Titlebook: Neural Information Processing; 28th International C Teddy Mantoro,Minho Lee,Achmad Nizar Hidayanto Conference proceedings 2021 Springer Nat

obesity

书目名称Neural Information Processing影响因子(影响力)




书目名称Neural Information Processing影响因子(影响力)学科排名




书目名称Neural Information Processing网络公开度




书目名称Neural Information Processing网络公开度学科排名




书目名称Neural Information Processing被引频次




书目名称Neural Information Processing被引频次学科排名




书目名称Neural Information Processing年度引用




书目名称Neural Information Processing年度引用学科排名




书目名称Neural Information Processing读者反馈




书目名称Neural Information Processing读者反馈学科排名

EXUDE

尊敬

煞费苦心

考古学

Metric Learning Based Vision Transformer for Product Matching products. The proposed ML-VIT adopts Arcface loss to achieve intra-class compactness and inter-class dispersion. Compared with Siamese neural network and other pre-trained models in terms of F1 score and accuracy, ML-VIT is proved to yield modest embeddings for product image matching.

独轮车

疼死我了

A Focally Discriminative Loss for Unsupervised Domain Adaptationiscrimination. The intergration of both losses makes the intra-class features close as well as push away the inter-class features far from each other. Moreover, the improved loss is simple yet effective. Our model shows state-of-the-art compared to the most domain adaptation methods.

blithe

Learning Discriminative Representation with Attention and Diversity for Large-Scale Face Recognitionenvalue decomposition or the approximation process. Visualization results illustrate that models with our attention module and diversity regularizers capture more critical localization information. And competitive performance on large-scale face recognition benchmark verifies the effectiveness of our approaches.

开始发作

Multi-task Perceptual Occlusion Face Detection with Semantic Attention Networkon is selected and aggregated automatically to the task of occlusion face detection. Finally, MTOFD is tested and compared with some typical algorithms, such as FAN and AOFD, and it is found that our algorithm achieves state-of-the-art performance on dataset MAFA.

处理

RAIDU-Net: Image Inpainting via Residual Attention Fusion and Gated Information Distillationnd decoder, which can further extract useful low-level features from the generator. Experiments on public databases show that our RAIDU-Net architecture achieves promising results and outperforms the existing state-of-the-art methods.