Results 1 to 10 of about 8,059,355 (318)
Visual attention network [PDF]
Computational Visual Media, 2023 While originally designed for natural language processing tasks, the self-attention mechanism has recently taken various computer vision areas by storm.
Meng-Hao Guo +4 more
doaj +4 more sources
Deep Visual Attention Prediction [PDF]
IEEE Transactions on Image Processing, 2018 In this work, we aim to predict human eye fixation with view-free scenes based on an end-to-end deep learning architecture. Although Convolutional Neural Networks (CNNs) have made substantial improvement on human attention prediction, it is still needed ...
Shen, Jianbing, Wang, Wenguan
core +4 more sources
Dynamic Computational Time for Visual Attention [PDF]
2017 IEEE International Conference on Computer Vision Workshops (ICCVW), 2017 We propose a dynamic computational time model to accelerate the average processing time for recurrent visual attention (RAM). Rather than attention with a fixed number of steps for each input image, the model learns to decide when to stop on the fly.
Li, Zhichao +5 more
core +2 more sources
Clothing Retrieval with Visual Attention Model [PDF]
Visual Communications and Image Processing, 2017 Clothing retrieval is a challenging problem in computer vision. With the advance of Convolutional Neural Networks (CNNs), the accuracy of clothing retrieval has been significantly improved.
Gu, Xiao +4 more
core +2 more sources
Diversified Visual Attention Networks for Fine-Grained Object Classification [PDF]
IEEE transactions on multimedia, 2017 Fine-grained object classification is a challenging task due to the subtle inter-class difference and large intra-class variation. Recently, visual attention models have been applied to automatically localize the discriminative regions of an image for ...
Feng, Jiashi +4 more
core +2 more sources
Visual Attention Methods in Deep Learning: An In-Depth Survey [PDF]
Information Fusion, 2022 Inspired by the human cognitive system, attention is a mechanism that imitates the human cognitive awareness about specific information, amplifying critical details to focus more on the essential aspects of data.
M. Hassanin +4 more
semanticscholar +1 more source
UniFormer: Unifying Convolution and Self-Attention for Visual Recognition [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022 It is a challenging task to learn discriminative representation from images and videos, due to large local redundancy and complex global dependency in these visual data.
Kunchang Li +7 more
semanticscholar +1 more source
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification [PDF]
IEEE International Conference on Computer Vision, 2021 Attention mechanism has demonstrated great potential in fine-grained visual recognition tasks. In this paper, we present a counterfactual attention learning method to learn more effective attention based on causal inference.
Yongming Rao +3 more
semanticscholar +1 more source
AiATrack: Attention in Attention for Transformer Visual Tracking [PDF]
European Conference on Computer Vision, 2022 Transformer trackers have achieved impressive advancements recently, where the attention mechanism plays an important role. However, the independent correlation computation in the attention mechanism could result in noisy and ambiguous attention weights,
Shenyuan Gao +4 more
semanticscholar +1 more source
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering [PDF]
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2017 Top-down visual attention mechanisms have been used extensively in image captioning and visual question answering (VQA) to enable deeper image understanding through fine-grained analysis and even multiple steps of reasoning.
Peter Anderson +6 more
semanticscholar +1 more source