Image retrieval via probabilistic hypergraph ranking

By Yuchi Huang, Qingshan Liu, Shaoting Zhang, Dimitris N. Metaxas. 2010

344 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

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. Luc Van Gool
3. Yi Yang
4. Qi Tian
5. Xiaogang Wang
6. Ming-Hsuan Yang
7. Ling Shao
8. Alan L. Yuille

Citations in the corpus

• Click Prediction for Web Image Reranking Using Multimodal Sparse Coding (2014, methodology): “In [28], a hypergraph-based image retrieval approach has been proposed.”
• Hypergraph Neural Networks (2018, methodology): “(Huang et al. 2010) used the hypergraph structure to model image relationship and conducted trans-ductive inference process for image ranking.”
• Ieee Transactions on Knowledge and Data Engineering Context-aware Hypergraph Construction for Robust Spectral Clustering (neutral): “This has been applied to many domains such as image matching [19], multi-label classification [20], video object segmentation [21], and image retrieval [22].”
• Hypergraph Convolution and Hypergraph Attention (2019, background): “For example, (Huang et al., 2010) apply hypergraph learning to image retrieval where each vertex collects its k-nearest neighbors to form a hyper-edge, as also the way of constructing hypergraphs in our experiments.”
• Attribute-assisted reranking for web image retrieval (2012, methodology): “We adopt Normalized Discounted Cumulative Gain (NDCG)[9] as the performance metric.”
• Visual Classification by ℓ1-Hypergraph Modeling (2015, methodology): “E-mail: {eric.mengwang@gmail.com, liuxueliang1982}@gmail.com.”
• An Attribute-Assisted Reranking Model for Web Image Search (2015, background): “Different from the typical hypergraph [10], [25], [26], it presents not only whether a vertex v belongs to a hyperedge e, but also the prediction score that v is affiliated to a specific e.”
• Multiview Spectral Clustering via Structured Low-Rank Matrix Factorization (2017, methodology): “The following state-of-the-art baselines used in [ Wang et al. , 2016a ] are compared: • MFMSC : concatenating multi-features to be the multi-view representation for similarity matrix, the spectral clustering is then conducted [Huang et al. , 2010”
• Visual-Textual Joint Relevance Learning for Tag-Based Social Image Search (2013, background): “For instance, assuming that samples are represented by feature vectors in a feature space, an undirected graph can be constructed by using their pairwise distances, and graph-based semi-supervised learning approaches can be performed [34], [43] on this graph to categorize objects.”
• Networks beyond pairwise interactions: structure and dynamics (2020, background): “[331] Yuchi Huang, Qingshan Liu, Shaoting Zhang, and Dimitris N Metaxas.”
• 3-D Object Retrieval and Recognition With Hypergraph Analysis (2012, methodology): “In the transductive learning framework for image retrieval [36], [44], each image is represented by a vertex in a probabilistic hypergraph and the image retrieval task is formulated as a hypergraph ranking problem.”
• Adaptive Hypergraph Learning and its Application in Image Classification (2012, neutral): “In [25], a hypergraph-based image retrieval approach is proposed.”