Automatic multimedia cross-modal correlation discovery

By Jia-Yu Pan, Hyung-Jeong Yang, Christos Faloutsos, Pinar Duygulu Sahin. Knowledge Discovery and Data Mining, 2004

546 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/b043f19fa263adb874becf32b912d9174bdea56d

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. Kyoung Mu Lee
2. Luc Van Gool
3. Ming-Hsuan Yang
4. Antonio Torralba
5. Yi Yang
6. Dacheng Tao
7. Jitendra Malik
8. Kristen Grauman

Citations in the corpus

• Unsupervised modeling of object categories using link analysis techniques (2008, background): “Pan et al .’s work [18] applies the PageRank algorithm to image data.”
• An experimental investigation of kernels on graphs for collaborative recommendation and semisupervised classification (2012, methodology): “Since x∞ is column i of matrix (I − αPT)−1, the random-walkwith-restart (KRWR) matrix (Gori & Pucci, 2006; Pan et al., 2006; Pucci et al., 2006; Tong et al., 2006, 2008) can be defined as the”
• Nonparametric higher-order learning for interactive segmentation (2010, background): “Specially it can be interpreted as a variant of Random Walks with Restart (RWR) [14][12] with the different criteria for deciding the restarting probability of each node in the graph G.”
• Unsupervised Detection of Regions of Interest Using Iterative Link Analysis (2009, methodology): “Recently, link analysis techniques on visual similarity networks were successfully exploited in computer vision problems [12, 15, 11, 16].”
• TagProp: Discriminative metric learning in nearest neighbor models for image auto-annotation (2009, unknown): “Examples of such techniques include methods based on label diffusion over a similarity graph of labeled and unlabeled images [16, 22], or learning discriminative models in neighborhoods of test images [27].”
• Fast Random Walk with Restart and Its Applications (2006, methodology): “The most natural way might be by row normalization [22].”
• Generative Image Segmentation Using Random Walks with Restart (2008, methodology): “It has good performance on many other applications: Cross-model correlation discovery [ 8 ], Center-piece subgraph discovery [13], Content based image retrieval [12], Neighborhood formulation [14] and etc.”
• Handbook of Big Data (2016, methodology): “Diffusions are associated with random-walk processes and we can simply simulate the random walk to propagate the diffusion [17,61,62].”
• Learning full pairwise affinities for spectral segmentation (2010, background): “Our work is novel in that it sheds understanding on the full affinities gained in integrating local grouping cues by using semi-supervised learning.”
• Joint Link Prediction and Attribute Inference Using a Social-Attribute Network (2014, methodology): “In the SAN model, a Random Walk with Restart [Brin and Page 1998; Pan et al. 2003] starting from u recursively walks to one of its neighbors t with probability proportional to the link weight w(u, t) and returns to u with a fixed restart probability α.”
• Fast Random Walk Graph Kernel (2012, background): “, random walk with restart [27, 39], sinkaugmented delivered current [8], cycle free effective conductance [22], survivable network [13], direction-aware proximity [38], ObjectRank [2], RelationalRank [11], SimRank [18] and its fast approximation [24] Low-Rank Approximation.”
• Neighborhood formation and anomaly detection in bipartite graphs (2005, methodology): “In order to deal with personalized query, Topic-Sensitive PageRank [8] increases the importance of certain web pages by putting non-uniform weights for �p. Similar random-walk approaches have been used into other domains; for example, Mixed Media Graph(MMG) [ 14 ]a pplies random walk with restart o”
• PageRank beyond the Web (2014, methodology): “Pan et al. [2004] define a random walk with restart, which is exactly a personalized PageRank system, to infer captions for a database of images.”
• Random walk with restart: fast solutions and applications (2008, methodology): “The most natural way might be by row normalization [25].”