Multiple Instance Learning with Manifold Bags

46 citations recorded by the source corpus.

How researchers see this paper

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

Learning Theory for Distribution Regression (2014, methodology): “In contrast to the previous approaches (Long and Tan, 1998; Auer, 1998; Blum and Kalai, 1998), Babenko et al. (2011) modelled the bags as low-dimensional manifolds, and proved PAC bounds.”
Multi-instance learning with any hypothesis class (2011, background): “Other applications can be found in follow-up research of the results we report here, such as a generic bag-construction mechanism (Sabato et al., 2010), and learning when bags have a manifold structure (Babenko et al., 2011).”
MILCut: A Sweeping Line Multiple Instance Learning Paradigm for Interactive Image Segmentation (2014, background): “Since then, a large number of methods, e.g., DD [23], EM-DD [42], citation-kNN [37], MI-SVM and mi-SVM [4], and IQH [6], have been proposed to solve the multiple instance learning problem.”
Deep Multi-patch Aggregation Network for Image Style, Aesthetics, and Quality Estimation (2015, methodology): “Recent studies have attempted to unify deep learning and the MIL framework for many applications.”