Multi-Instance Multi-Label Learning with Application to Scene Classification

By Zhi-Hua Zhou, Min-Ling Zhang. Neural Information Processing Systems, 2006

418 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/71564232ce7ff2187c1d73cc2d52fa79241c7113

How researchers see this paper

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

Citations in the corpus

A Bayesian Model for Simultaneous Image Clustering, Annotation and Object Segmentation (2009, unknown): “A relatively complete summary of the literature may be found in [16, 23], where the advantages of the approaches in [16, 23] are described relative to previous related approaches [3, 6, 10, 11, 18, 24, 27 ].”
Transductive Multilabel Learning via Label Set Propagation (2013, background): “Zhou et al. [39], [40] proposed the MIML framework which deals with multilabel examples each is represented as a set of instances.”
Relation Extraction with Multi-instance Multi-label Convolutional Neural Networks (2016, methodology): “This multi-instance multi-label (MIML) learning scenario was formulated in Zhou et al. (2012), and get widely employed in various tasks (Zha et al., 2008; Zhou and Zhang, 2006; Li et al., 2012).”
On the Consistency of Multi-Label Learning (2011, unknown): “…multi-label learning has attracted much attention during the past few years and many eﬀective approaches have been developed (Schapire and Singer, 2000; Elisseeﬀ and Weston, 2002; Zhou and Zhang, 2007; Zhang and Zhou, 2007; Hsu et al., 2009; Dembczy´nski et al., 2010; Petterson and Caetano, 2010).”
LEAP: Learning to Prescribe Effective and Safe Treatment Combinations for Multimorbidity (2017, background): “Zhou et al. [41] first address this problem in the context of scene classification and proposes to transform the MIML problem to an ensemble of single instance single label (SISL) sub-problems.”
A review on automatic image annotation techniques (2012, unknown): “more specifically, multi-instance multi-label (MIML) learning [129,130].”
Multi-instance multi-label learning (2008, methodology): “Five criteria are often used for evaluating the performance of learning with multilabel examples [56,92]; they are hamming loss, one-error, coverage, ranking loss and average precision.”
Simultaneous image classification and annotation (2009, unknown): “Discriminative methods include the work in [7, 30, 29, 16].”
Mining Multi-label Data (2010, methodology): “Several methods have been recently proposed for addressing such data [68, 69].”
A review of multi-instance learning assumptions (2010, methodology): “Zhou and Zhang (2006) formalized MI multi-label learning (MIML), where each MI bag may be associated with multiple class labels.”
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.”