Using the Forest to See the Trees: A Graphical Model Relating Features, Objects, and Scenes

By Kevin P. Murphy, Antonio Torralba, William T. Freeman. Neural Information Processing Systems, 2003

409 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/6a4300efb6895695205dfc1b74e124f9fea6aff2

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

Robust Multiperson Tracking from a Mobile Platform (2009, background): “…on the authors, the rather loose notion of " context " can refer to different types of complementary information, including motion [11], [54], stereo depth [15], [19], scene geometry [24], [29], temporal continuity [1], [31], [32], [57], or semantics of other image regions [36], [40], [50], [51].”
Domain Adaptation for Visual Applications: A Comprehensive Survey (2017, background): “large amount of annotated data is available. In general, it is solved by knowledge transfer through the reuse of model parameters [85], by sharing parts or features [12], or by contextual information [152]. An extreme case of few-shot learning is the zero-shot learning [84, 130], where the new task ”
Learning Spatial Context: Using Stuff to Find Things (2008, methodology): “Scene-Thing context allows scene-level information, such as the scale or the “gist” [5], to determine location priors for objects.”
Object categorization using co-occurrence, location and appearance (2008, background): “Previous works in object recognition, classification and labeling have benefited from CRFs [8] [9] [14] [23].”
Contextually Guided Semantic Labeling and Search for 3D Point Clouds (2011, background): “In the past, a signiﬁcant amount of work has been done in semantic labeling of 2D images (Murphy et al., 2003; Heitz and Koller, 2008; Felzenszwalb et al., 2008; Collet et al., 2011; Li et al., 2012).”
Nonparametric Scene Parsing via Label Transfer (2011, background): “Manuscript received 28 Aug. 2010; revised 4 Apr. 2011; accepted 11 May 2011; published online 22 June 2011.”
Towards total scene understanding: Classification, annotation and segmentation in an automatic framework (2009, background): “A few earlier approaches have proposed interesting models for image understanding by object and scene, or multiple object recognition [31, 30, 14, 23, 12].”
Context-based vision system for place and object recognition (2003, methodology): “In current work, we are extending this system by combining the top-down prior provided by context with the results of a more standard bottom-up object recognition phase [5].”
A Tree-Based Context Model for Object Recognition (2012, background): “This is extended in [21] to combine patch-based local features and the gist feature.”
Spatial Memory for Context Reasoning in Object Detection (2017, unknown): “46, 58, 63, 74, 81].”
Context models and out-of-context objects (2012, methodology): “Using these estimated samples, we train the likelihood of gist conditioned on hidden variables [13].”
Context-Aware CNNs for Person Head Detection (2015, methodology): “[24] propose a CRF model for jointly solving the task of object detection and scene classification.”
Recognition of natural scenes from global properties: Seeing the forest without representing the trees (2008, unknown): “Clearly, more sophisticated object models that incorporate structure and layout information should be able to capture more of the essence of a natural scene ([Grossberg and Huang, in press] and [Murphy et al., 2003]).”
Recognizing Human-Object Interactions in Still Images by Modeling the Mutual Context of Objects and Human Poses (2012, unknown): “In computer vision, context has been used in problems such as object detection and recognition [3], [4], [5], scene recognition [6], action classification [7], and image segmentation [8].”
An empirical study of context in object detection (2009, methodology): “Detections that occur at unusual poses should have significantly high score from the base detector for them to be selected in this scheme [26].”