Spatially Coherent Latent Topic Model for Concurrent Segmentation and Classification of Objects and Scenes

By Liangliang Cao, Li Fei-Fei. 2007

375 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

Citations in the corpus

Improving Interpretability of Deep Neural Networks with Semantic Information (2017, methodology): “, Latent Dirichlet Allocation (LDA) [4], which has been applied to image/video/text analysis tasks [13, 7, 6, 40].”
A Thousand Frames in Just a Few Words: Lingual Description of Videos through Latent Topics and Sparse Object Stitching (2013, positive): “[4] and subsequent extensions [6, 7, 11, 22, 32] jointly model image features (predominantly SIFT and HOG derivatives) and language words as mixed memberships over latent topics with considerable success.”
BiCoS: A Bi-level co-segmentation method for image classification (2011, methodology): “Due to the high dimensionality of superpixel descriptors and obvious interdependencies in their dimensions, generative modeling and classification of foreground and background distributions would be problematic, although one can use naive-Bayes approximation [3] as well as topic models [9, 32].”
A Bayesian Model for Simultaneous Image Clustering, Annotation and Object Segmentation (2009, methodology): “A relatively complete summary of the l it rature may be found in [16, 23], where the advantages of the approaches in [16, 23] are descri b d relative to previous related approaches [3, 6, 10, 11, 18, 24, 27].”
Weakly Supervised Localization and Learning with Generic Knowledge (2012, neutral): “…are part-based models [Crandall and Huttenlocher, 2006, Fergus et al, 2003], and segmentation-based models [Alexe et al, 2010a, Arora et al, 2007, Cao and Li, 2007, Galleguillos et al, 2008, Russell et al, 2006, Todorovic and Ahuja, 2006, Winn and Jojic, 2005a], and a wide variety of other…”
A Survey of Multi-View Representation Learning (2016, neutral): “[117] propose a spatially coherent latent topic model (Spatial-LTM), which represents an”
ClassCut for Unsupervised Class Segmentation (2010, methodology): “6%, outperforming both GrabCut (line (c)) and the spatial topic model [2] (line (a)).”
Topic Modeling in Management Research: Rendering New Theory from Textual Data (2019, background): “Recent developments have also moved topicmodeling further away fromNLP, as researchers have applied it to images (Cao & Fei-Fei, 2007) andmusic (Hu & Saul, 2009) rather than natural language. topics into constructs, causal links, or mechanisms).”