Joint Feature Selection and Subspace Learning for Cross-Modal Retrieval

By Kaiye Wang, Ran He, Liang Wang, Wei Wang, Tien-Ping Tan. 2016

306 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Information Retrieval & Search, Multimodal Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Yi Yang
3. Cheng Deng
4. Xiaodan Liang
5. Heng Tao Shen
6. Xuelong Li
7. Yunchao Wei
8. Luc Van Gool

In Information Retrieval & Search

1. Liang Wang
2. Dacheng Tao
3. Cheng Deng
4. Alan Hanjalic
5. Heng Tao Shen
6. Qiyue Yin
7. Kaiye Wang
8. Lianli Gao

In Multimodal Learning

1. Heng Tao Shen
2. Xing Xu
3. Yang Yang
4. Alan Hanjalic
5. Bokun Wang
6. Shu Wu
7. Qiyue Yin
8. Liang Wang

Citations in the corpus

• Self-Supervised Learning of Visual Features through Embedding Images into Text Topic Spaces (2017, neutral): “88 JFSSL [38] 42.”
• A Comprehensive Survey on Cross-modal Retrieval (2016, methodology): “For PLS, BLM, CCA, CDFE, GMMFA, GMLDA, CCA-3V, LCFS and JFSSL, we adopt the codes provided by the authors and use the setting in [53].”
• Adversarial Cross-Modal Retrieval (2017, methodology): “A variety of cross-modal retrieval methods [5, 9, 21, 30, 31] have been proposed recently, which propose different ways of learning the common representation subspace.”
• Learning Cross-Modal Common Representations by Private–Shared Subspaces Separation (2020, background): “On the Wikipedia dataset, when the values for the three hyperparameters are too large or too small (e.g., in [10, 1000] or [0.001, 0.01]), the performance drops severely as the impact of these loss terms becomes trivial.”
• Product1M: Towards Weakly Supervised Instance-Level Product Retrieval via Cross-Modal Pretraining (2021, background): “Cross-modal retrieval [43, 12, 48, 4, 44, 8] emerges as a promising avenue for efficient indexing and searching among large-scale data with different modalities, and is widely used in search engines [2, 14], E-commerce [18, 7], to name a few.”
• Triplet-Based Deep Hashing Network for Cross-Modal Retrieval (2018, background): “graph regularization [6] [7], and dictionary learning [8], are based on subspace learning [9]–[11], which maps different modality data into a common subspace and measures the similarities in the common space.”
• An Overview of Cross-Media Retrieval: Concepts, Methodologies, Benchmarks, and Challenges (2017, unknown): “Common space learning Traditional statistical correlation analysis [15](F) [16](U) [17](U) [18](U) [19](F) [20](U) [21](U,F) [22](F) [23](F) [24](F) [25](U) Cross-media graph regularization [9](F) [12](S) [13](S) [26][F] [27](S) [28](U) Metric learning [9](F) [29](F) Learning to rank [30](U) [31](F)”