Scratch

Li, Chuan-Xiang; Chen, Zhen-Duo; Zhang, Pengfei; Luo, Xin; Nie, Liqiang; Zhang, Wei; Xu, Xin-Shun

doi:10.1145/3240508.3240547

Cited by 46 publications

(2 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed LcKTLSH method is compared with nine typical and widely used baseline methods which are: CMFH [48], DCH [18], FSH [28], SCRATCH [20], EDMH [21], BATCH [22], AAH [23], FCMH [24], WASH [25]. We have set RON=0 in the experiments of baseline method WASH for fair comparison where we utilize the original label matrix for training.…”

Section: Baseline Methodsmentioning

confidence: 99%

“…For unpaired multi-modal data, generalized semantic preserving hashing (GSPH) [19] method was introduced to obtain the semantic representation through projecting the heterogeneous data into the latent Hamming space, which factorizes affinity matrix in various cross-modal scenarios. Other methods like scalable discrete matrix factorization hashing (SCRATCH) [20] and enhanced discrete multi-modal hashing (EDMH) [21] suffer from complex and inflexible optimization because of simultaneous hash codes and function learning. To overcome the above-mentioned limitations, the latent common semantic space learning was used to embed the semantic information into the discrete hash codes in scalable asymmetric discrete cross-modal hashing (BATCH) [22].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Label-consistent Kernel Transform Learning based Sparse Hashing for cross-modal retrieval

Maggu

2023

Preprint

View full text Add to dashboard Cite

Currently, there are various widely used methods for hashing-based cross modal retrieval to achieve promising performance in the information retrieval task. However, the challenge of learning discriminative representations against a heterogeneous gap in the case of multi-modal data still needs to be explored. Most existing methods directly project raw heterogeneous data linearly onto a common projection space, leading to high projection error because the semantic similarity of multi-modal data is not captured. We need the efficient feature representation of heterogeneous and multi-modal data to learn high-quality discrete hash codes and improve retrieval performance. This paper proposes a label-consistent kernel transform learning-based sparse hashing (LcKTLSH) for cross modal retrieval. Instead of projecting raw data samples, LcKTLSH learns transform and sparse coefficients suited for projection onto the kernel space, assuming each modality of a single instance has a unique hash code. The learned sparse coefficients are embedded into pre-learned hash codes, and semantic information from the similarity matrix is embedded into pre-learned hash codes to generate final hash codes. Kernel trick accounts for non-linearity in the data, and label-consistency constraint acts as the supervision term. Extensive experimental results on four benchmark datasets significantly advance over previous investigations.

show abstract

Section: Baseline Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Label-consistent Kernel Transform Learning based Sparse Hashing for cross-modal retrieval

Maggu

2023

Preprint

View full text Add to dashboard Cite

show abstract

Cross‐media search method based on complementary attention and generative adversarial network for social networks

Shi

Cheng

et al. 2021

Int J of Intelligent Sys

View full text Add to dashboard Cite

The rapid development of the social network has brought great convenience to people's lives. A large amount of cross-media big data, such as text, image, and video data, has been accumulated. A cross-media search can facilitate a quick query of information so that users can obtain helpful content for social networks. However, cross-media data suffer from semantic gaps and sparsity in social networks, which bring challenges to cross-media searches. To alleviate the semantic gaps and sparsity, we propose a crossmedia search method based on complementary attention and generative adversarial networks (CAGS).To obtain high-quality feature representations, we build a complementary attention mechanism containing the focused and unfocused features of images to realize the consistent association of cross-media data in social networks. By designing the cross-media

show abstract

Supervised Hashing with Recurrent Scaling

Bin

Wang

et al. 2019

Web and Big Data

View full text Add to dashboard Cite

Scratch

Cited by 46 publications

References 42 publications

Label-consistent Kernel Transform Learning based Sparse Hashing for cross-modal retrieval

Label-consistent Kernel Transform Learning based Sparse Hashing for cross-modal retrieval

Cross‐media search method based on complementary attention and generative adversarial network for social networks

Supervised Hashing with Recurrent Scaling

Contact Info

Product

Resources

About