Results 241 to 250 of about 1,111,935 (267)
Some of the next articles are maybe not open access.
Fast Self-Attentive Multimodal Retrieval
2018 IEEE Winter Conference on Applications of Computer Vision (WACV), 2018Multimodal bidirectional retrieval is a very challenging task that consists of semantically aligning two distinct modalities such as images and textual descriptions, allowing the retrieval of content from one of the modalities given the other. The goal is to find a common semantic space for both modalities in order to discover the correspondences ...
Jonatas Wehrmann +3 more
openaire +2 more sources
Improve Image Captioning by Self-attention
2019The common attention mechanism has been widely adopted in prevalent image captioning frameworks. In most of the prior work, attention weights were only determined by visual features as well as the hidden states of Recurrent Neural Network (RNN), while the interaction of visual features was not modelled.
Zhenru Li, Yaoyi Li, Hongtao Lu 0001
openaire +2 more sources
Beyond Self-Attention: External Attention Using Two Linear Layers for Visual Tasks
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022Zheng-Ning Liu, Shi-Min Hu, Tai-Jiang Mu
exaly
Self-attention neural architecture search for semantic image segmentation
Knowledge-Based Systems, 2022Junyu Dong, Gai-Ge Wang, Guosheng Hu
exaly
Cascaded feature fusion with multi-level self-attention mechanism for object detection
Pattern Recognition, 2023Huiru Wang
exaly
Relation-mining self-attention network for skeleton-based human action recognition
Pattern Recognition, 2023Yanli Ji +2 more
exaly
Relation constraint self-attention for image captioning
Neurocomputing, 2022Junzhong Ji +2 more
exaly
MHSA-Net: Multihead Self-Attention Network for Occluded Person Re-Identification
IEEE Transactions on Neural Networks and Learning Systems, 2023Hongchen Tan, Xiuping Liu
exaly
FsaNet: Frequency Self-Attention for Semantic Segmentation
IEEE Transactions on Image Processing, 2023Guangjun Gao, Fengyu Zhang
exaly