StreetStyle: Exploring world-wide clothing styles from millions of photos

Matzen, Kevin; Bala, Kavita; Snavely, Noah

doi:10.48550/arxiv.1706.01869

Cited by 16 publications

(28 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2. The GeoStyle dataset, like any Internet photo dataset, it has certain biases in terms of the demographics of the people who have uploaded photos and the locations-as discussed by the dataset creators [29]. These biases may affect the type of styles considered and their measured popularity.…”

Section: Style Trajectoriesmentioning

confidence: 99%

From Paris to Berlin: Discovering Fashion Style Influences Around the World

Al-Halah¹,

Grauman²

2020

Preprint

View full text Add to dashboard Cite

The evolution of clothing styles and their migration across the world is intriguing, yet difficult to describe quantitatively. We propose to discover and quantify fashion influences from everyday images of people wearing clothes. We introduce an approach that detects which cities influence which other cities in terms of propagating their styles. We then leverage the discovered influence patterns to inform a forecasting model that predicts the popularity of any given style at any given city into the future. Demonstrating our idea with GeoStyle-a large-scale dataset of 7.7M images covering 44 major world cities, we present the discovered influence relationships, revealing how cities exert and receive fashion influence for an array of 50 observed visual styles. Furthermore, the proposed forecasting model achieves state-of-the-art results for a challenging style forecasting task, showing the advantage of grounding visual style evolution both spatially and temporally.

show abstract

Section: Style Trajectoriesmentioning

confidence: 99%

From Paris to Berlin: Discovering Fashion Style Influences Around the World

Al-Halah¹,

Grauman²

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…One recent state-of-the-art study of fashion trends based on social media [2] extracted fashion attributes from social media images with a CNN model and investigated the trends of specific attributes in certain cities. Compared with other works which target on implicit fashion styles by visual clustering [10], [11], the fashion trends demonstrated in Mall's work were more specific. However, the fashion attributes it investigated to reveal specific fashion trends were coarsegrained and of less significance, sometimes showing seasonal patterns only, for example, wearing jacket.…”

mentioning

confidence: 88%

“…It trained a neural network model to detect the fashion attributes and learned a set of fashion styles based on attributes through Gaussian mixture model. The dataset they adopted is the GeoStyle dataset proposed by Matzen et al [2], [10]. In this dataset, more specific fashion attributes such as the neckline shape or sleeve length were explored.…”

Section: A Research Targets and Datasets For Fashion Trend Forecastingmentioning

confidence: 99%

“…For the annotations, there are 14 binary attributes (wearing Jacket, wearing scarf, collar presence, etc), 13 colors (black, white, etc), 7 categories (shirt, outwear, etc), 3 sleeve length (long, short, no sleeve), 3 neckline shape (round, folded, v-shape) and 6 clothing pattern (solid, graphics, etc), 46 different fashion elements in total. Readers can refer to [10] for more details about the fashion attributes adopted by GeoStyle. The temporal trend for each attribute in each city for each week is generated by computing the average appearances proportion of an attribute across all photos from that week and city [2].…”

Section: Problem Formulation and Datasetmentioning

confidence: 99%

See 1 more Smart Citation

Leveraging Multiple Relations for Fashion Trend Forecasting Based on Social Media

Ding

Liao

et al. 2022

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Fashion trend forecasting is of great research significance in providing useful suggestions for both fashion companies and fashion lovers. Although various studies have been devoted to tackling this challenging task, they only studied limited fashion elements with highly seasonal or simple patterns, which could hardly reveal the real complex fashion trends. Moreover, the mainstream solutions for this task are still statistical-based and solely focus on time-series data modeling, which limit the forecast accuracy. Towards insightful fashion trend forecasting, previous work [1] proposed to analyze more fine-grained fashion elements which can informatively reveal fashion trends. Specifically, it focused on detailed fashion element trend forecasting for specific user groups based on social media data. In addition, it proposed a neural network-based method, namely KERN, to address the problem of fashion trend modeling and forecasting. In this work, to extend the previous work [1], we propose an improved model named Relation Enhanced Attention Recurrent (REAR) network. Compared to KERN, the REAR model leverages not only the relations among fashion elements, but also those among user groups, thus capturing more types of correlations among various fashion trends. To further improve the performance of long-range trend forecasting, the REAR method devises a sliding temporal attention mechanism, which is able to capture temporal patterns on future horizons better. Extensive experiments and more analysis have been conducted on the FIT [1] and GeoStyle [2] datasets to evaluate the performance of REAR. Experimental and analytical results demonstrate the effectiveness of the proposed REAR model in fashion trend forecasting, which also show the improvement of REAR compared to the KERN.

show abstract

“…Furthermore, applying recognition systems to large collections of images can also reveal cultural trends or give us insight into the visual patterns in the world (e.g. [32,29,26]). Human-created images, such as paintings, are particularly interesting to analyze from this perspective.…”

Section: Introductionmentioning

confidence: 99%

Insights From A Large-Scale Database of Material Depictions In Paintings

Lin¹,

Zuijlen²,

Wijntjes³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Deep learning has paved the way for strong recognition systems which are often both trained on and applied to natural images. In this paper, we examine the give-and-take relationship between such visual recognition systems and the rich information available in the fine arts. First, we find that visual recognition systems designed for natural images can work surprisingly well on paintings. In particular, we find that interactive segmentation tools can be used to cleanly annotate polygonal segments within paintings, a task which is time consuming to undertake by hand. We also find that FasterRCNN, a model which has been designed for object recognition in natural scenes, can be quickly repurposed for detection of materials in paintings. Second, we show that learning from paintings can be beneficial for neural networks that are intended to be used on natural images. We find that training on paintings instead of natural images can improve the quality of learned features and we further find that a large number of paintings can be a valuable source of test data for evaluating domain adaptation algorithms. Our experiments are based on a novel large-scale annotated database of material depictions in paintings which we detail in a separate manuscript.

show abstract

StreetStyle: Exploring world-wide clothing styles from millions of photos

Cited by 16 publications

References 34 publications

From Paris to Berlin: Discovering Fashion Style Influences Around the World

From Paris to Berlin: Discovering Fashion Style Influences Around the World

Leveraging Multiple Relations for Fashion Trend Forecasting Based on Social Media

Insights From A Large-Scale Database of Material Depictions In Paintings

Contact Info

Product

Resources

About