Texture and Shape Biased Two-Stream Networks for Clothing Classification and Attribute Recognition

Zhang, Yuwei; Zhang, Peng; Yuan, Chun; Wang, Zhi

doi:10.1109/cvpr42600.2020.01355

Cited by 43 publications

(25 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, some CNN approaches used a modified version of the VGG16. Furthermore, some CNN approaches used a modified version of the VGG16 [15] to orient the garment recognition towards texture, fabric, shape, or style [16][17][18][19]. Nevertheless, those approaches did not produce a complete clothing ensemble classification; hence, they only obtained a single clothing garment classification per image.…”

Section: Of 28mentioning

confidence: 99%

Using Deep Learning in Real-Time for Clothing Classification with Connected Thermostats

et al. 2022

View full text Add to dashboard Cite

Thermal comfort is associated with clothing insulation, conveying a level of satisfaction with the thermal surroundings. Besides, clothing insulation is commonly associated with indoor thermal comfort. However, clothing classification in smart homes might save energy when the end-user wears appropriate clothes to save energy and obtain thermal comfort. Furthermore, object detection and classification through Convolutional Neural Networks has increased over the last decade. There are real-time clothing garment classifiers, but these are oriented towards single garment recognition for texture, fabric, shape, or style. Consequently, this paper proposes a CNN model classification for the implementation of these classifiers on cameras. First, the Fashion MNIST was analyzed and compared with the VGG16, Inceptionvv4, TinyYOLOv3, and ResNet18 classification algorithms to determine the best clo classifier. Then, for real-time analysis, a new dataset with 12,000 images was created and analyzed with the YOLOv3 and TinyYOLO. Finally, an Azure Kinect DT was employed to analyze the clo value in real-time. Moreover, real-time analysis can be employed with any other webcam. The model recognizes at least three garments of a clothing ensemble, proving that it identifies more than a single clothing garment. Besides, the model has at least 90% accuracy in the test dataset, ensuring that it can be generalized and is not overfitting.

show abstract

Section: Of 28mentioning

confidence: 99%

Using Deep Learning in Real-Time for Clothing Classification with Connected Thermostats

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The recent research in fashion domain evolves from fundamental clothing recognition [24,51], style understanding [7] to aesthetic and compatibility analysis [36,17,11,35,19]. Learning compatibility relationships is a challenging and sophisticated task, as whether two clothes (e.g., top and bottom clothes) are a good match is usually determined by a complex mixture of various factors.…”

Section: Abstract Clothing Recommendation • Explainable Recommender S...mentioning

confidence: 99%

Attribute-aware Explainable Complementary Clothing Recommendation

Chen

Huang

2021

Preprint

View full text Add to dashboard Cite

Modelling mix-and-match relationships among fashion items has become increasingly demanding yet challenging for modern E-commerce recommender systems. When performing clothes matching, most existing approaches leverage the latent visual features extracted from fashion item images for compatibility modelling, which lacks explainability of generated matching results and can hardly convince users of the recommendations. Though recent methods start to incorporate pre-defined attribute information (e.g., colour, style, length, etc.) for learning item representations and improving the model interpretability, their utilisation of attribute information is still mainly reserved for enhancing the learned item representations and generating explanations via post-processing. As a result, this creates a severe bottleneck when we are trying to advance the recommendation accuracy and generating fine-grained explanations since the explicit attributes have only loose connections to the actual recommendation process. This work aims to tackle the explainability challenge in fashion recommendation tasks by proposing a novel Attribute-aware Fashion Recommender (AFRec). Specifically, AFRec recommender assesses the outfit compatibility by explicitly leveraging the extracted attribute-level representations from each item's visual feature. The attributes serve as the bridge between two fashion items, where we quantify the affinity of a pair of items through the learned compatibility between their attributes. Extensive experiments have demonstrated that, by making full use of the explicit attributes in

show abstract

“…Pose information provides us prior knowledge of the interest region and has been utilized in many existing PAR works. Zhang et al (Zhang et al 2020) add a landmark detection branch to jointly learn the attributes and landmarks. Unlike the fashion dataset (Liu et al 2016), PAR datasets are not annotated with landmark information, we have to utilize a well-trained HPE model to generate keypoints as prior knowledge.…”

Section: Related Workmentioning

confidence: 99%

Deep Template Matching for Pedestrian Attribute Recognition with the Auxiliary Supervision of Attribute-wise Keypoints

Zhang,

Ren,

2020

Preprint

View full text Add to dashboard Cite

Pedestrian Attribute Recognition (PAR) has aroused extensive attention due to its important role in video surveillance scenarios. In most cases, the existence of a particular attribute is strongly related to a partial region. Recent works design complicated modules, e.g., attention mechanism and proposal of body parts to localize the attribute corresponding region. These works further prove that localization of attribute specific regions precisely will help in improving performance. However, these part-information-based methods are still not accurate as well as increasing model complexity which makes it hard to deploy on realistic applications. In this paper, we propose a Deep Template Matching based method to capture body parts features with less computation. Further, we also proposed an auxiliary supervision method that use human pose keypoints to guide the learning toward discriminative local cues. Extensive experiments show that the proposed method outperforms and has lower computational complexity, compared with the state-of-the-art approaches on large-scale pedestrian attribute datasets, including PETA, PA-100K, RAP, and RAPv2zs.

show abstract

Texture and Shape Biased Two-Stream Networks for Clothing Classification and Attribute Recognition

Cited by 43 publications

References 28 publications

Using Deep Learning in Real-Time for Clothing Classification with Connected Thermostats

Using Deep Learning in Real-Time for Clothing Classification with Connected Thermostats

Attribute-aware Explainable Complementary Clothing Recommendation

Deep Template Matching for Pedestrian Attribute Recognition with the Auxiliary Supervision of Attribute-wise Keypoints

Contact Info

Product

Resources

About