A Yu, K Grauman - … of the IEEE International Conference on …, 2017 - openaccess.thecvf.com
Distinguishing subtle differences in attributes is valuable, yet learning to make visual comparisons remains nontrivial. Not only is the number of possible comparisons quadratic in …
We propose a weakly-supervised approach that takes image-sentence pairs as input and learns to visually ground (ie, localize) arbitrary linguistic phrases, in the form of spatial …
R Armstrong, D Gannon, A Geist… - … Symposium on High …, 1999 - ieeexplore.ieee.org
Describes work in progress to develop a standard for interoperability among high- performance scientific components. This research stems from the growing recognition that …
In fashion recommender systems, each product usually consists of multiple semantic attributes (eg, sleeves, collar, etc). When making cloth decisions, people usually show …
X Zheng, Y Guo, H Huang, Y Li, R He - International Journal of Computer …, 2020 - Springer
Facial attribute analysis has received considerable attention when deep learning techniques made remarkable breakthroughs in this field over the past few years. Deep learning based …
KK Singh, YJ Lee - Computer Vision–ECCV 2016: 14th European …, 2016 - Springer
We propose an end-to-end deep convolutional network to simultaneously localize and rank relative visual attributes, given only weakly-supervised pairwise image comparisons. Unlike …
Y Souri, E Noury, E Adeli - Computer Vision–ACCV 2016: 13th Asian …, 2017 - Springer
Visual attributes are great means of describing images or scenes, in a way both humans and computers understand. In order to establish a correspondence between images and to be …
W Min, S Mei, L Liu, Y Wang… - IEEE Transactions on …, 2019 - ieeexplore.ieee.org
Visual urban perception aims to quantify perceptual attributes (eg, safe and depressing attributes) of physical urban environment from crowd-sourced street-view images and their …