Proceedings Article10.1145/3123266.3123392
Efficient Binary Coding for Subspace-based Query-by-Image Video Retrieval
Ruicong Xu,Yang Yang,Fumin Shen,Ning Xie,Heng Tao Shen +4 more
- 19 Oct 2017
- pp 1354-1362
16
TL;DR: A new geometry-preserving distance metric is defined to measure the image-to-video distance, which transforms the QBIVR task to be the Maximum Inner Product Search (MIPS) problem and introduces two asymmetric hashing schemes which can bridge the domain gap of images and videos properly.
read more
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.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Learning binary code for fast nearest subspace search
TL;DR: A new approach for hashing-based ANS search which can directly binarize a subspace without transforming it into a vector, and simultaneously leverages the learned binary codes for subspaces to train matrix classifiers as hash functions.
75
Discriminative Deep Metric Learning for Asymmetric Discrete Hashing
TL;DR: A novel discriminative deep metric learning approach for asymmetric discrete hashing (ADMH) approach for supervised hashing learning and extensive experiments show that the proposed asymmetric deep hashing method outperforms the existing hashing methods.
38
•Proceedings Article
Activity Image-to-Video Retrieval by Disentangling Appearance and Motion
Liu Liu,Jiangtong Li,Li Niu,Ruicong Xu,Liqing Zhang +4 more
- 18 May 2021
TL;DR: Wang et al. as discussed by the authors proposed a Motion-assisted Activity Proposal-based Image-to-Video Retrieval (MAP-IVR) approach to disentangle the video features into motion features and appearance features and obtain appearance features from the images.
A Proposal-Based Approach for Activity Image-to-Video Retrieval
Ruicong Xu,Li Niu,Jianfu Zhang,Liqing Zhang +3 more
- 03 Apr 2020
TL;DR: APIVR as discussed by the authors incorporates multi-instance learning into cross-modal retrieval framework to address the proposal noise issue and proposes geometry-aware triplet loss based on point-to-subspace distance to preserve the structural information of activity proposals.
Collaborative Learning for Extremely Low Bit Asymmetric Hashing
TL;DR: Multi-head Asymmetric Hashing (MAH) as mentioned in this paper was proposed for low-bit hash codes by jointly distilling bit-specific and informative representations for a group of pre-defined code lengths.
15
References
Improving the fisher kernel for large-scale image classification
Florent Perronnin,Jorge Sanchez,Thomas Mensink +2 more
- 05 Sep 2010
TL;DR: In an evaluation involving hundreds of thousands of training images, it is shown that classifiers learned on Flickr groups perform surprisingly well and that they can complement classifier learned on more carefully annotated datasets.
Iterative Quantization: A Procrustean Approach to Learning Binary Codes for Large-Scale Image Retrieval
TL;DR: This paper addresses the problem of learning similarity-preserving binary codes for efficient similarity search in large-scale image collections by proposing a simple and efficient alternating minimization algorithm, dubbed iterative quantization (ITQ), and demonstrating an application of ITQ to learning binary attributes or "classemes" on the ImageNet data set.
2.1K
Supervised hashing with kernels
Wei Liu,Jun Wang,Rongrong Ji,Yu-Gang Jiang,Shih-Fu Chang +4 more
- 16 Jun 2012
TL;DR: A novel kernel-based supervised hashing model which requires a limited amount of supervised information, i.e., similar and dissimilar data pairs, and a feasible training cost in achieving high quality hashing, and significantly outperforms the state-of-the-arts in searching both metric distance neighbors and semantically similar neighbors is proposed.
Simultaneous feature learning and hash coding with deep neural networks
Hanjiang Lai,Yan Pan,Ye Liu,Shuicheng Yan +3 more
- 07 Jun 2015
TL;DR: Extensive evaluations on several benchmark image datasets show that the proposed simultaneous feature learning and hash coding pipeline brings substantial improvements over other state-of-the-art supervised or unsupervised hashing methods.
•Book
Matrix Analysis for Scientists and Engineers
Alan J. Laub
- 01 Dec 2004
TL;DR: This book discusses vector spaces, linear transformations, eigenvalues and eigenvectors, and the singular value decomposition in the context of Kronecker products.
1K