ABSTRACT
Subspace representations have been widely applied for videos in many tasks. In particular, the subspace-based query-by-image video retrieval (QBIVR), facing high challenges on similarity-preserving measurements and efficient retrieval schemes, urgently needs considerable research attention. In this paper, we propose a novel subspace-based QBIVR framework to enable efficient video search. We first define a new geometry-preserving distance metric to measure the image-to-video distance, which transforms the QBIVR task to be the Maximum Inner Product Search (MIPS) problem. The merit of this distance metric lies in that it helps to preserve the genuine geometric relationship between query images and database videos to the greatest extent. To boost the efficiency of solving the MIPS problem, we introduce two asymmetric hashing schemes which can bridge the domain gap of images and videos properly. The first approach, termed Inner-product Binary Coding (IBC), achieves high-quality binary codes by learning the binary codes and coding functions simultaneously without continuous relaxations. The other one, Bilinear Binary Coding (BBC) approach, employs compact bilinear projections instead of a single large projection matrix to further improve the retrieval efficiency. Extensive experiments on four real-world video datasets verify the effectiveness of our proposed approaches, as compared to the state-of-the-art methods.
- Ronen Basri, Tal Hassner, and Lihi Zelnik-Manor. 2011. Approximate Nearest Subspace Search. TPAMI, Vol. 33, 2 (2011), 266--278. Google ScholarDigital Library
- Martin Bäuml, Makarand Tapaswi, and Rainer Stiefelhagen. 2013. Semi-supervised Learning with Constraints for Person Identification in Multimedia Data CVPR. 3602--3609. Google ScholarDigital Library
- Andre F. de Araújo, Jason Chaves, Roland Angst, and Bernd Girod. 2015. Temporal aggregation for large-scale query-by-image video retrieval ICIP. 1519--1522.Google Scholar
- Andre F. de Araújo, Mina Makar, Vijay Chandrasekhar, David M. Chen, Sam S. Tsai, Huizhong Chen, Roland Angst, and Bernd Girod. 2014. Efficient video search using image queries. In ICIP. 3082--3086.Google Scholar
- Guiguang Ding, Yuchen Guo, and Jile Zhou. 2014. Collective Matrix Factorization Hashing for Multimodal Data CVPR. 2083--2090. Google ScholarDigital Library
- Yunchao Gong, Sanjiv Kumar, Henry A. Rowley, and Svetlana Lazebnik. 2013 a. Learning Binary Codes for High-Dimensional Data Using Bilinear Projections CVPR. 484--491. Google ScholarDigital Library
- Yunchao Gong, Sanjiv Kumar, Vishal Verma, and Svetlana Lazebnik. 2012. Angular Quantization-based Binary Codes for Fast Similarity Search NIPS. 1205--1213. Google ScholarDigital Library
- Yunchao Gong, Svetlana Lazebnik, Albert Gordo, and Florent Perronnin. 2013 b. Iterative Quantization: A Procrustean Approach to Learning Binary Codes for Large-Scale Image Retrieval. TPAMI, Vol. 35, 12 (2013), 2916--2929. Google ScholarDigital Library
- Richang Hong, Yang Yang, Meng Wang, and Xian-Sheng Hua. 2015. Learning Visual Semantic Relationships for Efficient Visual Retrieval. TBD, Vol. 1, 4 (2015), 152--161.Google ScholarCross Ref
- Yiqun Hu, Ajmal S. Mian, and Robyn A. Owens. 2011. Sparse approximated nearest points for image set classification CVPR. 121--128. Google ScholarDigital Library
- Zi Huang, Heng Tao Shen, Jie Shao, Xiaofang Zhou, and Bin Cui. 2009. Bounded coordinate system indexing for real-time video clip search. TOIS, Vol. 27, 3 (2009), 17:1--17:33. Google ScholarDigital Library
- Jianqiu Ji, Jianmin Li, Qi Tian, Shuicheng Yan, and Bo Zhang. 2015. Angular-Similarity-Preserving Binary Signatures for Linear Subspaces. TIP, Vol. 24, 11 (2015), 4372--4380.Google ScholarDigital Library
- Jianqiu Ji, Jianmin Li, Shuicheng Yan, Qi Tian, and Bo Zhang. 2014. Similarity-Preserving Binary Signature for Linear Subspaces AAAI. 2767--2772. Google ScholarDigital Library
- Qing-Yuan Jiang and Wu-Jun Li. 2015. Scalable Graph Hashing with Feature Transformation IJCAI. 2248--2254. Google ScholarDigital Library
- Yu-Gang Jiang, Zuxuan Wu, Jun Wang, Xiangyang Xue, and Shih-Fu Chang. 2015. Exploiting Feature and Class Relationships in Video Categorization with Regularized Deep Neural Networks. CoRR Vol. abs/1502.07209 (2015).Google Scholar
- Hanjiang Lai, Yan Pan, Ye Liu, and Shuicheng Yan. 2015. Simultaneous feature learning and hash coding with deep neural networks CVPR. 3270--3278.Google Scholar
- Alan J. Laub. 2005. Matrix analysis - for scientists and engineers. SIAM. Google ScholarDigital Library
- Wu-Jun Li, Sheng Wang, and Wang-Cheng Kang. 2016. Feature Learning Based Deep Supervised Hashing with Pairwise Labels IJCAI. 1711--1717. 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 CVPR. 4758--4767.Google Scholar
- Zijia Lin, Guiguang Ding, Mingqing Hu, and Jianmin Wang. 2015. Semantics-preserving hashing for cross-view retrieval CVPR. 3864--3872.Google Scholar
- Venice Erin Liong, Jiwen Lu, Gang Wang, Pierre Moulin, and Jie Zhou. 2015. Deep hashing for compact binary codes learning. In CVPR. 2475--2483.Google Scholar
- Wei Liu, Jun Wang, Rongrong Ji, Yu-Gang Jiang, and Shih-Fu Chang. 2012. Supervised hashing with kernels. In CVPR. 2074--2081. Google ScholarDigital Library
- Wei Liu, Jun Wang, Sanjiv Kumar, and Shih-Fu Chang. 2011. Hashing with Graphs ICML. 1--8. Google ScholarDigital Library
- Mohammad Norouzi and David J. Fleet. 2011. Minimal Loss Hashing for Compact Binary Codes. In ICML. 353--360. Google ScholarDigital Library
- Florent Perronnin, Jorge Sánchez, and Thomas Mensink. 2010. Improving the Fisher Kernel for Large-Scale Image Classification ECCV. 143--156. Google ScholarDigital Library
- Mohammad Rastegari, Jonghyun Choi, Shobeir Fakhraei, Hal Daumé III, and Larry S. Davis. 2013. Predictable Dual-View Hashing. In ICML. 1328--1336. Google ScholarDigital Library
- Fumin Shen, Wei Liu, Shaoting Zhang, Yang Yang, and Heng Tao Shen. 2015. Learning Binary Codes for Maximum Inner Product Search ICCV. 4148--4156. Google ScholarDigital Library
- Fumin Shen, Xiang Zhou, Yang Yang, Jingkuan Song, Heng Tao Shen, and Dacheng Tao. 2016. A Fast Optimization Method for General Binary Code Learning. TIP, Vol. 25, 12 (2016), 5610--5621. Google ScholarDigital Library
- Anshumali Shrivastava and Ping Li. 2014. Asymmetric LSH (ALSH) for Sublinear Time Maximum Inner Product Search (MIPS) NIPS. 2321--2329. Google ScholarDigital Library
- Anshumali Shrivastava and Ping Li. 2015. Improved Asymmetric Locality Sensitive Hashing (ALSH) for Maximum Inner Product Search (MIPS). In UAI. 812--821. Google ScholarDigital Library
- Jingkuan Song, Yang Yang, Yi Yang, Zi Huang, and Heng Tao Shen. 2013. Inter-media hashing for large-scale retrieval from heterogeneous data sources SIGMOD. 785--796. Google ScholarDigital Library
- Raviteja Vemulapalli, Jaishanker K. Pillai, and Rama Chellappa. 2013. Kernel Learning for Extrinsic Classification of Manifold Features CVPR. 1782--1789. Google ScholarDigital Library
- Ruiping Wang and Xilin Chen. 2009. Manifold Discriminant Analysis. In CVPR. 429--436.Google Scholar
- Zhongwen Xu, Yi Yang, and Alexander G. Hauptmann. 2015. A discriminative CNN video representation for event detection CVPR. 1798--1807.Google Scholar
- Yang Yang, Yadan Luo, Weilun Chen, Fumin Shen, Jie Shao, and Heng Tao Shen. 2016. Zero-Shot Hashing via Transferring Supervised Knowledge ACM MM. 1286--1295. Google ScholarDigital Library
- Yang Yang, Fumin Shen, Heng Tao Shen, Hanxi Li, and Xuelong Li. 2015. Robust Discrete Spectral Hashing for Large-Scale Image Semantic Indexing. TBD, Vol. 1, 4 (2015), 162--171.Google ScholarCross Ref
- Yang Yang, Zheng-Jun Zha, Yue Gao, Xiaofeng Zhu, and Tat-Seng Chua. 2014. Exploiting Web Images for Semantic Video Indexing Via Robust Sample-Specific Loss. TMM, Vol. 16, 6 (2014), 1677--1689.Google ScholarCross Ref
- Litao Yu, Yang Yang, Zi Huang, Peng Wang, Jingkuan Song, and Heng Tao Shen. 2016. Web Video Event Recognition by Semantic Analysis from Ubiquitous Documents. TIP, Vol. 25, 12, 5689--5701. Google ScholarDigital Library
- Dongqing Zhang and Wu-Jun Li. 2014. Large-Scale Supervised Multimodal Hashing with Semantic Correlation Maximization AAAI. 2177--2183. Google ScholarDigital Library
- Yi Zhen and Dit-Yan Yeung. 2012. A probabilistic model for multimodal hash function learning SIGKDD. 940--948. Google ScholarDigital Library
- Jile Zhou, Guiguang Ding, and Yuchen Guo. 2014. Latent semantic sparse hashing for cross-modal similarity search SIGIR. 415--424. Google ScholarDigital Library
- Xiaofeng Zhu, Zi Huang, Heng Tao Shen, and Xin Zhao. 2013. Linear cross-modal hashing for efficient multimedia search ACM MM. 143--152. Google ScholarDigital Library
Index Terms
- Efficient Binary Coding for Subspace-based Query-by-Image Video Retrieval
Recommendations
Binary Coding by Matrix Classifier for Efficient Subspace Retrieval
ICMR '18: Proceedings of the 2018 ACM on International Conference on Multimedia RetrievalFast retrieval in large-scale database with high-dimensional subspaces is an important task in many applications, such as image retrieval, video retrieval and visual recognition. This can be facilitated by approximate nearest subspace (ANS) retrieval ...
Image retrieval based on incremental subspace learning
Many problems in information processing involve some form of dimensionality reduction, such as face recognition, image/text retrieval, data visualization, etc. The typical linear dimensionality reduction algorithms include principal component analysis (...
Learning a Maximum Margin Subspace for Image Retrieval
One of the fundamental problems in Content-Based Image Retrieval (CBIR) has been the gap been low level visual features and high level semantic concepts. To narrow down this gap, relevance feedback is introduced into image retrieval. With the user ...
Comments