Effective Multi-Modal Retrieval based on Stacked Auto-Encoders

Summary: Proposes an effective multi-modal retrieval framework using stacked auto-encoders to map heterogeneous media features into a shared low-dimensional space for cross-modal similarity search. Introduces a novel objective that models intra- and inter-modal semantics with minimal prior knowledge, and uses mini-batch, memory-efficient training, achieving state-of-the-art accuracy on real datasets. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: 11130
Venue: VLDB
Year: 2014
Pagerank: 5.093636e-05
Overall Rank: 12,214 | 16.21%
DOI: 10.14778/2732296.2732300

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

1. Wei Wang (National University of Singapore)
2. Beng Chin Ooi (National University of Singapore)
3. Xiaoyan Yang (Advanced Digital Sciences Center)
4. Dongxiang Zhang (National University of Singapore)
5. Yueting Zhuang (Zhejiang University)

BibTeX Citation

@article{wang_vldb14,
        title = {{Effective Multi-Modal Retrieval based on Stacked Auto-Encoders}},
        author = {Wang, Wei and Ooi, Beng Chin and Yang, Xiaoyan and Zhang, Dongxiang and Zhuang, Yueting},
        journal = {PVLDB},
        series = {{VLDB} '14},
        volume = {7},
        number = {8},
        pages = {649--660},
        doi = {10.14778/2732296.2732300},
        url = {https://doi.org/10.14778/2732296.2732300},
        year = {2014}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank

Outgoing Citations (Sorted by Pagerank)

Showing 2 of 2 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
46	A Quantitative Analysis and Performance Study for Similarity-Search Methods in High-Dimensional Spaces	1998	VLDB	0.00044853085
4,060	Inter-Media Hashing for Large-scale Retrieval from Heterogeneous Data Sources	2013	SIGMOD	6.9322681e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	12,972	Facilitating Multimedia Database Exploration through Visual Interfaces and Perpetual Query Reformulations	1997	VLDB
2	11,378	Effectiveness Perspectives and a Deep Relevance Model for Spatial Keyword Queries	2023	SIGMOD
3	1,153	Efficient Diversity-Aware Search	2011	SIGMOD
4	13,779	Studying Interaction Methodologies in Video Retrieval	2008	VLDB
5	9,174	Qcluster: Relevance Feedback Using Adaptive Clustering for Content-Based Image Retrieval	2003	SIGMOD
6	3,353	Efficient EMD-based Similarity Search in Multimedia Databases via Flexible Dimensionality Reduction	2008	SIGMOD
7	4,060	Inter-Media Hashing for Large-scale Retrieval from Heterogeneous Data Sources	2013	SIGMOD
8	3,365	Spatial and Temporal Constrained Ranked Retrieval over Videos	2022	VLDB
9	12,371	Effective Data Co-Reduction for Multimedia Similarity Search	2011	SIGMOD
10	8,343	An Interactive Multi-modal Query Answering System with Retrieval-Augmented Large Language Models	2024	VLDB