Recognition

By M. Hardinge, Patricia Johnston. 1999

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

The limits and potentials of deep learning for robotics (2018, background): “While the importance of semantic regularities and contextual information for human perception processes is well known in psychology [33], [81], current object detection systems [42], [67], [91] do not exploit this rich source of information.”
Region-Based Saliency Detection and Its Application in Object Recognition (2014, unknown): “Context information is also commonly used for object detection [16], [53], [50].”
Contextualizing Object Detection and Classification (2015, background): “A natural way of representing the context of an object is in terms of its relationship with other objects, e.g. co-occurrence based context model [30].”
Spatial Memory for Context Reasoning in Object Detection (2017, background): “Context helps image understanding! Apart from strong psychological evidence [4, 37, 64, 65] that context is vital for humans to recognize objects, many empirical studies in the computer vision community [10, 11, 16, 22, 23, 43, 60, 62, 73, 82, 83] have also suggested that recognition algorithms can ”
REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets (2020, background): “Object co-occurrence is a known contextual visual cue exploited by object detection models (Galleguillos et al., 2008; Oliva and Torralba, 2007), and thus can serve as an important measure of the diversity of object context.”