Image Categorization by Learning and Reasoning with Regions

By Yixin Chen, James Ze Wang. Journal of machine learning research, 2004

707 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/7a8665ada37b8a26f2a68c0b9c3f3ceb1e0f655a

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

Non-I.I.D. Multi-Instance Dimensionality Reduction by Learning a Maximum Bag Margin Subspace (2010, background): “The framework of multi-instance has attracted much attention in various domains such as object detection (Chen and Wang 2004), information retrieval (Settles, Graven, and Ray 2008), image classification (Qi et al. 2007), and biomedical informatics (Fung et al. 2007).”
MILES: Multiple-Instance Learning via Embedded Instance Selection (2006, methodology): “Since we will compare MILES with the DD-SVM approach, we adopt the same image segmentation algorithm as described in [16], [54].”
Video Event Detection by Inferring Temporal Instance Labels (2014, methodology): “In computer vision, MIL has been applied in scene classification [13], content-based image retrieval [27], and image classification [5].”
XRCE ’ s participation to ImagEval (2007, methodology): “The ROI can be obtained by image segmentation [3, 7, 8, 23], by applying specific interest point detectors [9, 34], by considering a regular grid [7, 12] or simply random sampling of image patches [25, 29].”
Multi-instance multi-label learning (2008, methodology): “Multi-instance learning techniques have already been applied to diverse applications including image categorization [17, 18], image retrieval [71, 84], text categorization [3, 60], web mining [86], spam detection [37], computer security [54], face detection [66, 76], computer-aided medical diagnosis”
Multiple instance classification: Review, taxonomy and comparative study (2013, methodology): “Several authors [31, 32, 33, 1, 2] use this algorithm, althou g this fact is not pointed out in the mentioned papers.”
Image retrieval: Ideas, influences, and trends of the new age (2008, methodology): “Similarly, multiple instance learning research has benefited by work on image categorization [Chen and Wang 2004].”
Multiple-instance ranking: Learning to rank images for image retrieval (2008, methodology): “MI learning has been widely exploited for content-based image retrieval [6, 8, 25], however, they are mainly in the classification setting.”
Multi-Instance Learning With Emerging Novel Class (2021, methodology): “For object-centric image classiﬁcation, we employ the popular used COREL image MIL data set [57], which contains 10 categories, i.e., African people, beach, historical building, buses, dinosaurs, elephants, ﬂowers, horses, mountains and food.”
Marginalized Multi-Instance Kernels (2007, methodology): “It also outperforms the DD-SVM, which is also using multiple DD hypotheses that are assumed to be equally important.”
Multiple Instance Learning: Algorithms and Applications (2008, background): “An interesting combination of Diverse Density and SVM was developed in [29, 30].”
Multiple instance learning for soft bags via top instances (2015, background): “The positive source is the distribution of the target concept (e.g., image patches of “flower”), the negative source the distribution of background clutter (e.g., image patches of everything else).”
A brief introduction to weakly supervised learning (2018, methodology): “Multi-instance learning has been successfully applied to various tasks, such as image categorization/retrieval/annotation [20, 73, 90], text categorization [3, 66], spam detection [45], medical diagnosis [34], face/object detection [30, 76], object class discovery [101], object tracking [6], etc.”
Multi-Instance Multi-Label Learning with Application to Scene Classification (2006, methodology): “Multi-instance learning techniques have been successfully applied to diverse applications including scene classification [3] [7].”
A Multiple Instance Learning Strategy for Combating Good Word Attacks on Spam Filters (2008, methodology): “Other algorithms that have been adapted to multiple instance learning include the neural network MI-NN (Ramon and Raedt, 2000), DD-SVM (Chen and Wang, 2004), MI-SVM and mi-SVM (Andrews et al., 2003), multi-instance kernels (Gärtner et al., 2002), MI-Ensemble (Zhou and Zhang, 2003), and MI-Boosting…”