VISUAL ATTENTION

By Jimmy Ba, Volodymyr Mnih, Koray Kavukcuoglu. 2014

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Coarse-to-Fine Question Answering for Long Documents (2016, neutral): “, 2016b), extractive summarization (Cheng and Lapata, 2016), machine translation (Ba et al., 2014) and sentiment analysis (Yessenalina et al.”
TensorFlow: A system for large-scale machine learning (2016, neutral): “In recent years, machine learning has driven advances in many different fields [3, 5, 23, 24, 30, 27, 40, 45, 48, 50, 55, 68, 69, 73, 76].”
Spatial Transformer Networks (2015, neutral): “In this section we discuss the prior work related to the paper, covering the central ideas of modelling transformations with neural networks [12, 13, 27], learning and analysing transformation-invariant representations [3, 5, 8, 17, 19, 25], as well as attention and detection mechanisms for feature ”
Learning to decompose for object detection and instance segmentation (2015, neutral): “(2014); Ba et al. (2015) both proposed visual attention models.”
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems (2016, neutral): “com sequence prediction [47], move selection for Go [34], pedestrian detection [2], reinforcement learning [38], and other areas [17, 5].”
DRAW: A Recurrent Neural Network For Image Generation (2015, positive): “The network is similar to the recently introduced Recurrent Attention Model (RAM) (Mnih et al., 2014), except that our attention method is differentiable; we therefore refer to it as “Differ-entiable RAM”.”
Dynamic Neural Networks: A Survey (2021, neutral): “Vision Sa & Sp & Te General classification [39], [159], [161], Multi-object classification [229], [230], Fine-grained classification [160]”
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention (2015, positive): “Using T s,t : R s → R t to denote a simple afﬁne transformation with parameters that are learned, Here, i t , f t , c t , o t , h t are the input, forget, memory, output and hidden state of the LSTM, respectively.”
Importance Weighted Autoencoders (2015, neutral): “Tang & Salakhutdinov (2013) and Ba et al. (2015) avoided recognition networks entirely, instead performing inference using importance sampling from the prior.”
Dueling Network Architectures for Deep Reinforcement Learning (2015, neutral): “Notable examples include deep Q-learning (Mnih et al., 2015), deep visuomotor policies (Levine et al., 2015), attention with recurrent networks (Ba et al., 2015), and model predictive control with embeddings (Watter et al., 2015).”
Rationalizing Neural Predictions (2016, neutral): “(Weaver and Tao, 2001; Mni et al., 2014; Ba et al., 2015; Xu et al., 2015)).”
Reinforcement Learning Neural Turing Machines (2015, neutral): “There have since been a number of papers on visual attention that have used both Reinforce and differentiable attention [1, 17].”
BAM: Bottleneck Attention Module (2018, neutral): “Attention mechanism in deep neural networks has been investigated in many previous works [2, 3, 12, 25, 35, 45].”
Learning World Graphs to Accelerate Hierarchical Reinforcement Learning (2019, positive): “In addition, th WN mechanism borrows ideas from attentive object understanding [31, 5, 95] in vision.”
Dynamic Routing Between Capsules (2017, neutral): “Hinton et al. propose the task of segmenting and recognizing highly overlapping digits (Hinton et al. [2000] and others have tested their networks in a similar domain (Goodfellow et al. [2013], Ba et al. [2014], Greff et al. [2016]).”
RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism (2016, neutral): “Attention based neural network models are being successfully applied to image processing [1, 32, 21, 37], natural language processing [2, 22, 33] and speech recognition [12].”
CBAM: Convolutional Block Attention Module (2018, neutral): “The significance of attention has been studied extensively in the previous literature [12,13,14,15,16,17].”
Using Fast Weights to Attend to the Recent Past (2016, positive): “[2014], Ba et al. [2015], Xu et al. [2015] have been shown to overcome some of the limitations in ConvNets.”
On the Binding Problem in Artificial Neural Networks (2020, neutral): “classification) or to interact with an environment (Mnih et al., 2014; Ba et al., 2014).”
Concept whitening for interpretable image recognition (2020, neutral): “, 2019; Wu & Song, 2019), to do classification based on hard attention (Mnih et al., 2014; Ba et al., 2014; Sermanet et al., 2015; Elsayed et al., 2019), or to do image recognition by decomposing the components of images (Saralajew et al.”