Multimedia content processing through cross-modal association

By Dongge Li, N. Dimitrova, Mingkun Li, I. Sethi. MULTIMEDIA '03, 2003

304 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/cfcd7b0683862e1063867d9e17c647f31f634841

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

Citations in the corpus

Multimodal fusion for multimedia analysis: a survey (2010, methodology): “[72] proposed the cross-modal factor analysis (CFA) method, in which, the features from different modalities are treated as two subsets and the semantic patterns between these two subsets are discovered.”
An Overview of Cross-Media Retrieval: Concepts, Methodologies, Benchmarks, and Challenges (2017, methodology): “The compared methods in the experiments include: BITR [20], CCA [18], CCA+SMN [27], CFA [30], CMCP [6], DCMIT [35], HSNN [5], JGRHML [7], JRL [10], LGCFL [85], ml-CCA [26], mv-CCA [25] and S2UPG [11].”
Text-to-image Synthesis via Symmetrical Distillation Networks (2018, unknown): “1 INTRODUCTION As a multimedia technology, cross-modal retrieval [6, 20, 29, 38, 43] has become a highlighted topic of research in the big data era.”
Heterogeneous Attention Network for Effective and Efficient Cross-modal Retrieval (2021, background): “Early works of joint embedding mainly rely on linear projection [12, 21, 31].”
On the Role of Correlation and Abstraction in Cross-Modal Multimedia Retrieval (2014, methodology): “This allows assessments of image similarity in terms of weighted combinations of vocabulary words and substantially extends the range of concepts that can effectively be retrieved.”
Learning Cross-Media Joint Representation With Sparse and Semisupervised Regularization (2014, methodology): “[12] introduced a cross-modal factor analysis (CFA) approach to evaluate the association between two modalities, and demonstrated its superior performance with respect to CCA.”
Joint Feature Selection and Subspace Learning for Cross-Modal Retrieval (2016, background): “[15] introduce a cross-modal factor analysis (CFA) approach to evaluate the association between two modalities.”
Cluster Canonical Correlation Analysis (2014, methodology): “Joint dimensionality reduction techniques such as Canonical Correlation Analysis (CCA) [12], Partial Least Squares (PLS) [23], Bilinear Model [26], Cross-modal Factor Analysis (CFA) [19] etc. have become quite popular in recent years.”
See, Hear, and Read: Deep Aligned Representations (2017, background): “One of the early works, [24], explored the cross-modal relations between “talking head” images and speech through CCA and cross-modal factor analysis.”
Heterogeneous Metric Learning with Joint Graph Regularization for Cross-Media Retrieval (2013, methodology): “Unlike CCA which finds transformation matrices that maximize the correlation between two subsets of features, the cross-modal factor analysis (CFA) method (Li et al. 2003) adopts a criterion of minimizing the Frobenius norm between pairwise data in the transformed domain.”
A Comprehensive Survey on Cross-modal Retrieval (2016, methodology): “Subspace learning methods CCA [13], PLS [14], BLM [15], [16], CFA [17], MCU [18], CoCA [19], MMD [20]”
Cross-modal deep metric learning with multi-task regularization (2017, methodology): “8 state-of-the-art cross-modal retrieval methods are used for comparison: CCA [1], CFA [4], KCCA [18] (with Poly and RBF kernel functions), Bimodal AE [8], Multimodal DBN [19], Corr-AE [13], JRL [5] and CMDN [10].”
Learnable PINs: Cross-Modal Embeddings for Person Identity (2018, background): “Cross-modal embeddings: The relationship between visual content and audio has been researched in several di↵erent contexts, with common applications being generation, matching and retrieval [21, 23, 25].”
A Survey of Multi-View Representation Learning (2016, unknown): “[31] as a simple example of multiview embedding learning based on the consensus principle.”
Adversarial Cross-Modal Retrieval (2017, methodology): “For example, early works, like CCA-based methods [15, 39] and graph-based methods [40, 43], learn linear projections to generate a common representation by maximizing the cross-modal pairwise item correlation or item classification accuracy.”
Learning Cross-Modal Common Representations by Private–Shared Subspaces Separation (2020, methodology): “In addition to the CCA and its extensions, some other methods that utilize advanced schemes, such as factor analysis [25], dictionary learning [26], and half-quadratic optimization [27], to learn more effective common representations.”