outlooks
Viaarxiv icon

Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs

Jun 09, 2022
Jinguo Zhu, Xizhou Zhu, Wenhai Wang, Xiaohua Wang, Hongsheng Li, Xiaogang Wang, Jifeng Dai

Figure 1 for Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs
Figure 2 for Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs
Figure 3 for Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs
Figure 4 for Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs
Viaarxiv icon

Spatial Parsing and Dynamic Temporal Pooling networks for Human-Object Interaction detection

Jun 07, 2022
Hongsheng Li, Guangming Zhu, Wu Zhen, Lan Ni, Peiyi Shen, Liang Zhang, Ning Wang, Cong Hua

Figure 1 for Spatial Parsing and Dynamic Temporal Pooling networks for Human-Object Interaction detection
Figure 2 for Spatial Parsing and Dynamic Temporal Pooling networks for Human-Object Interaction detection
Figure 3 for Spatial Parsing and Dynamic Temporal Pooling networks for Human-Object Interaction detection
Figure 4 for Spatial Parsing and Dynamic Temporal Pooling networks for Human-Object Interaction detection
Viaarxiv icon

Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training

May 28, 2022
Renrui Zhang, Ziyu Guo, Peng Gao, Rongyao Fang, Bin Zhao, Dong Wang, Yu Qiao, Hongsheng Li

Figure 1 for Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training
Figure 2 for Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training
Figure 3 for Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training
Figure 4 for Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training
Viaarxiv icon

MixMIM: Mixed and Masked Image Modeling for Efficient Visual Representation Learning

May 28, 2022
Jihao Liu, Xin Huang, Yu Liu, Hongsheng Li

Figure 1 for MixMIM: Mixed and Masked Image Modeling for Efficient Visual Representation Learning
Figure 2 for MixMIM: Mixed and Masked Image Modeling for Efficient Visual Representation Learning
Figure 3 for MixMIM: Mixed and Masked Image Modeling for Efficient Visual Representation Learning
Figure 4 for MixMIM: Mixed and Masked Image Modeling for Efficient Visual Representation Learning
Viaarxiv icon

ConvMAE: Masked Convolution Meets Masked Autoencoders

May 19, 2022
Peng Gao, Teli Ma, Hongsheng Li, Ziyi Lin, Jifeng Dai, Yu Qiao

Figure 1 for ConvMAE: Masked Convolution Meets Masked Autoencoders
Figure 2 for ConvMAE: Masked Convolution Meets Masked Autoencoders
Figure 3 for ConvMAE: Masked Convolution Meets Masked Autoencoders
Figure 4 for ConvMAE: Masked Convolution Meets Masked Autoencoders
Viaarxiv icon

MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection

May 12, 2022
Xuesong Chen, Shaoshuai Shi, Benjin Zhu, Ka Chun Cheung, Hang Xu, Hongsheng Li

Figure 1 for MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection
Figure 2 for MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection
Figure 3 for MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection
Figure 4 for MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection
Viaarxiv icon

Efficient Burst Raw Denoising with Variance Stabilization and Multi-frequency Denoising Network

May 10, 2022
Dasong Li, Yi Zhang, Ka Lung Law, Xiaogang Wang, Hongwei Qin, Hongsheng Li

Figure 1 for Efficient Burst Raw Denoising with Variance Stabilization and Multi-frequency Denoising Network
Figure 2 for Efficient Burst Raw Denoising with Variance Stabilization and Multi-frequency Denoising Network
Figure 3 for Efficient Burst Raw Denoising with Variance Stabilization and Multi-frequency Denoising Network
Figure 4 for Efficient Burst Raw Denoising with Variance Stabilization and Multi-frequency Denoising Network
Viaarxiv icon

EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers

May 06, 2022
Junting Pan, Adrian Bulat, Fuwen Tan, Xiatian Zhu, Lukasz Dudziak, Hongsheng Li, Georgios Tzimiropoulos, Brais Martinez

Figure 1 for EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers
Figure 2 for EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers
Figure 3 for EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers
Figure 4 for EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers
Viaarxiv icon