Pedestrian Parsing via Deep Decompositional Network

By Ping Luo, Xiaogang Wang, Xiaoou Tang. 2013

148 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

Hypercolumns for object segmentation and fine-grained localization (2014, methodology): “There has also been work on parsing pedestrians [3, 31].”
Semantic Image Segmentation via Deep Parsing Network (2015, positive): “With deep models, these works [23, 24, 25, 22, 3, 28, 39, 30, 19] demonstrated encouraging results using simple definition of the pairwise function or even ignore it.”
MARS: A Video Benchmark for Large-Scale Person Re-Identification (2016, methodology): “For GEI, the segmentation method [26] already corrects this artifact, so the improvement is limited (not shown, because it overlaps with other lines).”
DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations (2016, background): “masks of clothes) [20, 12], or cross-domain image correspondences [10, 12].”
A Deep Sum-Product Architecture for Robust Facial Attributes Analysis (2013, background): “These models can be divided into two categories: implicitly learning robust features [22, 4, 13], and explicitly modeling the structure of occlusions [21, 20, 18, 16, 15, 14].”
Pedestrian detection aided by deep learning semantic tasks (2014, background): “This problem is challenging because of large variation and confusion in human body and background scene, as shown in Fig.1 (a), where the positive and hard negative patches have large ambiguity.”
Deep Learning for Semantic Part Segmentation with High-Level Guidance (2015, unknown): “rpixel labels: for each superpixel we compute a histogram of the pixel labels it contains and choose the most Method head upper body lower body FG BG Average SBP [1] 51.6 72.6 71.6 73.3 81.0 70.3 DDN [21] 60.2 75.7 73.1 78.4 85.0 74.5 DL [21] 60.0 76.3 75.6 78.7 86.30 75.4 Ours (CNN) 67.8 77.0 76.0 ”
Beyond Bounding Boxes: Precise Localization of Objects in Images (2015, background): “This is different from most prior work on these problems [57, 56, 60, 59, 4, 45], which operates on the immediate vicinity of ground-truth”
Clothing Co-parsing by Joint Image Segmentation and Labeling (2014, background): “In literature, existing efforts on clothing/human segmentation and recognition mainly focused on constructing expressive models to address various clothing styles and appearances [6, 8, 2, 28, 21, 30, 22].”
Recognize complex events from static images by fusing deep channels (2015, background): “Following the recent success of deep models [6, 12, 20], attempts [23, 30] have been made to connect multiple modalities through deep networks.”
Domain2Vec: Domain Embedding for Unsupervised Domain Adaptation (2020, methodology): “Color [37] 10,000 pedestrian 24 LabelMeFacade [38] 395 building 25 UT Zappos50K [39] 10,000 shoes 26 TRANCOS [40] 1,244 traffic 27 FGVC [40] 10,000 aeroplane 28 Mall Dataset [41] 2,000 mall 29 Chars74K [42] 7,705 character 30 DomainNet [8] 10,000 painting 31 Paris Dataset [43] 3,187 street 32 Domain”