Learning visual biases from human imagination

By Carl Vondrick, Hamed Pirsiavash, Aude Oliva, Antonio Torralba. 2014

24 citations recorded by the source corpus.

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

Global-and-local attention networks for visual recognition (2018, background): “Previous work has shown that it is possible to augment vision systems with human perceptual judgments on difﬁcult problems including face recognition and localization [23–25], bird categorization [26], action recognition [27], and object detection and segmentation [28–31].”
PsyPhy: A Psychophysics Driven Evaluation Framework for Visual Recognition (2016, methodology): “[27] devised a method inspired by psychophysics to estimate useful biases for recognition in computer vision feature spaces.”
What are the Visual Features Underlying Human Versus Machine Vision? (2017, background): “Researchers have found that in cases like these human perceptual judgments can augment the performance of vision models [35], resulting in significant gains in face recognition and localization [24, 2, 14], action recognition [31], object detection and segmentation [20, 26, 32].”
Cross-Modal Scene Networks (2016, background): “In a similar fashion, zero-shot learning [3], [10], [27], [34], [43] addresses the problem of learning new classifiers without training examples in a given domain, by using additional knowledge in the form of textual descriptions or attributes.”
Learning Aligned Cross-Modal Representations from Weakly Aligned Data (2016, unknown): “In a similar fashion, zero-shot learning [25, 31, 9, 2, 40] addresses the problem of learning new classifiers without training examples in a given domain, e.”