J
Jun Miao
Researcher at Chinese Academy of Sciences
Publications - 86
Citations - 1247
Jun Miao is an academic researcher from Chinese Academy of Sciences. The author has contributed to research in topics: Extreme learning machine & Image segmentation. The author has an hindex of 15, co-authored 78 publications receiving 1113 citations.
Papers
More filters
Proceedings ArticleDOI
Visual saliency detection by spatially weighted dissimilarity
TL;DR: Experimental results show that the proposed new visual saliency detection method outperforms current state-of-the-art methods on predicting human fixations.
Journal ArticleDOI
A hierarchical multiscale and multiangle system for human face detection in a complex background using gravity-center template
TL;DR: A novel faster search scheme of gravity-center template matching compared with the traditional search method in an image for human face detection, which significantly saves the time consumed in rough detection of human faces in a mosaic image.
Journal ArticleDOI
One-Class Classification with Extreme Learning Machine
TL;DR: The experimental evaluation shows that the ELM based one-class classifier can learn hundreds of times faster than autoencoder and it is competitive over a variety of one- class classification methods.
Proceedings ArticleDOI
Hierarchical Extreme Learning Machine for unsupervised representation learning
TL;DR: Compared to traditional deep learning methods, the proposed trans-layer representation method with ELM-AE based learning of local receptive filters has much faster learning speed and is validated in several typical experiments, such as digit recognition on MNIST and MNIST variations, object recognition on Caltech 101.
Proceedings ArticleDOI
Activity Auto-Completion: Predicting Human Activities from Partial Videos
Zhen Xu,Laiyun Qing,Jun Miao +2 more
TL;DR: An activity auto-completion (AAC) model for human activity prediction is proposed by formulating activity prediction as a query auto- completion (QAC) problem in information retrieval by extracting discriminative patches in frames of videos.