"No one is harder on a talented person than the person themselves" - Linda Wilkinson ; "Trust your guts and don't follow the herd" ; "Validate direction not destination" ;

August 14, 2022

Fashion - Papers - Vision and Fashion

Paper #1 - Session-based Complementary Fashion Recommendations

Key Notes

  • Sampling strategy adopted to build the training set
  • A/B test carried out in a fashion e-commerce platform with 28 million active customers.
  • ”Perfect pairings: You might also like”. ‡ese type of recommendations allow customers to continue the fashion discovery journey by €finding items that can be worn together
  • Worn-together concept: two items are complementary if they can be worn together.
  • Collaborative €filltering approach based on cosine similarity
  • Click through rate (CTR) measure
  • Session-based Recommendations
  • Combine both stylistic and functional facets of complementary items across categories
  • Session-based approaches that follow a Recurrent Neural Networks architecture
  • STAMP, a novel Short-Term AŠention Priority Model for Session-based Recommendation
  • Customers’ response to the baseline recommender, and training the model to maximize the accuracy of the next-click prediction
  • Cross-sell sequences selected from the users’ interaction histories
  • Items purchased by users are intuitively more representative for their long-term tastes and preferences.
  • Categorical features coming from the metadata of an item such as the category
  • The training set consists of 5073130 cross-sell examples from
  • 1195512 users with an average length of 13.08

Key observations (Inspirations)

  • Get recent browse / search history
  • Get recent cross-category search/purchases
  • Look at patterns in combinations for search / past purchase / cross category views
  • Club of all of them for Work together / perfect pairing

Paper #2 - +GAN: Complementary Fashion Item Recommendation

Key Notes

  • Generative adversarial model to draw realistic samples from paired fashion clothing distribution
  • Dataset from web crawled data
  • bidirectional LSTM model to sequentially predict the next item
  • A conditional GAN can be trained to fill up this missing piece by generating possible clothing choices which can be subsequently
  • Discrete cosine transform (DCT) 
  • K-means based clustering on the intensity field of the images

Paper #3 - Fashion Recommendation Based on Style and Social Events

Key Notes

  • Semantic layer is based on the style of the proposed dressing
  • Mood and the emotion concealed behind color combination patterns
  • Patterns behind color combinations have been extensively studied
  • Fashion4Events dataset comprising approximately 400k garment images with social event labels
  • DeepFashion2 is a dataset that proposed a unified benchmark for clothes detection, segmentation, retrieval, and landmark prediction
  • Color classifier and the event classifier in our recommendation system
  • Visual-semantic embedding and training a bidirectional LSTM (Bi-LSTM) model to sequentially predict the next item

Paper #4 - A method for extracting emotion using colors comprise the painting image

Key Notes

Colors to Emotions




No comments: