Efficient unsupervised video hashing with contextual modeling and structural controlling

The most important effect of the video hashing technique is to support fast retrieval, which is benefiting from the high efficiency of binary calculation. Current video hash approaches are thus mainly targeted at learning compact binary codes to represent video content accurately. However, they may...

Full description

Saved in:
Bibliographic Details
Main Authors: DUAN, Jingru, HAO, Yanbin, ZHU, Bin, CHENG, Lechao, ZHOU, Pengyuan, WANG, Xiang
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2024
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/8723
https://ink.library.smu.edu.sg/context/sis_research/article/9726/viewcontent/TMM_zhu24_av.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-9726
record_format dspace
spelling sg-smu-ink.sis_research-97262024-04-18T07:36:04Z Efficient unsupervised video hashing with contextual modeling and structural controlling DUAN, Jingru HAO, Yanbin ZHU, Bin CHENG, Lechao ZHOU, Pengyuan WANG, Xiang The most important effect of the video hashing technique is to support fast retrieval, which is benefiting from the high efficiency of binary calculation. Current video hash approaches are thus mainly targeted at learning compact binary codes to represent video content accurately. However, they may overlook the generation efficiency for hash codes, i.e., designing lightweight neural networks. This paper proposes an method, which is not only for computing compact hash codes but also for designing a lightweight deep model. Specifically, we present an MLP-based model, where the video tensor is split into several groups and multiple axial contexts are explored to separately refine them in parallel. The axial contexts are referred to as the dynamics aggregated from different axial scales, including long/middle/short-range dependencies. The group operation significantly reduces the computational cost of the MLP backbone. Moreover, to achieve compact video hash codes, three structural losses are utilized. As demonstrated by the experiment, the three structures are highly complementary for approximating the real data structure. We conduct extensive experiments on three benchmark datasets for the unsupervised video hashing task and show the superior trade-off between performance and computational cost of our EUVH to the state of the arts. 2024-01-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/8723 info:doi/10.1109/TMM.2024.3368924 https://ink.library.smu.edu.sg/context/sis_research/article/9726/viewcontent/TMM_zhu24_av.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Codes Computational modeling Context modeling Data Structure Data structures Deep Neural Network Feature extraction Hash functions Large-scale retrieval Transformers Video hashing Graphics and Human Computer Interfaces Numerical Analysis and Scientific Computing
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Codes
Computational modeling
Context modeling
Data Structure
Data structures
Deep Neural Network
Feature extraction
Hash functions
Large-scale retrieval
Transformers
Video hashing
Graphics and Human Computer Interfaces
Numerical Analysis and Scientific Computing
spellingShingle Codes
Computational modeling
Context modeling
Data Structure
Data structures
Deep Neural Network
Feature extraction
Hash functions
Large-scale retrieval
Transformers
Video hashing
Graphics and Human Computer Interfaces
Numerical Analysis and Scientific Computing
DUAN, Jingru
HAO, Yanbin
ZHU, Bin
CHENG, Lechao
ZHOU, Pengyuan
WANG, Xiang
Efficient unsupervised video hashing with contextual modeling and structural controlling
description The most important effect of the video hashing technique is to support fast retrieval, which is benefiting from the high efficiency of binary calculation. Current video hash approaches are thus mainly targeted at learning compact binary codes to represent video content accurately. However, they may overlook the generation efficiency for hash codes, i.e., designing lightweight neural networks. This paper proposes an method, which is not only for computing compact hash codes but also for designing a lightweight deep model. Specifically, we present an MLP-based model, where the video tensor is split into several groups and multiple axial contexts are explored to separately refine them in parallel. The axial contexts are referred to as the dynamics aggregated from different axial scales, including long/middle/short-range dependencies. The group operation significantly reduces the computational cost of the MLP backbone. Moreover, to achieve compact video hash codes, three structural losses are utilized. As demonstrated by the experiment, the three structures are highly complementary for approximating the real data structure. We conduct extensive experiments on three benchmark datasets for the unsupervised video hashing task and show the superior trade-off between performance and computational cost of our EUVH to the state of the arts.
format text
author DUAN, Jingru
HAO, Yanbin
ZHU, Bin
CHENG, Lechao
ZHOU, Pengyuan
WANG, Xiang
author_facet DUAN, Jingru
HAO, Yanbin
ZHU, Bin
CHENG, Lechao
ZHOU, Pengyuan
WANG, Xiang
author_sort DUAN, Jingru
title Efficient unsupervised video hashing with contextual modeling and structural controlling
title_short Efficient unsupervised video hashing with contextual modeling and structural controlling
title_full Efficient unsupervised video hashing with contextual modeling and structural controlling
title_fullStr Efficient unsupervised video hashing with contextual modeling and structural controlling
title_full_unstemmed Efficient unsupervised video hashing with contextual modeling and structural controlling
title_sort efficient unsupervised video hashing with contextual modeling and structural controlling
publisher Institutional Knowledge at Singapore Management University
publishDate 2024
url https://ink.library.smu.edu.sg/sis_research/8723
https://ink.library.smu.edu.sg/context/sis_research/article/9726/viewcontent/TMM_zhu24_av.pdf
_version_ 1814047494349258752