Fusing Image and Segmentation Cues for Skeleton Extraction in the Wild

Liu, Xiaolong; Lyu, Pengyuan; Bai, Xiang; Cheng, Ming–Ming

doi:10.1109/iccvw.2017.205

Cited by 16 publications

(8 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning-based methods: With the popularization of CNNs, deep learning-based methods [35,34,17,24,51,22] igure 2. The DeepFlux pipeline.…”

Section: Related Workmentioning

confidence: 99%

“…Liu et at. [24] develop a two-stream network that combines image and segmentation cues to capture complementary information for skeleton localization. In [51], the authors introduce a hierarchical feature integration (Hi-Fi) mechanism.…”

Section: Related Workmentioning

confidence: 99%

“…Though the method we propose in the present paper ben-efits from CNN-based learning, it differs from the methods in [35,34,17,24,51,22] in a fundamental way, due to its different learning objective. Instead of treating object skeleton detection in natural images as a binary classification problem, DeepFlux focuses on learning the context flux of skeletons, and as such includes more informative nonlocal cues, such as the relative position of skeleton points to image points in their vicinity, and thus also, implicitly, the associated object boundaries.…”

Section: Related Workmentioning

confidence: 99%

“…The recent surge of work in convolutional neural networks (CNNs) has lead to vast improvements in the performance of object skeleton detection algorithms [35,34,17,24,51,22]. These existing CNN-based methods usually derive from Holistically-Nested Edge Detection (HED) [47], and frame the problem as binary pixel classification.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

DeepFlux for Skeletons in the Wild

Wang

Tsogkas

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

View full text Add to dashboard Cite

Computing object skeletons in natural images is challenging, owing to large variations in object appearance and scale, and the complexity of handling background clutter. Many recent methods frame object skeleton detection as a binary pixel classification problem, which is similar in spirit to learning-based edge detection, as well as to semantic segmentation methods. In the present article, we depart from this strategy by training a CNN to predict a twodimensional vector field, which maps each scene point to a candidate skeleton pixel, in the spirit of flux-based skeletonization algorithms. This "image context flux" representation has two major advantages over previous approaches. First, it explicitly encodes the relative position of skeletal pixels to semantically meaningful entities, such as the image points in their spatial context, and hence also the implied object boundaries. Second, since the skeleton detection context is a region-based vector field, it is better able to cope with object parts of large width. We evaluate the proposed method on three benchmark datasets for skeleton detection and two for symmetry detection, achieving consistently superior performance over state-of-the-art methods.

show abstract

“…Deep learning-based methods: With the popularization of CNNs, deep learning-based methods [35,34,17,24,51,22] igure 2. The DeepFlux pipeline.…”

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

DeepFlux for Skeletons in the Wild

Wang

Tsogkas

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Liu, Lyu et al [15] also train a CNN using both original images and semantic segmentation probability maps obtained via the DeepLab [16] model. With both of these inputs, the authors demonstrate a high performance when compared to only using the original images, and are able to predict skeletons with high accuracy.…”

Section: Introductionmentioning

confidence: 99%

Person reidentification using deep foreground appearance modeling

Watson

Bhalerao

2018

J. Electron. Imag.

View full text Add to dashboard Cite

Person Re-Identification is the process of matching individuals from images taken of them at different times, and often with different cameras. To perform matching, most methods extract features from the entire image, however, this gives no consideration to the spatial context of the information present in the image. In this paper, we propose using a convolutional neural network approach based on ResNet-50 to predict the foreground of an image: the parts with the head, torso and limbs of a person. With this information, we use the LOMO and Salient Colour Name feature descriptors to extract features primarily from the foreground areas. In addition, we use a distance metric learning technique (XQDA), to calculate optimally weighted distances between the relevant features. We evaluate on the VIPeR, QMUL GRID and CUHK03 data sets, and compare our results against a linear foreground estimation method, and show competitive or better overall matching performance.

show abstract

DeepFlux for Skeleton Detection in the Wild

Wang

Tsogkas

et al. 2021

Int J Comput Vis

View full text Add to dashboard Cite

Fusing Image and Segmentation Cues for Skeleton Extraction in the Wild

Cited by 16 publications

References 20 publications

DeepFlux for Skeletons in the Wild

DeepFlux for Skeletons in the Wild

Person reidentification using deep foreground appearance modeling

DeepFlux for Skeleton Detection in the Wild

Contact Info

Product

Resources

About