2019
DOI: 10.1609/aaai.v33i01.33014400
|View full text |Cite
|
Sign up to set email alerts
|

Ranking-Based Deep Cross-Modal Hashing

Abstract: Cross-modal hashing has been receiving increasing interests for its low storage cost and fast query speed in multi-modal data retrievals. However, most existing hashing methods are based on hand-crafted or raw level features of objects, which may not be optimally compatible with the coding process. Besides, these hashing methods are mainly designed to handle simple pairwise similarity. The complex multilevel ranking semantic structure of instances associated with multiple labels has not been well explored yet.… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
22
0

Year Published

2020
2020
2022
2022

Publication Types

Select...
5
2
2

Relationship

2
7

Authors

Journals

citations
Cited by 63 publications
(22 citation statements)
references
References 13 publications
0
22
0
Order By: Relevance
“…Like single-modal hashing methods which are based on a structure preserving criterion, existing cross-modal hashing can be categorized into three types: pairwise [46], [20], [33], [28], [19], [32], [9], [23], [8], [14], [4], multi-wise [37], [42], [26], and implicit similarity preserving [15], [34]. Semantic correlation maximization (SCM) [46] optimizes the hashing functions by maximizing the correlation between two modalities with respect to the pairwise semantic similarity.…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…Like single-modal hashing methods which are based on a structure preserving criterion, existing cross-modal hashing can be categorized into three types: pairwise [46], [20], [33], [28], [19], [32], [9], [23], [8], [14], [4], multi-wise [37], [42], [26], and implicit similarity preserving [15], [34]. Semantic correlation maximization (SCM) [46] optimizes the hashing functions by maximizing the correlation between two modalities with respect to the pairwise semantic similarity.…”
Section: Related Workmentioning
confidence: 99%
“…Deep Cross-Modal Hashing (DCMH) [13] combines hashing learning and deep feature learning by preserving the semantic similarity between modalities. Rankingbased Deep Cross-modal Hashing (RDCMH) [26] preserves the multi-level semantic similarity order between labeled and unlabeled multi-label samples for cross-modal hashing. Deep semantic-preserving ordinal hashing (DSPOH) [14] adopts deep neural networks to learn hashing functions by exploring the ranking structure.…”
Section: Related Workmentioning
confidence: 99%
“…We collected the multiple features of these images from [53], where each image is represented by six representative feature views: HUE, SIFT, GIST, HSV, RGB and LAB. Each sample in Mirflicker 2 and Nus-wide 3 consists of an image and textual tags, we construct the two views (image and text) according to [54]. For each dataset, we randomly sample 30% data for training and use the remaining 70% data for testing (unlabeled data).…”
Section: A Experimental Setupmentioning
confidence: 99%
“…Song et al [17] combined global context with locally-guided features with multi-head selfattention and residual learning to improve cross-modal representation. Liu et al [18] proposed ranking-based deep crossmodal hashing method that integrates the semantic ranking information.…”
Section: Related Workmentioning
confidence: 99%