Effective and efficient self-supervised masked model based on mixed feature training [0.03%]
基于混合特征训练的有效高效自监督掩码模型
Qingjiu Kang,Feng Liu,Chunliu Cai
Qingjiu Kang
Under the influence of Masked Language Modeling (MLM), Masked Image Modeling (MIM) employs an attention mechanism to perform masked training on images. However, processing a single image requires numerous iterations and substantial computat...
A simple robot suggests trunk rotation is essential for emergence of inside leading limb during quadruped galloping turns [0.03%]
一个简单的机器人表明躯干旋转对于四足动物疾跑转弯时内侧前肢的出现至关重要
Tomoe Maeta,Shoei Hattori,Takeshi Kano et al.
Tomoe Maeta et al.
During turning maneuvers in the galloping gait of quadruped animals, a strong relationship exists between the turning direction and the sequence in which the forelimbs make ground contact: the outer forelimb acts as the "trailing limb" whil...
TSLNet: a hierarchical multi-head attention-enabled two-stream LSTM network for accurate pedestrian tracking and behavior recognition [0.03%]
基于层次结构的多头注意力两流LSTM网络在行人跟踪和行为识别中的应用研究
Shouye Lv,Rui He,Xiaofei Cheng et al.
Shouye Lv et al.
Accurate pedestrian tracking and behavior recognition are essential for intelligent surveillance, smart transportation, and human-computer interaction systems. This paper introduces TSLNet, a Hierarchical Multi-Head Attention-Enabled Two-St...
Adaptive-expert-weight-based load balance scheme for dynamic routing of MoE [0.03%]
基于自适应专家权重的MoE动态路由负载均衡方案
Jialin Wen,Xiaojun Li,Junping Yao et al.
Jialin Wen et al.
Load imbalance is a major performance bottleneck in training mixture-of-experts (MoE) models, as unbalanced expert loads can lead to routing collapse. Most existing approaches address this issue by introducing auxiliary loss functions to ba...
UHGAN: a dual-phase GAN with Hough-transform constraints for accurate farmland road extraction [0.03%]
基于霍夫变换约束的双重生成对抗网络算法的精准提取农田道路研究
Xinliang Wang,Yuan Ma
Xinliang Wang
Introduction: Traditional methods for farmland road extraction, such as U-Net, often struggle with complex noise and geometric features, leading to discontinuous extraction and insufficient sensitivity. To address these l...
UAV-based intelligent traffic surveillance using recurrent neural networks and Swin transformer for dynamic environments [0.03%]
基于无人机的智能交通监控：用于动态环境的循环神经网络和Swin变换器方法
Mohammed Alshehri,Ting Wu,Nouf Abdullah Almujally et al.
Mohammed Alshehri et al.
Introduction: Urban traffic congestion, environmental degradation, and road safety challenges necessitate intelligent aerial robotic systems capable of real-time adaptive decision-making. Unmanned Aerial Vehicles (UAVs), ...
End-to-end robot intelligent obstacle avoidance method based on deep reinforcement learning with spatiotemporal transformer architecture [0.03%]
基于时空变换器架构的深度强化学习端到端机器人智能避障方法
Yuwen Zhou,Weizhong Zhang
Yuwen Zhou
To enhance the obstacle avoidance performance and autonomous decision-making capabilities of robots in complex dynamic environments, this paper proposes an end-to-end intelligent obstacle avoidance method that integrates deep reinforcement ...
DWMamba: a structure-aware adaptive state space network for image quality improvement [0.03%]
DWMamba：一种结构感知自适应状态空间网络用于图像质量提升
Wenjun Fu,Xiaobin Wang,Chuncai Yang et al.
Wenjun Fu et al.
Overcoming visual degradation in challenging imaging scenarios is essential for accurate scene understanding. Although deep learning methods have integrated various perceptual capabilities and achieved remarkable progress, their high comput...
Tom Donnelly,Elena Seminati,Benjamin Metcalfe
Tom Donnelly
Introduction: Abandonment rates for myoelectric upper limb prostheses can reach 44%, negatively affecting quality of life and increasing the risk of injury due to compensatory movements. Traditional myoelectric prostheses...
Weizhen Tang,Jie Dai
Weizhen Tang
Introduction: To address the challenges of cumulative errors, insufficient modeling of complex spatiotemporal features, and limitations in computational efficiency and generalization ability in 4D trajectory prediction, t...