Image caption models using visual attention and reinforcement learning (The 4th place solution to the AIChallenger Contest, Image Caption Track by team xiaoquexing)
-
Updated
Dec 21, 2017 - Jupyter Notebook
Image caption models using visual attention and reinforcement learning (The 4th place solution to the AIChallenger Contest, Image Caption Track by team xiaoquexing)
Chainer implementation of Deepmind's Visual Attention Model paper
Tools for the paper of IEEE Journal on Emerging and Selected Topics in Circuits and Systems: Visual Attention-Aware Omnidirectional Video Streaming Using Optimal Tiles for Virtual Reality
Implementation of a Multimodal Neural Network for Image Captioning in Tensorflow.
Code for the paper 'A Biologically Inspired Visual Working Memory for Deep Networks'
STNet: Selective Tuning of Convolutional Networks for Object Localization
AttentionBox: Efficient Object Proposal Generation based on AttentionMask
A model of mixed neural networks for step-by-step processing of dynamic visual scenes, activity recognition and behavioral prediciton
Implemenetation of 2016 paper "Show, Attend and Tell: Neural Image Caption Generation with Visual Attention" on Flick30k dataset.
Visual Attention : what is salient in an image with DeepRare2019
RARE2012 is a feature-engineered bottom-up visual attention model
RARE2007 is a feature-engineered bottom-up salienct model only using color information (no orientation)
Where do people look on images in average? At rare, thus surprising things! Let's compute them automatically
ETTO (Eye-Tracking Through Objects) and EToCVD (Eye-Tracking of Colour Vision Deficiencies) datasets are shared with all who might be interested in working on Visual Attention/Visual Saliency.
Global-Local Capsule Network (GLCapsNet) is a capsule-based architecture able to provide context-based eye fixation prediction for several autonomous driving scenarios, while offering interpretability both globally and locally.
Salient Object Detection in the Deep Learning Era: An In-Depth Survey
Code for "Multiple decisions about one object involve parallel sensory acquisition but time-multiplexed evidence incorporation"
Salient Object Detection Driven by Fixation Prediction (CVPR2018)
Add a description, image, and links to the visual-attention topic page so that developers can more easily learn about it.
To associate your repository with the visual-attention topic, visit your repo's landing page and select "manage topics."