Name: Mariya Hendriksen
Type: User
Company: University of Amsterdam
Bio: Intern @Google Gemini & Ph.D. candidate in multimodal ML for IR.
Interned at Bloomberg AI, AmazonScience, @ratschlab (ETH Zurich), KU Leuven
Twitter: MarieHendriksen
Blog: mariyahendriksen.github.io
Mariya Hendriksen's Projects
scripts for the course "Artificial Neural Networks" at KU Leuven
Deep Learning Computer Vision Algorithms for Real-World Use
An Image/Text Retrieval Test Collection to Support Multimedia Content Creation
Attention based dialog embedding for dialog breakdown detection (in DSTC6 task 3)
Awesome list for research on CLIP (Contrastive Language-Image Pre-Training).
A repository to curate and summarise research papers related to fashion and e-commerce
Reading list for research topics in intent analysis.
Reading list for research topics in multimodal machine learning
(เท`๊ณยดเท) A Survey on Text-to-Image Generation/Synthesis.
Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome
EasyTransfer is designed to make the development of transfer learning in NLP applications easier.
This repository contains the code for the paper "Extending CLIP for Category-to-image Retrieval in E-commerce" published at ECIR 2022.
This repository contains the code for the paper "Object-centric vs. Scene-centric Image-Text Cross-modal Retrieval: A Reproducibility Study" published at ECIR 2023.
The https://freeCodeCamp.org open source codebase and curriculum. Learn to code for free together with millions of people.
The repository contains some pieces of code that I found useful when it comes writing a scientific paper or experiments
Converting GloVe vectors into word2vec format for easy usage with Gensim
Course materials for Georgia Tech CS 4650 and 7650, "Natural Language"
PyTorch Blog Post On Image Similarity Search
Uncovering common themes from a large number of unor- ganized search queries is a primary step to mine insights about aggregated user interests. Common topic model- ing techniques for document modeling often face sparsity problems with search query data as these are much shorter than documents. We present two novel techniques that can discover semantically meaningful topics in search queries: i) word co-occurrence clustering generates topics from words frequently occurring together; ii) weighted bigraph cluster- ing uses URLs from Google search results to induce query similarity and generate topics. We exemplify our proposed methods on a set of Lipton brand as well as make-up & cos- metics queries. A comparison to standard LDA clustering demonstrates the usefulness and improved performance of the two proposed methods. keywords: search queries, topic clustering, word co- occurrence, bipartite graph, co-clustering.
(CVPR2021) Kaleido-BERT: Vision-Language Pre-training on Fashion Domain
Deep Learning for humans
This repository walks you through the Object Oriented Programming in python. Illustrates real world examples, working codes and going about finding a coding solution.