Scene Classication Using a Hybrid Generative/Discriminative Approach
By C. V. D. Linden, Jacobo Josep. 2009
103 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.
Citations in the corpus
- Nonparametric kernel estimators for image classification (2012, methodology): “[5, 2, 24]).”
- Topic Models for Image Annotation and Text Illustration (2010, background): “Several approaches attempt to render images more word-like, by reducing the dimensionality of the image feature space (Bosch et al., 2008; Fei-Fei and Perona, 2005) or by learning a single representation for both visual and textual features (Monay and Gatica-Perez, 2007; Zhao and Grosky, 2003).”
- Learning Color Names for Real-World Applications (2009, methodology): “Recently such models have also been applied in computer vision, where images take the role of documents and pixels or small image patches take the role of words [17], [23], [24], [25], [26], [27].”
- Generative-Discriminative Basis Learning for Medical Imaging (2012, methodology): “11 ( (cid:107) w 22 ).”
- From BoW to CNN: Two Decades of Texture Representation for Texture Classification (2018, background): “…(FV) [203], and wavelet Scattering Convolution Networks (ScatNet) [24]) is that they were found to be well applicable to other problems of image understanding and computer vision, such as object recognition [57, 201], scene classification [18, 36, 106, 197] and facial image analysis [3, 215, 265].”
- Kernel Codebooks for Scene Categorization (2008, methodology): “[6] show that probabilistic latent semantic analysis (pLSA) improves on LDA.”
- Dynamic scene understanding: The role of orientation features in space and time in scene classification (2012, background): “These representations have come in the form of semantic descriptions (e.g., water vs. sky [4, 37] and ruggedness vs. openness [26]) and latent theme models [10, 24, 3, 28].”
- Multi-scale Recognition with DAG-CNNs (2015, unknown): “Deep19-DAG 92.9 Deep19 [29] 90.8 Caffe-DAG 89.7 Caffe [14] 86.8 Place [39] 91.6 CENTRIST [36] 84.8 Hybrid [3] 83.7 Spatial pyramid [17] 81.4 Object bank [19] 80.9 Reconfigurable model [23] 78.6 Spatial Envelop [22] 74.1 Baseline [9] 65.2 Table 1.”
- Modeling Search for People in 900 Scenes: A combined source model of eye guidance (2009, unknown): “Several models of scene recognition have been proposed in recent years (Bosch, Zisserman, & Mun˜oz, 2008; Fei Fei & Perona, 2005; Grossberg, & Huang, 2009; Lazebnik, Schmidt, & Ponce, 2006; Oliva & Torralba, 2001; Renninger & Malik, 2004; Vogel & Schiele, 2007), with most of the approaches…”
- Pseudo-Marginal Bayesian Inference for Gaussian Processes (2013, background): “Although these classifiers are based on different modeling assumptions and paradigms of statistical inference, they are characterized by a kernel function or covariance operator that allows one to build nonlinear classifiers able to tackle challenging problems [6], [7], [8], [9], [10], [11].”
- A review of automatic mass detection and segmentation in mammographic images (2010, background): “Actual trends in unsupervised object recognition are based on probabilistic latent semantic analysis and visual vocabularies (Sivic et al., 2005; Bosch et al., 2008).”
- Support Distribution Machines (2012, methodology): “We evaluate the algorithms on 2-fold cross-validation runs on the whole dataset, following the set up used by Bosch et al. (2008).”