Wu Gengshen, Han Jungong, Guo Yuchen, Liu Li, Ding Guiguang, Ni Qiang, Shao Ling
IEEE Trans Image Process. 2018 Nov 19. doi: 10.1109/TIP.2018.2882155.
This paper proposes a deep hashing framework, namely Unsupervised Deep Video Hashing (UDVH), for largescale video similarity search with the aim to learn compact yet effective binary codes. Our UDVH produces the hash codes in a self-taught manner by jointly integrating discriminative video representation with optimal code learning, where an efficient alternating approach is adopted to optimize the objective function. The key differences from most existing video hashing methods lie in 1) UDVH is an unsupervised hashing method that generates hash codes by cooperatively utilizing feature clustering and a specifically-designed binarization with the original neighborhood structure preserved in the binary space; 2) a specific rotation is developed and applied onto video features such that the variance of each dimension can be balanced, thus facilitating the subsequent quantization step. Extensive experiments performed on three popular video datasets show that UDVH is overwhelmingly better than the state-of-the-arts in terms of various evaluation metrics, which makes it practical in real-world applications.
本文提出了一种深度哈希框架，即无监督深度视频哈希（UDVH），用于大规模视频相似性搜索，旨在学习紧凑而有效的二进制代码。我们的UDVH通过将判别性视频表示与最优代码学习相结合，以自学的方式生成哈希代码，其中采用了一种有效的交替方法来优化目标函数。与大多数现有视频哈希方法的关键区别在于：1）UDVH是一种无监督哈希方法，它通过协同利用特征聚类和专门设计的二值化方法来生成哈希代码，同时在二进制空间中保留原始邻域结构；2）开发了一种特定的旋转方法并将其应用于视频特征，以便平衡每个维度的方差，从而促进后续的量化步骤。在三个流行视频数据集上进行的大量实验表明，在各种评估指标方面，UDVH比现有技术有压倒性的优势，这使其在实际应用中具有实用性。
