ModaNet

Zheng, Shuai; Yang, Fan; Kiapour, M. Hadi; Piramuthu, Robinson

doi:10.1145/3240508.3240652

Cited by 91 publications

(10 citation statements)

References 43 publications

(63 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning methods can currently solve various problems in the domain of fashion and style such as human pose estimation, body parts segmentation [2], clothing items detection [3], [4] and semantic segmentation [5].…”

Section: Related Workmentioning

confidence: 99%

Assessment of the color compatibility of garments for building a recommendation system for an outfit

Gerasimova,

Sholomov

2024

Sixteenth International Conference on Machine Vision (ICMV 2023)

View full text Add to dashboard Cite

In this paper, we consider the problem of clothes compatibility for total look recommendation systems by means of deep neural networks. This task has become very popular in recent years, primarily due to the growth of online retail sales of clothing. Unlike the existing solutions, we developed a comprehensive model of clothes compatibility evaluation based on color characteristics as well as on the characteristics of the style. As a rule, neural networks are robust to the color characteristics of an image, but color is an extremely important component in the task of a total look evaluation, so such additional branch with color characteristics is well justified. The proposed model uses both: color embedding obtained from color clustering and histograms, and style embedding as an output tensor of ResNet-50 encoder. The paper shows that color embeddings significantly improve the quality of the total look evaluation. The model was trained on Polyvore dataset, which was pre-processed and cleaned from the items not related to the topic of total look compatibility.

show abstract

Section: Related Workmentioning

confidence: 99%

Assessment of the color compatibility of garments for building a recommendation system for an outfit

Gerasimova,

Sholomov

2024

Sixteenth International Conference on Machine Vision (ICMV 2023)

View full text Add to dashboard Cite

show abstract

“…These defects also lead to the low accuracy of image retrieval and limit the application scope of global descriptor algorithm. Just at this time, image retrieval algorithm based on local features brings the dawn to solve this problem [7]. The figure 3…”

Section: Content-based Image Retrievalmentioning

confidence: 99%

Research on unsupervised image retrieval methods based on contrastive learning

Liu

2024

ACE

View full text Add to dashboard Cite

In the convergence of fashion and artificial intelligence (AI), significant strides have been made in areas such as clothing recognition, retrieval, and classification, enabled by advanced AI technologies and expansive annotated datasets. As the AI in Fashion market continues to surge, the future of the fashion industry promises to be redefined by intelligent, efficient, and more accessible solutions. Image retrieval, one of the important parts in AI, has experienced remarkable growth, empowered by advanced algorithms and vast annotated datasets, making it a crucial component in various domains such as digital libraries, online marketing. Therefore, this report mainly provides an extensive review of image retrieval methods and the emerging paradigm of contrastive learning, underscoring their relevance and applications in the realm of artificial intelligence. This paper primarily reviews the technologies in the amalgamation of the image retrieval field and contrastive learning. It elucidates the history and progression of image retrieval, offers a methodical analysis of the two primary approachestext-based image retrieval and content-based image retrievaland examines how contrastive learning is employed in image retrieval systems.

show abstract

“…We use ModaNet dataset 3 in our experiments, which comprises 52,377 fully annotated images for training as well as 13 meta categories including footwear, sunglasses, pants, etc. In detail, we use the first 4,000 images for the testing and the remaining part for training.…”

Section: Experiments 41 Dataset and Evaluation Metricsmentioning

confidence: 99%

A transformer-based semantic segmentation model for street fashion images

PENG

Kameyama

2023

International Workshop on Advanced Imaging Technology (IWAIT) 2023

View full text Add to dashboard Cite

Semantic segmentation is a pixel-level classification problem in computer vision, in which pixels of the same class are grouped into a single category in order to interpret pictures at the pixel level. In this field, semantic segmentation of street fashion images is a challenging task since the clothing items would appear with wide variations in fabrics, layering, occlusion and viewpoint. To help better understanding the street fashion images, we propose a lightweight Semantic Context Aware Transformer (SCAT) to be applied to the semantic segmentation task for street fashion images, which integrates semantic context into the encoding, and models the relationship between multi-level outputs from transformer layers. Extensive experiments and comparisons show that the proposal achieves the state-of-the-art results on ModaNet dataset with relatively small model size, with over 1.1 point improvement compared to Shunted Transformer, and even surpasses other CNNs and Transformers with a large margin of over 2 point in mIoU.

show abstract

ModaNet

Cited by 91 publications

References 43 publications

Assessment of the color compatibility of garments for building a recommendation system for an outfit

Assessment of the color compatibility of garments for building a recommendation system for an outfit

Research on unsupervised image retrieval methods based on contrastive learning

A transformer-based semantic segmentation model for street fashion images

Contact Info

Product

Resources

About