gombru

SocialMediaWeakLabeling

Learning to learn from Web and Social Media data. Joint image-text embeddings oriented to image by text retrieval.

LearnFromWebData

Code used in the paper "Learning to Learn from Web Data through Deep Semantic Embeddings" ECCV 2018 MULA Workshop

HateSpeech

gombru.github.io

My blog

insbcn

Code used in the paper "Learning from #Barcelona Instagram data what Locals and Tourists post about its Neighbourhoods" ECCV 2018 MULA Workshop

MMSemanticRetrievalDemo

multi-modal-hate-speech

Code of the paper "Exploring Hate Speech Detection in Multimodal Publications" accepted in WACV 2020.

face_attributes_retrieval

Project description in https://gombru.github.io/

LocSens

Code of Location Sensitive Image Retrieval and Tagging, ECCV 2020 by Raul Gomez, Jaume Gibert, Lluis Gomez and Dimosthenis Karatzas

HateSonar

Hate Speech Detection Library for Python.

HateSpeechLabeler

chase

Cyber Hate detection And tracking on Social mEdia

datePrediction

deepdream

detectron2

Detectron2 is FAIR's next-generation platform for object detection and segmentation.

EAST

This is a pytorch re-implementation of EAST: An Efficient and Accurate Scene Text Detector.

EAST-1

A tensorflow implementation of EAST text detector

GAN10YearsChallenge

geoRetrieval

geoSemantics

hate-speech-and-offensive-language

Repository for the paper "Automated Hate Speech Detection and the Problem of Offensive Language", ICWSM 2017

iMaterialistFashion

landMarks

lstm_sentence_classifier

LSTM-based Models for Sentence Classification in PyTorch

lucid

A collection of infrastructure and tools for research in neural network interpretability.

magenta_styleTransfer

This is actually a fork of TensorFlow magenta with my version of styleTransfer

pytorch-ssd

MobileNetV1, MobileNetV2, VGG based SSD/SSD-lite implementation in Pytorch 1.0 / Pytorch 0.4. Out-of-box support for retraining on Open Images dataset. ONNX and Caffe2 support. Experiment Ideas like CoordConv.

PytorchCNN

TextStyleTransfer

TextTopicNet

Self-supervised learning of visual features through embedding images into text topic spaces