Antler Program T-5days
We are about to start the Antler program in the Nordics in just 5 days and I can’t wait. For the past 6 weeks, we’ve had the pre-ramp phase, where we already started chatting with other founders and Antler coaches, mentors and partners. For those that don’t know, Antler is a 12-week program that helps you meet like-minded founders and work on ideas in a systematic way. At the end of the program, you present your progress to an Investment Committee to see if your startup will …
Tutorial: Intro to Deep Learning
In this talk, I give a gentle introduction to the fundamental concepts behind Deep Learning. The underlying concepts are surprisingly simple, but extremely powerful. I hope you enjoy it.
Waste Analytics System for Greyparrot.ai
At Greyparrot.ai, I helped build a world-class waste analytics platform. I led the Deep Learning team to create a system that automatically recognizes all trash items going through recycling facilities, helping recover all valuable materials and converting them to assets. Cameras were installed on top of conveyor belts that transport waste. Our tech accurately recognized around 50 distinct object categories and hundreds of brands, empowering robotic manipulation and data-driven insights. As Head …
Talk: Computer Vision for Recycling and Waste Management
I gave a talk about how we are using Computer Vision to detect and track all waste through recycling facilities for the Women in Data Science group.
SETI Talk: Planetary Defense: Long Period Comets
Together with my team, we gave a talk on how we can provide more warning time in case a long-period comet happens to be in a collision trajectory with Earth. .
Searching for Long Period Comets with Deep Learning at NASA and SETI
In planetary defence (yes! there is such a thing, where scientists and engineers try to defend the planet from hazards), long-period comets are recognized as the potentially most devastating threat. However, any new comet on an impact trajectory would likely only be discovered about one year before impact. The goal of this project is to add years of extra warning time by providing comet searchers directions on where to look for comets when they are still far out. To aid and guide a dedicated …
Get the Look on our Chatbot with Visual Search
Leveraging our image and pattern recognition technology, we developed a chatbot that enables users to search product collections using images. Additionally, users can search using both language and images together. For example, I like this item, but I want it with a longer skirt and a V-neck instead of high neck. See it in action here: Your browser does not support the video tag. From the video above, you can see you can perform the following actions: Upload a picture of something you like and …
Talk at ReWork: Deep Learning for Fashion Attributes Search
I gave a talk on how to use Deep Learning to search and serve relevant products to your web visitors. The fashion industry is a visual world. Millions of images are displayed everyday by fashion commerce sites to serve consumers the latest trends and products. However, automatically categorizing and searching through large collections of images according to fine-grained attributes remains a challenge. In this talk we present our research on deep learning techniques to automatically identify …
Transforming the in-store shopping experience with AI
At Macty, we developed a novel in-store experience, where users can upload images of outfits and we suggest lingerie to pair it with. Our ‘Complete the Look’ application inspires customers while helping sellers increase the findability of their products and stimulate sales.” We use advanced image recognition to detect visual attributes from outfits and lingerie to pair them together. Here’s a demo of what this looks like:
Cross-modal Search for Fashion Attributes
In this paper we develop a neural network which learns inter- modal representations for fashion attributes to be utilized in a cross-modal search tool. Our neural network learns from organic e-commerce data, which is characterized by clean image material, but noisy and incomplete product descrip- tions. First, we experiment with techniques to segment e- commerce images and their product descriptions into respec- tively image and text fragments denoting fashion attributes. Here, we propose a …
Latent Dirichlet Allocation for Linking User-Generated Content and e-Commerce Data
Automatic linking of online content improves navigation possibilities for end users. We focus on linking content generated by users to other relevant sites. In particular, we study the problem of linking information between different usages of the same language, e.g., colloquial and formal idioms or the language of consumers versus the language of sellers. The challenge is that the same items are described using very distinct vocabularies. As a case study, we investigate a new task of linking …
Learning to Bridge Colloquial and Formal Language Applied to Linking and Search of E-Commerce Data
We study the problem of linking information between different idiomatic usages of the same language, for example, colloquial and formal language. We propose a novel probabilistic topic model called multi-idiomatic LDA (MiLDA). Its modeling principles follow the intuition that certain words are shared between two idioms of the same language, while other words are non-shared. We demonstrate the ability of our model to learn relations between cross-idiomatic topics in a dataset containing product …
Inferring User Interests on Social Media From Text and Images
We propose to infer user interests on social media where multi-modal data (text, image etc.) exist. We leverage user-generated data from Pinterest.com as a natural expression of users’ interests. Our main contribution is exploiting a multi-modal space composed of images and text. This is a natural approach since humans express their interests with a combination of modalities. We performed experiments using the state-of-the-art image and textual representations, such as convolutional neural …
Cross-Modal Fashion Search
In this paper we show an online demo that allows bidrectional multimodal queries for garments. Check out our paper Cross-Modal Fashion Search In Lecture Notes in Computer Science (LNCS) Vol. 9517, pp 367-373, 2016 Susana Zoghbi, Geert Heyman, Juan Carlos Gomez, Sien Moens PDF
Are words enough?: a study on text-based representations and retrieval models for linking pins to online shops
User-generated content offers opportunities to learn about people’s interests and hobbies. We can leverage this infor- mation to help users find interesting shops and businesses find interested users. However this content is highly noisy and unstructured as posted on social media sites and blogs. In this work we evaluate different textual representations and retrieval models that aim to make sense of social media data for retail applications. Our task is to link the text of pins (from …