1 code implementation • EMNLP 2018 • Yao Zhao, Xiaochuan Ni, Yuanyuan Ding, Qifa Ke
Long text has posed challenges for sequence to sequence neural models in question generation {--} worse performances were reported if using the whole paragraph (with multiple sentences) as the input.
no code implementations • 11 Dec 2013 • Jingdong Wang, Jing Wang, Qifa Ke, Gang Zeng, Shipeng Li
Traditional $k$-means is an iterative algorithm---in each iteration new cluster centers are computed and each data point is re-assigned to its nearest center.
no code implementations • CVPR 2013 • Tiezheng Ge, Kaiming He, Qifa Ke, Jian Sun
Product quantization is an effective vector quantization approach to compactly encode high-dimensional vectors for fast approximate nearest neighbor (ANN) search.
no code implementations • 18 Dec 2012 • Yunchao Gong, Qifa Ke, Michael Isard, Svetlana Lazebnik
This paper investigates the problem of modeling Internet images and associated text or tags for tasks such as image-to-image search, tag-to-image search, and image-to-tag search (image annotation).