-
Fraunhofer HHI
- Berlin
- ujemd.github.io/resume/
Stars
Scripts for numerical evaluations for the GENEA Gesture Generation Challenge
This repository contains demos I made with the Transformers library by HuggingFace.
Data preparation and loader for AMASS
Magenta: Music and Art Generation with Machine Intelligence
A real-time implementation of "Ray Tracing in One Weekend" using nannou and rust-gpu.
A mask-guided method for control over localized regions in StyleGAN2 images.
A Deep Learning based project for colorizing and restoring old images (and video!)
An audio model for recognizing a whistle pattern was trained to toggle a Sonoff/Ewelink socket device connected to a room light
Implementation of Constructing Human Motion Manifold with Sequential Networks in PyTorch
Sourcecode for the TNNLS 2022 paper: Fusing Higher-Order Features in Graph Neural Networks for Skeleton-Based Action Recognition
This repository provides scripts that can be used to visualize BVH files. These scripts were developed for the GENEA Challenge 2020, and enables reproducing the visualizations used for the challeng…
[ICCV'21] EigenGAN: Layer-Wise Eigen-Learning for GANs
High-Resolution 3D Human Digitization from A Single Image.
State-of-the-Art Text Embeddings
A concise but complete full-attention transformer with a set of promising experimental features from various papers
Codebase for Time-series Generative Adversarial Networks (TimeGAN) - NeurIPS 2019
Automatic headphone equalization from frequency responses
[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821
Type annotations and dynamic checking for a tensor's shape, dtype, names, etc.
Implementation of STAM (Space Time Attention Model), a pure and simple attention model that reaches SOTA for video classification
Send text to girlfriend in the morning
SEAN: Image Synthesis with Semantic Region-Adaptive Normalization (CVPR 2020, Oral)
Navigating StyleGAN2 w latent space using CLIP