A survey of multimodal federated learning: background, applications, and perspectives

H Pan, X Zhao, L He, Y Shi, X Lin - Multimedia Systems, 2024 - Springer
Abstract Multimodal Federated Learning (MMFL) is a novel machine learning technique that
enhances the capabilities of traditional Federated Learning (FL) to support collaborative …

Sparse Query Dense: Enhancing 3D Object Detection with Pseudo Points

Y Mo, Y Wu, J Zhao, Z Hou, W Huang, Y Hu… - Proceedings of the …, 2024 - dl.acm.org
Current LiDAR-only 3D detection methods are limited by the sparsity of point clouds. The
previous method used pseudo points generated by depth completion to supplement the …

Multi-view key information representation and multi-modal fusion for single-subject routine action recognition

X Chao, G Ji, X Qi - Applied Intelligence, 2024 - Springer
Currently, human action recognition has witnessed remarkable progress, and its
achievements have been applied to daily life. However, most methods extract features from …

Posture-Invariant Human Detection and Tracking for Outdoor Night-Time Surveillance

M Younsi, M Diaf, P Siarry - Circuits, Systems, and Signal Processing, 2024 - Springer
Human detection and tracking from infrared image sequences has received considerable
attention in many practical applications, ranging from security and surveillance to automated …

MGSAN: multimodal graph self-attention network for skeleton-based action recognition

J Wang, Z Li, B Liu, H Cai, M Saada, Q Meng - Multimedia Systems, 2024 - Springer
Due to the emergence of graph convolutional networks (GCNs), the skeleton-based action
recognition has achieved remarkable results. However, the current models for skeleton …

Motion synthesis via distilled absorbing discrete diffusion model

J Wang, C Zheng, B Liu, H Cai, Q Meng - Multimedia Systems, 2024 - Springer
In this work, we explore the potential of discrete diffusion model in text-driven motion
synthesis. Previous methods aimed at improving the quality of generated motions often led …

Sparse Query Dense: Enhancing 3D Object Detection with Pseudo points

M Yujian, Y Wu, J Zhao, H Yinghao, J Wang, J Yan - ACM Multimedia … - openreview.net
Current LiDAR-only 3D detection methods are limited by the sparsity of point clouds. The
previous method used pseudo points generated by depth completion to supplement the …