Each part matters: Local patterns facilitate cross-view geo-localization
Cross-view geo-localization is to spot images of the same geographic target from different
platforms, eg, drone-view cameras and satellites. It is challenging in the large visual …
platforms, eg, drone-view cameras and satellites. It is challenging in the large visual …
Attentive fashion grammar network for fashion landmark detection and clothing category classification
This paper proposes a knowledge-guided fashion network to solve the problem of visual
fashion analysis, eg, fashion landmark localization and clothing category classification. The …
fashion analysis, eg, fashion landmark localization and clothing category classification. The …
Invariant scattering convolution networks
A wavelet scattering network computes a translation invariant image representation which is
stable to deformations and preserves high-frequency information for classification. It …
stable to deformations and preserves high-frequency information for classification. It …
Object detection with discriminatively trained part-based models
PF Felzenszwalb, RB Girshick… - IEEE transactions on …, 2009 - ieeexplore.ieee.org
We describe an object detection system based on mixtures of multiscale deformable part
models. Our system is able to represent highly variable object classes and achieves state-of …
models. Our system is able to represent highly variable object classes and achieves state-of …
Adaptive data augmentation for image classification
Data augmentation is the process of generating samples by transforming training data, with
the target of improving the accuracy and robustness of classifiers. In this paper, we propose …
the target of improving the accuracy and robustness of classifiers. In this paper, we propose …
Visual turing test for computer vision systems
D Geman, S Geman, N Hallonquist… - Proceedings of the …, 2015 - National Acad Sciences
Today, computer vision systems are tested by their accuracy in detecting and localizing
instances of objects. As an alternative, and motivated by the ability of humans to provide far …
instances of objects. As an alternative, and motivated by the ability of humans to provide far …
A discriminatively trained, multiscale, deformable part model
P Felzenszwalb, D McAllester… - 2008 IEEE conference …, 2008 - ieeexplore.ieee.org
This paper describes a discriminatively trained, multiscale, deformable part model for object
detection. Our system achieves a two-fold improvement in average precision over the best …
detection. Our system achieves a two-fold improvement in average precision over the best …
Unsupervised learning of invariant feature hierarchies with applications to object recognition
MA Ranzato, FJ Huang, YL Boureau… - 2007 IEEE conference …, 2007 - ieeexplore.ieee.org
We present an unsupervised method for learning a hierarchy of sparse feature detectors that
are invariant to small shifts and distortions. The resulting feature extractor consists of …
are invariant to small shifts and distortions. The resulting feature extractor consists of …
[图书][B] Recognition using visual phrases
MA Sadeghi, A Farhadi - 2011 - ieeexplore.ieee.org
In this paper we introduce visual phrases, complex visual composites like “a person riding a
horse”. Visual phrases often display significantly reduced visual complexity compared to …
horse”. Visual phrases often display significantly reduced visual complexity compared to …
Hough-based tracking of non-rigid objects
Online learning has shown to be successful in tracking-by-detection of previously unknown
objects. However, most approaches are limited to a bounding-box representation with fixed …
objects. However, most approaches are limited to a bounding-box representation with fixed …