GitHub

Virtual Sparse Convolution for Multimodal 3D Object Detection

VirConv-L: A light-weight multimodal 3D detector based on Virtual Sparse Convolution. VirConv-T: A improved multimodal 3D detector based on Virtual Sparse Convolution and transformed refinement scheme ...
IEEE

Fully Sparse Fusion for 3D Object Detection

Abstract: Currently prevalent multi-modal 3D detection methods rely on dense detectors that usually use dense Bird’s-Eye-View (BEV) feature maps. However, the cost of such BEV feature maps is ...
IEEE

16.1 MuITCIM: A 28nm $2.24 \mu\mathrm{J}$ /Token Attention-Token-Bit Hybrid Sparse Digital CIM-Based Accelerator for Multimodal Transformers

Abstract: Human perception is multimodal and able to comprehend a mixture of vision, natural language, speech, etc. Multimodal Transformer (MuIT, Fig. 16.1.1) models introduce a cross-modal attention ...