Zoom Better to See Clearer: Human Part Segmentation with Auto Zoom Net

By Fangting Xia, Peng Wang, Liang-Chieh Chen, Alan L. Yuille. 2015

39 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

Citations in the corpus

Rethinking Atrous Convolution for Semantic Image Segmentation (2017, background): “2 for illustration) that exploit context information for semantic segmentation [25, 13, 52, 8, 81, 46, 55, 63, 75].”
UberNet: Training a Universal Convolutional Neural Network for Low-, Mid-, and High-Level Vision Using Diverse Datasets and Limited Memory (2016, background): “mean IoU Deeplab LargeFOV [106] 51.78 Deeplab LargeFOV-CRF [106] 52.95 Multi-scale averaging [15] 54.91 Attention [15] 55.17 Auto Zoom [106] 57.54 Graph-LSTM [60] 60.16 Ours, 1-Task 51.98 Ours, 7-Task 48.82 Table 7: Part segmentation - mean Intersction-Over-Union accuracy on the dataset of [17].”
Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features (2018, background): “A large number of works [1, 18, 32] have been proposed based on FCN and DeepLab.”
Look into Person: Self-Supervised Structure-Sensitive Learning and a New Benchmark for Human Parsing (2017, methodology): “apture the rich structure information based on the advanced CNN architecture, common solutions inlcude the combination of CNNs and CRFs [4,37] and the adoptions of multi-scale feature representations [4,5,30]. Chen et al. [5] proposed an attention mechanism that learns to weight the multi-scale feat”
NDDR-CNN: Layerwise Feature Fusing in Multi-Task CNNs by Neural Discriminative Dimensionality Reduction (2018, background): “Benefiting from that, significant improvements have been witnessed in fundamental computer vision tasks, such as image classification [23, 47, 16, 19, 18], object detection [9, 8, 38, 15, 37, 28, 46, 50, 44, 45], semantic segmentation [4, 29, 39, 1, 35, 5, 2, 51, 3], etc.”
Semantic Object Parsing with Graph LSTM (2016, methodology): “Recently, Convolutional Neural Networks (CNNs) have demonstrated exciting success in various pixel-wise prediction tasks such as semantic segmentation [6][7], semantic part segmentation [8][9] and depth prediction [10].”
Self-Correction for Human Parsing (2019, unknown): “ state-of-the-arts on LIP validation set. ydesignates the test time augmentation. Method head torso u-arm l-arm u-leg l-leg bkg mIoU Attention [5] 81.47 59.06 44.15 42.50 38.28 35.62 93.65 56.39 HAZN [30] 80.76 60.50 45.65 43.11 41.21 37.74 93.78 57.54 LG-LSTM [20] 82.72 60.99 45.40 47.76 42.33 37.9”
Unite the People: Closing the Loop Between 3D and 2D Human Representations (2017, background): “Their representational power has led to increasingly robust algorithms for bounding box detection [10], keypoint detection [19, 32, 42] and body part segmentation [7, 15, 43].”
Instance-level Human Parsing via Part Grouping Network (2018, methodology): “ing Network 11 Table 2: Comparison of semantic part segmentation performance with the state-of-theart methods on the PASCAL-Person-Part [6]. Method head torso u-arms l-arms u-legs l-legs Bkg Avg HAZN [39] 80.79 59.11 43.05 42.76 38.99 34.46 93.59 56.11 Attention [5] 81.47 59.06 44.15 42.50 38.28 35.”
Look into Person: Joint Body Parsing & Pose Estimation Network and a New Benchmark (2018, methodology): “Following [17], [19], the annotations are merged to be six person part classes and one background class, which are head, torso, upper / lower arms and upper / lower legs.”
Dense and Low-Rank Gaussian CRFs Using Deep Embeddings (2017, methodology): “For this task, we compare our approach to the following methods: (a) the Deeplab attention to scale network [4], (b) the Auto Zoom network [37], (c) the Local Global LSTM network [25] which combines local and global cues via LSTM units, (d) the Graph LSTM network [24], (e) the base network with and ”