Pose pooling kernels for sub-category recognition

By Ning Zhang, Ryan Farrell, Trevor Darrell. 2012

144 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition (2015, background): “Sec. 5, and conclude with discussion in Sec. 6. 2 Related Work Fine-Grained Recognition. The majority of research in ne-grained recognition has focused on developing improved models for classication [1,3,5,7,9,8,14,16,18,20,21,22,28,29,36,37,41,42,49,51,50,66,68,69,71,73,72,76,77,75,78]. The Unreaso”
Bilinear CNN Models for Fine-Grained Visual Recognition (2015, background): “Recently variants of such models based on convolutional neural networks (CNNs) [2, 38] have been shown to significantly improve over earlier work that relied on hand-crafted features [1, 11, 39].”
PANDA: Pose Aligned Networks for Deep Attribute Modeling (2013, background): “Several approaches [11, 26] have used poselets as a part localization scheme for fine-grained categorization tasks which are related to attribute prediction.”
Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks (2015, background): “One of the earliest work in the area of fine-grained recognition uses an ellipsoid to model the bird pose [13] and fuse obtained parts using very specific kernel functions [38].”
Bird Species Categorization Using Pose Normalized Deep Convolutional Nets (2014, methodology): “Areas explored include feature representations that better preserve fine-grained information [35, 46, 47, 48], segmentation-based approaches [1, 13, 14, 15, 21, 37] that facilitate extraction of purer features, and part/pose normalized feature spaces [5, 6, 19, 33, 38, 39, 43, 50, 51].”
Which Looks Like Which: Exploring Inter-class Relationships in Fine-Grained Visual Categorization (2014, methodology): “Most of the existing works only focused on solving the first issue by proposing new feature representations, as they emphasized that insufficient discriminative power resides in the way that features are encoded [19,41,18,43,34,40].”
Local Alignments for Fine-Grained Categorization (2014, methodology): “Recent works in computer vision have verified this mechanism (Farrell et al. 2011; Zhang et al. 2012; Chai et al. 2013; Zhang et al. 2013; Berg and Belhumeur 2013).”
Improving Fine-Grained Visual Classification using Pairwise Confusion (2017, background): “Pose-normalized CNNs have also been shown to be eﬀective at FGVC [19,20].”
Hierarchical Part Matching for Fine-Grained Visual Categorization (2013, background): “Wah [19] Zhang [24] Wang [20] Xie [21] Ours 17.”
The Ignorant Led by the Blind: A Hybrid Human–Machine Vision System for Fine-Grained Categorization (2014, methodology): “FGVC methods that incorporate a super-category detection model (Farrell et al. 2011; Wah et al. 2011; Parkhi et al. 2011; Zhang et al. 2012; Liu et al. 2012; Parkhi et al. 2012) (i.”
CNN Features Off-the-Shelf: An Astounding Baseline for Recognition (2014, methodology): “We [43] 28.20 RF[42] 19.20 DPD[44] 50.98 Poof[5] 56.78 Oxford 102 ﬂowers dataset [25] contains 102 categories.”
Fine-Grained Crowdsourcing for Fine-Grained Recognition (2013, methodology): “1The results from [38] on the same 14 classes are not comparable as a newer version [33] of the dataset with more images is used”
Learning a Discriminative Filter Bank Within a CNN for Fine-Grained Recognition (2016, background): “ response map. vantages of both categories of previous approaches. 2. Related Work Fine-grained recognition Research in ﬁne-grained recognition has shifted to deep learning from multistage frameworks [48,38,13,30,34,29,8,53,4,3,49,6, 35,10,54,14] based on hand-crafted features such as utilizing DPM ”
Weakly Supervised Fine-Grained Image Categorization (2015, methodology): “For example, in [8, 33], the poselet [2] is used to detect object parts.”
Multiple Granularity Descriptors for Fine-Grained Categorization (2015, methodology): “To tackle the issue of the insufficient discriminative power for fine-grained categorization, some of the existing works focused on feature encoding, such as partbased or pose normalized frameworks[5][36][38][37] and segmentation-based methods[1][7][14].”
POOF: Part-Based One-vs.-One Features for Fine-Grained Categorization, Face Verification, and Attribute Estimation (2013, background): “[8, 32, 33, 35] in different ways attempt to find parts of the image that are discriminative without explicit part labels, but cannot achieve the accuracy of a supervised part-based approach.”
Fine-grained recognition without part annotations (2015, background): “Compared to generic object recognition, fine-grained recognition benefits more from learning critical parts of the objects that can help align objects of the same class and discriminate between neighboring classes [3, 16, 52, 10, 13].”
Multipath Sparse Coding Using Hierarchical Matching Pursuit (2013, methodology): “to boost the classification accuracy; pose pooling [34] exploits additional labeled parts to train and test models.”