Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

10-2022

Abstract

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.

Keywords

Hashing, feature contextualization, unsupervised learning, video retrieval

Discipline

Graphics and Human Computer Interfaces

Research Areas

Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

Proceedings of the 30th ACM International Conference on Multimedia, Lisboa, Portugal, 2022 October 10 - 14

First Page

3754

Last Page

3763

ISBN

9781450392037

Identifier

10.1145/3503161.3547836

Publisher

ACM

City or Country

New York

Additional URL

https://doi.org/10.1145/3503161.3547836

Share

COinS