聪明
发表于 2025-3-23 10:22:54
Exploring Interpretable Semantic Alignment for Multimodal Machine Translationsults. Existing methods focus on constructing the global cross-modal interaction between text and vision while ignoring the local semantic correspondences, which may improve the interpretability of multimodal feature fusion. To this end, we propose a novel multimodal fusion encoder with local semant
痴呆
发表于 2025-3-23 15:04:44
Modal Fusion-Enhanced Two-Stream Hashing Network for Cross Modal Retrievalretrieval, which does not rely on image label information, has garnered widespread attention. However, existing unsupervised methods still face several common issues. Firstly, current methods often only consider either local or global single-feature extraction in image feature extraction. Secondly,
人充满活力
发表于 2025-3-23 20:01:42
http://reply.papertrans.cn/17/1677/167619/167619_13.png
召集
发表于 2025-3-24 01:31:01
Unifying Visual and Semantic Feature Spaces with Diffusion Models for Enhanced Cross-Modal Alignmenting visual perspectives of subject objects and lighting discrepancies. To mitigate these challenges, existing studies commonly incorporate additional modal information matching the visual data to regularize the model’s learning process, enabling the extraction of high-quality visual features from co
granite
发表于 2025-3-24 05:35:02
Addressing the Privacy and Complexity of Urban Traffic Flow Prediction with Federated Learning and S short of adequately safeguarding user privacy. Moreover, these systems tend to overlook how external factors affect traffic flow. To tackle these concerns, we propose a novel architecture based on federated learning and Spatiotemporal GCN. Simultaneously, we employ graph embedding techniques to inc
束缚
发表于 2025-3-24 08:35:19
An Accuracy-Shaping Mechanism for Competitive Distributed Learningw data, while competing for the same customer base using model-based services. Federated learning is an extensively studied distributed learning approach, but it has been shown to discourage collaboration in a competitive environment. The reason is that the shared global model is a public good, whic
Custodian
发表于 2025-3-24 10:42:55
Federated Adversarial Learning for Robust Autonomous Landing Runway Detectionhe face of possible adversarial attacks. In this paper, we propose a federated adversarial learning-based framework to detect landing runways using paired data comprising of clean local data and its adversarial version. Firstly, the local model is pre-trained on a large-scale lane detection dataset.
撤退
发表于 2025-3-24 15:12:35
http://reply.papertrans.cn/17/1677/167619/167619_18.png
dagger
发表于 2025-3-24 22:15:35
Layer-Wised Sparsification Based on Hypernetwork for Distributed NN Trainingining strategies have been proposed to speed up training, the efficiency of these strategies is often hindered by the frequent communication required between different computational nodes. Numerous gradient compression techniques (e.g., Sparsification, Quantization, Low-Rank) have been introduced to
glowing
发表于 2025-3-24 23:55:47
http://reply.papertrans.cn/17/1677/167619/167619_20.png