【17-21期VALSE Webinar活动】

正文

请到「今天看啥」查看全文

A summary of hashing researches will be introduced, and some algorithms used to solve retrieval and classification applications will be explained in detail. Recently, learning based hashing techniques have attracted broad research interests due to their ability to support efficient storage and retrieval for high-dimensional data such as images, videos, documents, etc. The major difficulty of learning to hash lies in handling the discrete constraints imposed on the pursued hash codes, which typically makes hash optimizations very challenging (NP-hard in general). The widely adopted relaxation scheme simplifies the optimization, however, tends to produce less effective codes. In this talk, we will present our recent work investigating how to directly learn binary codes via discrete optimization, namely discrete hashing. Discrete hashing has been shown to significantly boost the performance of hashing algorithms (e.g., Supervised Discrete Hashing, Discrete Proximal Linearized Minimization) in large-scale similarity search. We will also introduce our recent work on applying hashing techniques to boost and improve conventional tasks, such as linear classification, clustering, sketch based visual retrieval, recommendation systems and action recognition.

论文相关：

[1] Jingdong Wang, Ting Zhang, Jingkuan Song, NicuSebe, Heng Tao Shen*. "A Survey on Learning to Hash". IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2017. (An early version "Hashing for similarity search: A survey" at arXiv:1408.2927).

[2] Mengqiu Hu, Yang Yang, Fumin Shen, Ning Xie, Heng Tao Shen. “Hashing with Angular Reconstructive Embeddings”. IEEE Transactions on Image Processing (TIP), 2017.

[3] Litao Yu, Zi Huang, Fumin Shen, Jingkuan Song, Heng Tao Shen*, Xiaofang Zhou. “Bilinear Optimized Product Quantization for Scalable Visual Content Analysis”. IEEE Transactions on Image Processing (TIP), 2017.

[4] Xing Xu, Fumin Shen, Yang Yang, Heng Tao Shen, Xuelong Li. "Learning Discriminative Binary Codes for Large-scale Cross-modal Retrieval". IEEE Transactions on Image Processing (TIP), 2017.

[5] Fumin Shen, Chunhua Shen, Wei Liu, Heng Tao Shen, "Supervised Discrete Hashing", IEEE CVPR 2015.

请到「今天看啥」查看全文