Object categorization using co-occurrence, location and appearance

By Carolina Galleguillos, Andrew Rabinovich, Serge J. Belongie. 2008

533 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Relation Networks for Object Detection (2017, background): “Object relation in post-processing Most early works use object relations as a post-processing step [12, 17, 46, 47, 36, 17].”
Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials (2011, methodology): “Fully connected CRFs have been used for semantic image labeling in the past [18, 22, 6, 17], but the complexity of inference in fully connected models has restricted their application to sets of hundreds of image regions or fewer.”
Scene Graph Generation by Iterative Message Passing (2017, background): “Visual scene understanding often harnesses the statistical patterns of object co-occurrence [11, 22, 30, 35] as well as spatial layout [2, 9].”
Exploring Visual Relationship for Image Captioning (2018, background): “Some early works [9,10] attempt to learn four spatial relations (i.”
Visual Relationship Detection with Language Priors (2016, background): “They attempted to learn four spatial relationships: “above”, “below”, “inside”, and “around” [13].”
Weakly-Supervised Learning of Visual Relations (2017, background): “This visual representation shares the spirit of [13, 22, 29] and we show it can handle multimodal relations and generalizes well to unseen triplets.”
An empirical study of context in object detection (2009, background): “It also may indicate the presence and location (spatial context) of other objects and materials [10, 11, 12, 37].”
Ieee Transactions on Pattern Analysis and Machine Intelligence 1 Exploring Tiny Images: the Roles of Appearance and Contextual Information for Machine and Human Object Recognition (unknown): “Numerous works attempt to model the contextual relationships between objects [5], [7], [26], [27].”
Bringing Semantics into Focus Using Visual Abstraction (2013, background): “Relative spatial location: The relative spatial location of two objects has been used to provide contextual information for scene understanding [4, 10].”
Context models and out-of-context objects (2012, background): “Choi et al. [10] uses a tree-structured graphical model with these binary variables to capture co-occurrence probabilities between object categories.”
Exploiting hierarchical context on a large database of object categories (2010, background): “In [7], spatial relationships are quantized to four prototypical relationships - above, below, inside and around, whereas in [8] a non-parametric map of spatial priors are learned for each pair of objects.”
Relation-Aware Graph Attention Network for Visual Question Answering (2019, background): “Some previous work [16, 17] also probed the idea that spatial relationships (e.”
Are spatial and global constraints really necessary for segmentation? (2011, background): “[7] model the full joint transition likelihood between neighboring pixels, where the parameters of their spatial model are set via simple counting of co-occurrences in the labeled images.”
A Tree-Based Context Model for Object Recognition (2012, background): “This approach is extended in [10] and [11] to encode spatial relationships between a pair of objects.”
Learning a Dictionary of Shape Epitomes with Applications to Image Labeling (2013, methodology): “We demonstrate its quantitative and qualitative properties of our approach with image labeling experiments on two standard datasets: MSRC-21 and Stanford Background.”
Beyond Categories: The Visual Memex Model for Reasoning About Object Relationships (2009, methodology): “The distributions returned by CoLA tend to degenerate to a single non-zero value (most often on one of the popular categories such as window).”
Associative hierarchical CRFs for object class image segmentation (2009, methodology): “In this section, we draw comparisons with the current state of the art models for object segmentation [10, 18, 19, 32] and show that at certain choices of the parameters of our model, these methods fall out as special cases (illustrated in ﬁgure 2).”
Understanding images of groups of people (2009, background): “Learning these co-occurence, relativ co-locations, and scale models improves object recognitio n [11, 20, 21, 22].”
Spatial Pattern Templates for Recognition of Objects with Regular Structure (2013, methodology): “They learn edge-specific weights in a fully connected graph, which is directly tractable only when the number of nodes n is small (10 segments and 4 spatial relations in [3]) due to edge number growing with O(n(2)).”