有斑点 发表于 2025-3-26 23:23:24
Hierarchical Graph Convolutional Network for Skeleton-Based Action Recognitiony ignore the topological structure of the skeleton which is very important for action recognition. Recently, Graph Convolutional Networks (GCNs) achieve remarkable performance in modeling non-Euclidean structures. However, current graph convolutional networks lack the capacity of modeling hierarchic单调女 发表于 2025-3-27 03:47:10
http://reply.papertrans.cn/47/4615/461490/461490_32.pngorganism 发表于 2025-3-27 08:00:31
http://reply.papertrans.cn/47/4615/461490/461490_33.pngadumbrate 发表于 2025-3-27 12:38:04
http://reply.papertrans.cn/47/4615/461490/461490_34.png暴行 发表于 2025-3-27 16:14:29
http://reply.papertrans.cn/47/4615/461490/461490_35.png起来了 发表于 2025-3-27 17:55:56
http://reply.papertrans.cn/47/4615/461490/461490_36.pngCRAFT 发表于 2025-3-27 22:01:26
Semantic Segmentation of Street Scenes Using Disparity Informationlent results on several semantic segmentation benchmarks. Most of them, however, only exploit RGB information. Due to the development of stereo matching algorithms, disparity maps can be more easily acquired. Structural information encoded in disparity can be treated as supplementary information of前奏曲 发表于 2025-3-28 02:30:57
http://reply.papertrans.cn/47/4615/461490/461490_38.png联想记忆 发表于 2025-3-28 06:54:32
http://reply.papertrans.cn/47/4615/461490/461490_39.png反馈 发表于 2025-3-28 11:45:35
Residual Joint Attention Network with Graph Structure Inference for Object Detectionng on the improvement of the feature extraction, we propose Residual Joint Attention Network, a convolutional neural network using a residual joint attention module which is composed of a spatial attention branch, a channel attention branch, and a residual learning branch within an advanced object d