Visual Content Analysis
for Innovative Advertising and Selling

Stimulate purchases via any visual content

1
Video Content Targeting Engine “Palantir”

makes video a showcase of goods and services

Content-based targeting as a way of additional video monetization in conditions of extended privacy protection
Features
Accurate and fast (in real time) content recognition and fashion retrieval.

Configurable flexible and scalable using hardware.

Able working with GPUs of different types.

Distributed computing on servers and GPUs.

Ready-to-go pipeline.

API for simple integration.

Benefits
New ways of targeting that protect privacy.
Stimulating impulsive purchases of goods from content.
Audience loyalty: entertainment and involving.
Unobtrusive and effective advertising.
Trusted

The engine was used to search for analogues of clothes from TV shows (in third-party app) and for contextual ad on HbbTV.  


1a
Contextual Advertising in Video
Match video content with relevant ads and offers

How it works:

  • Objects detection
  • Scene analysis
  • Video fragments classification
  • Video fragments matching with categories of goods and services to place relevant ads

Special Features

The most common types of scenes in typical video content are recognized and associated with ad categories, for example food delivery, sporting goods, pets keeping, and café services.

High accuracy of scene type recognition.


1b
Fashion Recommendations from Video
Visual search for analogs of clothing items from the video
How it works:
  • Object detection and tracking
  • Person appearance matching with one of video characters
  • Gender recognition
  • Pose estimation
  • Features extraction for garments
  • Similar offers search by a set of samples from video, based on features similarity

Special Features

Variety of supported object types: clothes, shoes, hats, bags, and accessories, such as ties and glasses.

Able to work with millions of Stock Keeping Units in multiple shops, keeping the catalog up-to date on the daily basis.

High accuracy recommendations of similar merchandise items.


2
Solutions for Fashion e-Commerce
Increase sales through effective tools
based on product appearance analysis
AUTOMATIC TAGGING AND TITLES GENERATION

Efficient alternative to manual tagging: number of tags per product is doubled with the similar accuracy.

Thousand tags supported: category and model of clothing, shades of colors, texture, trim, material properties, style, gender, special attributes such as sleeve shape, heel height, etc.

Providing meaningful titles in a readable form.



SIMILAR OFFERS SEARCH

Search for similar offers by photo.

A product photo or any image uploaded by the user can be used as a search sample.

This efficient alternative to text search provides smart navigation in online fashion shops.

All detected garments in the uploaded photo are samples for retrieval enabling the user to reproduce the whole seen look.



LOOK BUILDER

Pick up variants of complementary clothing products to combine them with the sample item or with its analogues.

Scalable solution: no manual marking required.

Cross-selling as a benefit.



VIRTUAL TRY-ON
(in progress)

Get the image roughly predicting how the user will look in the selected dress.

Two images required: photo of the desired dress, demonstrated by the model in online shop, and user’s photo.

Give customers the opportunity to see their image in the selected garments and to make informed decision about purchase.

Remove barriers to online shopping
and reduce returns.



The approach is based on the Generative Adversarial Network (GAN).

Features

Variety of supported object types: clothes, shoes, hats, bags, and accessories, such as ties and glasses.

Variety of image types: product photos, images from the Internet, UGC, video.

High accuracy recommendations of similar and complementary merchandise items.

Real time processing.

Configurable flexible and scalable using hardware.

Able working with GPUs of different types.

Distributed computing on servers and GPUs.

Ready-to-go pipeline.

API for simple integration.

Benefits
Audience loyalty and engagement growth.
Cross-selling.
Sales and retention growth.
Identification of popular fashion trends based on image recognition.
Trusted
Trusted by independent companies including two large European marketplaces.

Technologies
Machine Learning, Computer Vision, Neural Networks
How it works:

Objects detection

Objects tracking in videos

Persons and face appearances detection

Gender recognition

Human pose estimation

Garments detection, segmentation and recognition

Similar offers search for any garment based on its neural network features

Video scene analysis

Video fragments classification and matching with categories of goods and services for smart advertising

Video sentiment recognition (in progress)

Ready for use digital AI-based platform for visual content processing


DressCoder

CV expert in visual content understanding specializing in fashion recognition,

powering intelligent advertising and innovative sales practices

Authors of the world state of the art technological solutions, including achievements such as

- Top 1 in the clothing recognition competition: iMaterialist Challenge at FGVC 2017

- Two patents in Computer Vision

High recognition accuracy and real-time performance characterizes DressCoder products and solutions.


Get in Touch

Please contact us at dresscoder.team@gmail.com

This site was made on Tilda — a website builder that helps to create a website without any code
Create a website