Large-Scale Video Hashing via Structure Learning

Ye, Guangnan; Liu, Dong; Wang, Jun; Chang, Shih-Fu

doi:10.1109/iccv.2013.282

Cited by 72 publications

(42 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The goal of large-scale retrieval algorithms is to support efficient and accurate querying into the collection under memory and time constraints. Methods for large-scale retrieval may be divided into two main groups: hashing methods [3,4,6,9,12,13,15,20,21,22,23] and lookup-based methods [2,7,8,10,16]. Hashing methods learn a mapping from high-dimensional feature descriptors to compact binary codes such that the locality relationships in the original feature space are closely preserved in the reduced Hamming space.…”

Section: Introductionmentioning

confidence: 99%

Bank of Quantization Models: A Data-Specific Approach to Learning Binary Codes for Large-Scale Retrieval Applications

Tung

Martínez

Hoos

et al. 2015

2015 IEEE Winter Conference on Applications of Computer Vision

View full text Add to dashboard Cite

We explore a novel paradigm in learning binary codes for large-scale image retrieval applications. Instead of learning a single globally optimal quantization model as in previous approaches, we encode the database points in a data-specific manner using a bank of quantization models. Each individual database point selects the quantization model that minimizes its individual quantization error. We apply the idea of a bank of quantization models to dataindependent and data-driven hashing methods for learning binary codes, obtaining state-of-the-art performance on three benchmark datasets.

show abstract

Section: Introductionmentioning

confidence: 99%

Bank of Quantization Models: A Data-Specific Approach to Learning Binary Codes for Large-Scale Retrieval Applications

Tung

Martínez

Hoos

et al. 2015

2015 IEEE Winter Conference on Applications of Computer Vision

View full text Add to dashboard Cite

show abstract

“…A lot of hashing algorithms have been proposed for various applications, such as image and video retrieval [28,27,31,12], duplicate image detection [3], key point detection [29] and so on.…”

Section: Introductionmentioning

confidence: 99%

Iterative Multi-View Hashing for Cross Media Indexing

Jin

Ren

et al. 2014

Proceedings of the 22nd ACM International Conference on Multimedia

View full text Add to dashboard Cite

Cross media retrieval engines have gained massive popularity with rapid development of the Internet. Users may perform queries in a corpus consisting of audio, video, and textual information. To make such systems practically possible for large mount of multimedia data, two critical issues must be carefully considered: (a) reduce the storage as much as possible; (b) model the relationship of the heterogeneous media data. Recently academic community have proved that encoding the data into compact binary codes can drastically reduce the storage and computational cost. However, it is still unclear how to integrate multiple information sources properly into the binary code encoding scheme.In this paper, we study the cross media indexing problem by learning the discriminative hashing functions to map the multi-view datum into a shared hamming space. Not only meaningful withinview similarity is required to be preserved, we also incorporate the between-view correlations into the encoding scheme, where we map the similar points close together and push apart the dissimilar ones. To this end, we propose a novel hashing algorithm called Iterative Multi-View Hashing (IMVH) by taking these information into account simultaneously. To solve this joint optimization problem efficiently, we further develop an iterative scheme to deal with it by using a more flexible quantization model. In particular, an optimal alignment is learned to maintain the between-view similarity in the encoding scheme. And the binary codes are obtained by directly solving a series of binary label assignment problems without continuous relaxation to avoid the unnecessary quantization loss. In this way, the proposed algorithm not only greatly improves the retrieval accuracy but also performs strong robustness. An extensive set of experiments clearly demonstrates the superior performance of the proposed method against the state-of-the-art techniques on both multimodal and unimodal retrieval tasks.

show abstract

“…• Video Hashing with both Discriminative commonality and Temporal consistency (VHDT) [104]: An inductive structural hashing model specially designed for large-scale video retrieval, which can explore both the discriminative local visual commonality and temporal consistency. • Visual State Binary Embedding (VSBE): Our proposed model in this work.…”

Section: Comparison Of Different Binary Embedding Methodsmentioning

confidence: 99%

“…Until now there is still only a very limited number of hashing methods specifically designed for unconstrained video event retrieval. One representative hashing model is the inductive hashing via structural learning proposed by Ye et al, which is a supervised hashing model [104]. This model attempts to learn the hash functions by discriminating event classes at the video level.…”

Section: Hashingmentioning

confidence: 99%

See 1 more Smart Citation

Effective multimedia event analysis in large-scale videos

Yu¹

View full text Add to dashboard Cite

In the last decade, video content analysis has attracted increasing research interest in the fields of multimedia and computer vision. With the explosive growth of videos on the web and other multimedia sources, it is important for many applications to build effective models that can help us automatically analyse the videos. Among different video content analysis tasks, event detection, recognition, recounting and retrieval in unconstrained cases are the most challenging, because events often consist of miscellaneous spatial-temporal semantics such as various objects, human actions and scenes. In order to better analyse the events contained in videos, scholars have tried to either design powerful visual features or build effective models. However, several technical issueshave not yet been well addressed. These include, for example, how to reduce the computational complexity of the hash model training procedure for video event retrieval when given more training videos, how to integrate the spatial and temporal information well in videos for event detection, and how to make use of contextual information to enhance the model training. This thesis focuses on building effective and efficient models for video event detection, recognition and retrieval, and it contains the following four parts:The first part aims to design a generic model Max-margin adaptive model (MMA) for video pattern recognition. The MMA model adopts the advantages of semi-supervised learning and transfer learning, which can utilize both labelled and unlabelled videos for model training. It considers the data distribution consistency between labelled videos and unlabelled auxiliary videos from a statistical perspective by learning an optimal mapping function. It also broadens the geometric margin between positive-labelled videos and negative-labelled videos to improve the robustness of the model. The second part aims to build a deep spatial-temporal model for multimedia event detection (MED). In our setting, each video follows a multiple instance assumption, where its visual segments contain both spatial and temporal properties of events. Regarding these properties, we try to implement the MED system by a two-step deep training model: unsupervised recurrent video reconstruction and supervised fine-tuning, to improve the generality of the model and boost the event detection accuracy.In the third part, we propose a context based framework for web video event recognition.iii Different from content based video recognition tasks, our proposed framework considers the properties of both video content and web documents. Web videos often describe large-granular events and carry very limited textual information. In this work we first construct an event knowledge base by deeply mining the semantic information from web documents, then propose a Two-view adaptive regression model (TVAR) that explores the intrinsic correlation between the visual and textual cues of the web videos to learn reliable classifiers.In the fourth part, we set out a hashing mode...

show abstract

Large-Scale Video Hashing via Structure Learning

Cited by 72 publications

References 12 publications

Bank of Quantization Models: A Data-Specific Approach to Learning Binary Codes for Large-Scale Retrieval Applications

Bank of Quantization Models: A Data-Specific Approach to Learning Binary Codes for Large-Scale Retrieval Applications

Iterative Multi-View Hashing for Cross Media Indexing

Effective multimedia event analysis in large-scale videos

Contact Info

Product

Resources

About