Fashion Parsing With Weak Color-Category Labels

Liu, Si; Feng, Jiashi; Domokos, Csaba; Xu, Hui; Huang, Junshi; Hu, Zhenzhen; Yan, Shuicheng

doi:10.1109/tmm.2013.2285526

Cited by 197 publications

(131 citation statements)

References 24 publications

Supporting

Mentioning

123

Contrasting

Unclassified

Order By: Relevance

“…Common examples are clothing classification or retrieval [3,2,23], clothing parsing (i.e., semantically label each image pixel) [29,21,4,15] or higher level tasks such as evaluating style or deducting people's occupation or social tribe [24,11,28,22,17].…”

Section: State Of the Artmentioning

confidence: 99%

Multi-modal Embedding for Main Product Detection in Fashion

Simo-Serra

Moreno-Noguer

et al. 2017

2017 IEEE International Conference on Computer Vision Workshops (ICCVW)

View full text Add to dashboard Cite

Section: State Of the Artmentioning

confidence: 99%

Multi-modal Embedding for Main Product Detection in Fashion

Simo-Serra

Moreno-Noguer

et al. 2017

2017 IEEE International Conference on Computer Vision Workshops (ICCVW)

View full text Add to dashboard Cite

“…The Color-Fashion dataset [18] is composed of 2682 images of people wearing different outfits. Furthermore, it is a fashion-oriented dataset, which means that poses may have some variety but the number of people shown in such images may not exceed a person.…”

Section: Datasetsmentioning

confidence: 99%

Stripe based clothes segmentation

Lorenzo-Navarro

Castrillón-Santana

Freire-Obregón

et al. 2015

2015 IEEE International Conference on Multimedia &Amp; Expo Workshops (ICMEW)

View full text Add to dashboard Cite

In this paper, a clothes segmentation method for fashion parsing is described. This method does not rely in a previous pose estimation but people segmentation. Therefore, novel and classic segmentation techniques have been considered and improved in order to achieve accurate people segmentation. Unlike other methods described in the literature, the output is the bounding box and the predominant color of the different clothes and not a pixel level segmentation. The proposal is based on dividing the person area into an initial fixed number of stripes, that are later fused according to similar color distribution. To assess the quality of the proposed method the experiments are carried out with the Fashionista dataset that is widely used in the fashion parsing community.

show abstract

“…After the segmentation of an image using superpixel segmentation, they extract the following features: colour information in both RGB and CieLab colour space which is run through a K-means classifier, obtaining a final length of 150 based on the code words; densely sampled SIFT descriptors are extracted and run through a K-means classifier with a vocabulary of 300 words; finally the 2D co-ordinate of each superpixel centroid is stored as an absolute location feature. To perform this task they use two fashion based auxiliary datasets [21,95] for the process of transfer learning, where [21] is specifically used for its texture annotations. Evaluating their technique as a re-identification method yields state-of-theart for unsupervised matching tested on the VIPeR [59], CUHK01 [87], and PRID450S [122] datasets.…”

Section: Semantic Search Techniquesmentioning

confidence: 99%

“…Approaching the problem of clothing parsing in fashion images in a different manner Liu et al [95] propose the use of weak supervision based on user generated colour category tags ("red jeans", "white t-shirt"). Similar to previous techniques they rely on a pose estimation module to locate the keypoints of interest, and superpixel segmentation to group complementary pixels.…”

Section: Clothing Stylementioning

confidence: 99%

“…Each of the attributes are supplied at an image level, and in high resolution, and include texture based annotation as well as binary classes. From a fashion standpoint the Colourful-Fashion dataset by [95] includes 2, 682 images. Each image contains pixel-level annotations including thirteen colour labels (e.g., brown, red) and twenty three category labels (e.g., bag, T-shirt).…”

Section: Datasetsmentioning

confidence: 99%

See 1 more Smart Citation

Locating People in Video Surveillance from Semantic Descriptions

Halstead¹

View full text Add to dashboard Cite

AcknowledgmentsThe completion of my PhD research programme has been an enjoyable and at times difficult and complex journey that has involved a number of people that have assisted me in so many ways throughout the process. The people that I thank here is by no means a comprehensive list as there isn't enough paper for the names I have to mention.I would firstly like to thank my supervisory team, Clinton Fookes, Sridha Sridharan, and Simon Denman for providing valuable guidance throughout the course of my study. I would like to thank Clinton and Sridha for providing me with the opportunity to study my PhD, and also for providing the Vision and Signal Processing (VSP) laboratory environment that allowed me to research at a high level, and interact with other PhD students to assist with my PhD. I would like to make special mention of Simon for his day to day support and being consistently available to help me with my endless questions, and without his help, guidance, and encouragement I would not have made it to the end of my PhD. Another member of the of the VSP discipline that I would like to thank is David Dean, as a member of VSP he assisted me multiple times throughout the course of my PhD.I would also like to thank the other students and past and present staff within the VSP laboratory, thank you for the sharing of knowledge but mostly thank you all for the entertainment, and enjoyable moments that we shared throughout this time. AbstractIn surveillance and security situations it is often necessary to search and locate a subject of interest from a verbally or textually supplied subject description. At present, searches using these forms of queries are still predominantly performed manually and often ineffectively, via physical searching of a premises or personally watching countless hours of video footage, looking for the specific subject of interest. Surveillance networks are typically monitored by few people viewing several monitors displaying single and multiple camera feeds. In these situations, the ability to translate an externally supplied description into one of computer vision relevance would be of great assistance.To date, state-of-the-art soft biometric based search techniques primarily include some form of pre-enrollment component, where the target subject is enrolled from one camera and searched in other cameras for a match, or alternatively enrolled in an earlier instance of the same camera, and searched for in later footage. These re-identification techniques exclude however, instances where the subject has not previously been located and enrolled from the footage.Soft biometric based semantic search is one technique that provides a solution to this problem. The target query no longer requires scene interrogation and instead can be generated from a textually supplied query. While soft biometrics have obvious limitations, non-permanence and not individually identifiable, they are generally simplistic for a human operator to visually extract and relay to another human operator. They also have th...

show abstract

Fashion Parsing With Weak Color-Category Labels

Cited by 197 publications

References 24 publications

Multi-modal Embedding for Main Product Detection in Fashion

Multi-modal Embedding for Main Product Detection in Fashion

Stripe based clothes segmentation

Locating People in Video Surveillance from Semantic Descriptions

Contact Info

Product

Resources

About