Statistical context priming for object detection

By Antonio Torralba, P. Sinha. 2001

203 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

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

In Media Technology

Citations in the corpus

Women also Snowboard: Overcoming Bias in Captioning Models (2018, background): “Exploiting contextual cues can frequently lead to better performance on computer vision tasks [1,2,3].”
An empirical study of context in object detection (2009, methodology): “Overall our approach follows the methodology of context priming [37].”
Context-based vision system for place and object recognition (2003, methodology): “However, the context can provide a strong prior for which objects are likely to appear, as well as their expected size and position within the image, thus reducing the need for brute force search [15, 13].”
Modeling Visual Context is Key to Augmenting Object Detection Datasets (2018, background): “Relatively early, visual context has been modeled by computing statistical correlation between low-level features of the global scene and descriptors representing an object [17,18].”
Contextual Priming for Object Detection (2003, methodology): “As suggested in Torralba and Oliva (1999), Oliva and Torralba (2001), and Torralba and Sinha (2001) the scene/context can be considered a single entity that can be recognized by means of a scene-centered representation bypassing the identification of the constituent objects.”
Objects in Action: An Approach for Combining Action Understanding and Object Perception (2007, background): “al used low level image cues [29] for providing context based on depth and viewpoint cues.”
Exploring Person Context and Local Scene Context for Object Detection (2015, background): “A lot of work has focused on using global scene features to identify possible locations of objects [22, 20, 27, 28].”
50 Years of object recognition: Directions forward (2013, background): “Various knowledge representation schemes were implemented over the years in order to improve the performance of vision systems, through the integration of task-specific knowledge [116], [117], [118],[119], [120], [121], [122], [123].”
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): “Global scene information, such as global texture [8], [17] or 3D scene information [6] can be used as context.”
Contextual Modulation of Target Saliency (2001, background): “A more comprehensive representation of an object should include contextual information [11] [13]: Obj. representatian == {intrisic obj. model, contextual obj. model}.”
Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope (2001, methodology): “The holistic scene representation provides an efficient way for context modeling that can be used as the first stage of object detection algorithms by priming typical objects, scales and locations (Torralba and Sinha, 2001).”
Bayesian models of object perception. (2003, background): “Recent studies of natural image data have shown how statistics can provide an efficient characterization of homogeneous textures [10,11 ,12], help to discount the illuminant [13,14 ], find object boundaries [15 ], contribute to scene recognition [16], and constrain the context for object recognition”
Using Group Prior to Identify People in Consumer Images (2007, background): “The group prior serves as the context for the classification problem, akin to performing object detection by setting the context of the scene [10].”
Class-specific Hough forests for object detection (2009, background): “This is, of course, a simplifying assumption, and such “long-range” context information has been proven useful for object recognition [26].”
Observing Human-Object Interactions: Using Spatial and Functional Compatibility for Recognition (2009, background): “They discovered that the weight of an object is most robustly estimated, while size and shape are harder to estimate.”
An Integrated Model of Top-Down and Bottom-Up Attention for Optimizing Detection Speed (2006, background): “Few top-down models consider the distractors [23], by using global features representing the scene context.”
Understanding images of groups of people (2009, background): “[15], and Torralba and Sinha [25] describe the context (in 3D and 2D, respectively) of a scene and the relationship between context and object detection.”
Putting Objects in Perspective (2006, background): “From lowlevel image cues, Torralba and Oliva [26] get a sense of the viewpoint and mean scene depth, which provides a useful prior for object detection [27].”