Unsupervised video hashing with multi-granularity contextualization and multi-structure preservation

Unsupervised video hashing typically aims to learn a compact binary vector to represent complex video content without using manual annotations. Existing unsupervised hashing methods generally suffer from incomplete exploration of various perspective dependencies (e.g., long-range and short-range) an...

Full description

Saved in:
Bibliographic Details
Main Authors: HAO, Yanbin, DUAN, Jingru, ZHANG, Hao, ZHU, Bin, ZHOU, Pengyuan, HE, Xiangnan
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2022
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/9014
https://ink.library.smu.edu.sg/context/sis_research/article/10017/viewcontent/mm22_video_hashing.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-10017
record_format dspace
spelling sg-smu-ink.sis_research-100172024-07-25T08:11:52Z Unsupervised video hashing with multi-granularity contextualization and multi-structure preservation HAO, Yanbin DUAN, Jingru ZHANG, Hao ZHU, Bin ZHOU, Pengyuan HE, Xiangnan Unsupervised video hashing typically aims to learn a compact binary vector to represent complex video content without using manual annotations. Existing unsupervised hashing methods generally suffer from incomplete exploration of various perspective dependencies (e.g., long-range and short-range) and data structures that exist in visual contents, resulting in less discriminative hash codes. In this paper, we propose aMulti-granularity Contextualized and Multi-Structure preserved Hashing (MCMSH) method, exploring multiple axial contexts for discriminative video representation generation and various structural information for unsupervised learning simultaneously. Specifically, we delicately design three self-gating modules to separately model three granularities of dependencies (i.e., long/middle/short-range dependencies) and densely integrate them into MLP-Mixer for feature contextualization, leading to a novel model MC-MLP. To facilitate unsupervised learning, we investigate three kinds of data structures, including clusters, local neighborhood similarity structure, and inter/intra-class variations, and design a multi-objective task to train MC-MLP. These data structures show high complementarities in hash code learning. We conduct extensive experiments using three video retrieval benchmark datasets, demonstrating that our MCMSH not only boosts the performance of the backbone MLP-Mixer significantly but also outperforms the competing methods notably. Code is available at: https://github.com/haoyanbin918/MCMSH. 2022-10-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/9014 info:doi/10.1145/3503161.3547836 https://ink.library.smu.edu.sg/context/sis_research/article/10017/viewcontent/mm22_video_hashing.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 Hashing feature contextualization unsupervised learning video retrieval Graphics and Human Computer Interfaces
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Hashing
feature contextualization
unsupervised learning
video retrieval
Graphics and Human Computer Interfaces
spellingShingle Hashing
feature contextualization
unsupervised learning
video retrieval
Graphics and Human Computer Interfaces
HAO, Yanbin
DUAN, Jingru
ZHANG, Hao
ZHU, Bin
ZHOU, Pengyuan
HE, Xiangnan
Unsupervised video hashing with multi-granularity contextualization and multi-structure preservation
description Unsupervised video hashing typically aims to learn a compact binary vector to represent complex video content without using manual annotations. Existing unsupervised hashing methods generally suffer from incomplete exploration of various perspective dependencies (e.g., long-range and short-range) and data structures that exist in visual contents, resulting in less discriminative hash codes. In this paper, we propose aMulti-granularity Contextualized and Multi-Structure preserved Hashing (MCMSH) method, exploring multiple axial contexts for discriminative video representation generation and various structural information for unsupervised learning simultaneously. Specifically, we delicately design three self-gating modules to separately model three granularities of dependencies (i.e., long/middle/short-range dependencies) and densely integrate them into MLP-Mixer for feature contextualization, leading to a novel model MC-MLP. To facilitate unsupervised learning, we investigate three kinds of data structures, including clusters, local neighborhood similarity structure, and inter/intra-class variations, and design a multi-objective task to train MC-MLP. These data structures show high complementarities in hash code learning. We conduct extensive experiments using three video retrieval benchmark datasets, demonstrating that our MCMSH not only boosts the performance of the backbone MLP-Mixer significantly but also outperforms the competing methods notably. Code is available at: https://github.com/haoyanbin918/MCMSH.
format text
author HAO, Yanbin
DUAN, Jingru
ZHANG, Hao
ZHU, Bin
ZHOU, Pengyuan
HE, Xiangnan
author_facet HAO, Yanbin
DUAN, Jingru
ZHANG, Hao
ZHU, Bin
ZHOU, Pengyuan
HE, Xiangnan
author_sort HAO, Yanbin
title Unsupervised video hashing with multi-granularity contextualization and multi-structure preservation
title_short Unsupervised video hashing with multi-granularity contextualization and multi-structure preservation
title_full Unsupervised video hashing with multi-granularity contextualization and multi-structure preservation
title_fullStr Unsupervised video hashing with multi-granularity contextualization and multi-structure preservation
title_full_unstemmed Unsupervised video hashing with multi-granularity contextualization and multi-structure preservation
title_sort unsupervised video hashing with multi-granularity contextualization and multi-structure preservation
publisher Institutional Knowledge at Singapore Management University
publishDate 2022
url https://ink.library.smu.edu.sg/sis_research/9014
https://ink.library.smu.edu.sg/context/sis_research/article/10017/viewcontent/mm22_video_hashing.pdf
_version_ 1814047692713623552