Turnitin
降AI改写
早检测系统
早降重系统
Turnitin-UK版
万方检测-期刊版
维普编辑部版
Grammarly检测
Paperpass检测
checkpass检测
PaperYY检测
Efficient 3D Recognition with Event-driven Spike Sparse Convolution
Spiking Neural Networks (SNNs) provide an energy-efficient way to extract 3D spatio-
temporal features. Point clouds are sparse 3D spatial data, which suggests that SNNs …
temporal features. Point clouds are sparse 3D spatial data, which suggests that SNNs …
Quantized Spike-driven Transformer
Spiking neural networks are emerging as a promising energy-efficient alternative to
traditional artificial neural networks due to their spike-driven paradigm. However, recent …
traditional artificial neural networks due to their spike-driven paradigm. However, recent …
Universal Image Restoration Pre-training via Degradation Classification
This paper proposes the Degradation Classification Pre-Training (DCPT), which enables
models to learn how to classify the degradation type of input images for universal image …
models to learn how to classify the degradation type of input images for universal image …
Beyond Timesteps: A Novel Activation-wise Membrane Potential Propagation Mechanism for Spiking Neural Networks in 3D cloud
J Song, B Zheng, X Yang, D Wang - arxiv preprint arxiv:2502.12791, 2025 - arxiv.org
Due to the similar characteristics between event-based visual data and point clouds, recent
studies have emerged that treat event data as event clouds to learn based on point cloud …
studies have emerged that treat event data as event clouds to learn based on point cloud …