ABSTRACT
Recent years have witnessed the success of the emerging hash-based approximate nearest neighbor search techniques in large-scale image retrieval. However, for large-scale video search, most of the existing hashing methods mainly focus on the visual content contained in the still frames, without considering their temporal relations. Therefore, they usually suffer greatly from the insufficient capability of capturing the intrinsic video similarities, from both the visual and the temporal aspects. To address the problem, we propose a temporal binary coding solution in an unsupervised manner, which simultaneously considers the intrinsic relations among the visual content and the temporal consistency among the successive frames. To capture the inherent data similarities among videos, we adopt the sparse, nonnegative feature to characterize the common local visual content and approximate their intrinsic similarities using a low-rank matrix. Then a standard graph-based loss is adopted to guarantee that the learnt hash codes can well preserve the similarities. Furthermore, we introduce a subspace rotation to model the small variation among the successive frames, and thus essentially preserve the temporal consistency in Hamming space. Finally, we formulate the video hashing problem as a joint learning of the binary codes, the hash functions and the temporal variation, and devise an alternating optimization algorithm that enjoys fast training and discriminative hash functions. Extensive experiments on three large video datasets demonstrate the proposed method significantly outperforms a number of state-of-the-art hashing methods.
- Liangliang Cao, Zhenguo Li, Yadong Mu, and Shih-Fu Chang. 2012. Submodular Video Hashing: A Unified Framework Towards Video Pooling and Indexing ACM MM. 299--308. Google ScholarDigital Library
- Jian Cheng, Cong Leng, Jiaxiang Wu, Hainan Cui, and Hanqing Lu. 2014. Fast and Accurate Image Matching with Cascade Hashing for 3D Reconstruction IEEE CVPR. 4321--4328. Google ScholarDigital Library
- Mayur Datar, Nicole Immorlica, Piotr Indyk, and Vahab S. Mirrokni. 2004. Locality-sensitive hashing scheme based on p-stable distributions SCG. 253--262. Google ScholarDigital Library
- Thomas Dean, Mark Ruzon, Mark Segal, Jon Shlens, Sudheendra Vijayanarasimhan, and Jay Yagnik. 2013. Fast, Accurate Detection of 100,000 Object Classes on a Single Machine IEEE CVPR. 1--8.Google Scholar
- Yunchao Gong and S. Lazebnik. 2011. Iterative quantization: A procrustean approach to learning binary codes IEEE CVPR. 817--824. Google ScholarDigital Library
- Junfeng He, Jinyuan Feng, Xianglong Liu, Tao Cheng, Tai-Hsu Lin, Hyunjin Chung, and Shih-Fu Chang. 2012. Mobile Product Search with Bag of Hash Bits and Boundary Reranking IEEE CVPR. 3005--3012. Google ScholarDigital Library
- Kaiming He, Fang Wen, and Jian Sun. 2013. K-Means Hashing: An Affinity-Preserving Quantization Method for Learning Binary Compact Codes. In IEEE CVPR. 2938--2945. Google ScholarDigital Library
- Jae-Pil Heo, Youngwoon Lee, Junfeng He, Shih-Fu Chang, and Sung-Eui Yoon. 2012. Spherical hashing IEEE CVPR. 2957--2964. Google ScholarDigital Library
- Piotr Indyk and Rajeev Motwani. 1998. Approximate nearest neighbors: towards removing the curse of dimensionality ACM STOC. 604--613. Google ScholarDigital Library
- Prateek Jain, Sudheendra Vijayanarasimhan, and Kristen Grauman. 2010. Hashing Hyperplane Queries to Near Points with Applications to Large-Scale Active Learning. Advances in Neural Information Processing Systems. 928--936. Google ScholarDigital Library
- X. Li, G. Lin, C. Shen, A. van den Hengel, and A. Dick. 2013. Learning hash functions using column generation. ICML. Google ScholarDigital Library
- Yan Li, Ruiping Wang, Zhiwu Huang, Shiguang Shan, and Xilin Chen. 2015. Face video retrieval with image query via hashing across Euclidean space and Riemannian manifold. IEEE CVPR Vol. 00 (2015), 4758--4767.Google Scholar
Index Terms
Temporal Binary Coding for Large-Scale Video Search
Recommendations
A Fast k-Nearest Neighbor Search Using Query-Specific Signature Selection
CIKM '15: Proceedings of the 24th ACM International on Conference on Information and Knowledge Managementk-nearest neighbor (k-NN) search aims at finding k points nearest to a query point in a given dataset. k-NN search is important in various applications, but it becomes extremely expensive in a high-dimensional large dataset. To address this performance ...
Random Binary Search Trees for approximate nearest neighbour search in binary spaces
AbstractApproximate nearest neighbour (ANN) search is one of the most important problems in numerous computer science applications, including data mining, machine learning and computer vision. In this paper, we address the problem of ANN for ...
Graphical abstractDisplay Omitted
Highlights- Random Binary Search Trees (RBST) are a relatively simple yet powerful ANN method.
Query-Adaptive Hash Code Ranking for Fast Nearest Neighbor Search
MM '14: Proceedings of the 22nd ACM international conference on MultimediaRecently hash-based nearest neighbor search has become attractive in many applications due to its compressed storage and fast query speed. However, the quantization in the hashing process usually degenerates its discriminative power when using Hamming ...
Comments