The task of multi-label image recognition is to predict a set of object labels that present in an image. As objects normally co-occur in an image, it is desirable to model the label dependencies to improve the recognition performance. To capture and explore such important dependencies, we propose a multi-label classification model based on Graph Convolutional Network (GCN). The model builds a directed graph over the object labels, where each node (label) is represented by word embeddings of a label, and GCN is learned to map this label graph into a set of inter-dependent object classifiers. These classifiers are applied to the image descriptors extracted by another sub-net, enabling the whole network to be end-to-end trainable. Furthermore, we propose a novel re-weighted scheme to create an effective label correlation matrix to guide information propagation among the nodes in GCN. Experiments on two multi-label image recognition datasets show that our approach obviously outperforms other existing state-of-the-art methods. In addition, visualization analyses reveal that the classifiers learned by our model maintain meaningful semantic topology.
In skeleton-based action recognition, graph convolutional networks (GCNs), which model the human body skeletons as spatiotemporal graphs, have achieved remarkable performance. H...
Text classification is an important and classical problem in natural language processing. There have been a number of studies that applied convolutional neural networks (convolu...
Action recognition with skeleton data has recently attracted much attention in computer vision. Previous studies are mostly based on fixed skeleton graphs, only capturing local ...
For object detection, the two-stage approach (e.g., Faster R-CNN) has been achieving the highest accuracy, whereas the one-stage approach (e.g., SSD) has the advantage of high e...
Many interesting problems in machine learning are being revisited with new deep learning tools. For graph-based semi-supervised learning, a recent important development is graph...
Social media, news, blog, policy document mentions