[图书][B] Synthetic data for deep learning
SI Nikolenko - 2021 - Springer
You are holding in your hands… oh, come on, who holds books like this in their hands
anymore? Anyway, you are reading this, and it means that I have managed to release one of …
anymore? Anyway, you are reading this, and it means that I have managed to release one of …
[PDF][PDF] From Virtual to Reality: Fast Adaptation of Virtual Object Detectors to Real Domains.
The most successful 2D object detection methods require a large number of images
annotated with object bounding boxes to be collected for training. We present an alternative …
annotated with object bounding boxes to be collected for training. We present an alternative …
Learning scene-specific pedestrian detectors without real data
H Hattori, V Naresh Boddeti… - Proceedings of the …, 2015 - openaccess.thecvf.com
We consider the problem of designing a scene-specific pedestrian detector in a scenario
where we have zero instances of real pedestrian data (ie, no labeled real data or …
where we have zero instances of real pedestrian data (ie, no labeled real data or …
Domain adaptation of deformable part-based models
The accuracy of object classifiers can significantly drop when the training data (source
domain) and the application scenario (target domain) have inherent differences. Therefore …
domain) and the application scenario (target domain) have inherent differences. Therefore …
Efficient boosted exemplar-based face detection
Despite the fact that face detection has been studied intensively over the past several
decades, the problem is still not completely solved. Challenging conditions, such as extreme …
decades, the problem is still not completely solved. Challenging conditions, such as extreme …
Deep decision tree transfer boosting
Instance transfer approaches consider source and target data together during the training
process, and borrow examples from the source domain to augment the training data, when …
process, and borrow examples from the source domain to augment the training data, when …
Synthesizing a scene-specific pedestrian detector and pose estimator for static video surveillance: Can we learn pedestrian detectors and pose estimators without real …
We consider scenarios where we have zero instances of real pedestrian data (eg, a newly
installed surveillance system in a novel location in which no labeled real data or …
installed surveillance system in a novel location in which no labeled real data or …
Contextual exemplar classifier-based image representation for classification
The use of local features for image representation has become popular in recent years.
Local features are often used in the bag-of-visual-words scheme. Although proven effective …
Local features are often used in the bag-of-visual-words scheme. Although proven effective …
Fast and accurate real time pedestrian detection using convolutional neural network
H Albehadili, L Alzubaidi, J Rashed… - QALAAI ZANIST …, 2017 - journal.lfu.edu.krd
Recently, pedestrian detection has become an important problem of interest. Our work
primarily depends on robust and fast deep neural network architectures. This paper used …
primarily depends on robust and fast deep neural network architectures. This paper used …
Fast head-shoulder proposal for deformable part model based pedestrian detection
TR Liu, T Stathaki - 2016 IEEE International Conference on …, 2016 - ieeexplore.ieee.org
In this paper we propose a fast head-shoulder detector as a means to facilitating faster
pedestrian detection. The proposed approach is based on the observation that human head …
pedestrian detection. The proposed approach is based on the observation that human head …