Results 31 to 40 of about 7,775,419 (309)
Scientific Reports, 2021 In many research areas, scientific progress is accelerated by multidisciplinary access to image data and their interdisciplinary annotation. However, keeping track of these annotations to ensure a high-quality multi-purpose data set is a challenging and ...
Christian Marzahl +9 more
doaj +1 more source
Face recognition technologies for evidential evaluation of video traces [PDF]
, 2017 Human recognition from video traces is an important task in forensic investigations and evidence evaluations. Compared with other biometric traits, face is one of the most popularly used modalities for human recognition due to the fact that its ...
Li, Chang-Tsun, Wei, Xingjie
core +1 more source
AUCReshaping: improved sensitivity at high-specificity
Scientific Reports, 2023 The evaluation of deep-learning (DL) systems typically relies on the Area under the Receiver-Operating-Curve (AU-ROC) as a performance metric. However, AU-ROC, in its holistic form, does not sufficiently consider performance within specific ranges of ...
Sheethal Bhat +9 more
doaj +1 more source
British Machine Vision Conference, 2015 The goal of this paper is face recognition – from either a single photograph or from a set of faces tracked in a video. Recent progress in this area has been due to two factors: (i) end to end learning for the task using a convolutional neural network ...
Omkar M. Parkhi +2 more
semanticscholar +1 more source
Speech recognition with deep recurrent neural networks [PDF]
IEEE International Conference on Acoustics, Speech, and Signal Processing, 2013 Recurrent neural networks (RNNs) are a powerful model for sequential data. End-to-end training methods such as Connectionist Temporal Classification make it possible to train RNNs for sequence labelling problems where the input-output alignment is ...
Alex Graves +2 more
semanticscholar +1 more source
Advances in Multimedia, 2023 With the rapid development of the national power grid, there is an increasing and strict demand for accurate intelligent management. However, the current detection algorithms have limited abilities under adverse conditions, especially in regions like ...
R. Chang +8 more
doaj +1 more source
CNN Features Off-the-Shelf: An Astounding Baseline for Recognition [PDF]
2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2014 Recent results indicate that the generic descriptors extracted from the convolutional neural networks are very powerful. This paper adds to the mounting evidence that this is indeed the case.
A. Razavian +3 more
semanticscholar +1 more source
Damage to Association Fiber Tracts Impairs Recognition of the Facial Expression of Emotion [PDF]
, 2009 An array of cortical and subcortical structures have been implicated in the recognition of emotion from facial expressions. It remains unknown how these regions communicate as parts of a system to achieve recognition, but white matter tracts are likely ...
Adolphs, Ralph +4 more
core +1 more source