Codebase for "Revisiting spatio-temporal layouts for compositional action recognition" (Oral at BMVC 2021).

Last update: Dec 15, 2022

Overview

Revisiting spatio-temporal layouts for compositional action recognition

Codebase for "Revisiting spatio-temporal layouts for compositional action recognition" (Oral at BMVC 2021).

New year's arrival (01.01.2022) > Code release date > CVPR 2021 deadline (17.11.2021)...

Owner

Gorjan

Third year PhD in Machine Learning at KU Leuven. Interested in multi-modal deep learning and spatial reasoning involving vision and language.

GitHub Repository

Using pretrained language models for biomedical knowledge graph completion.

LMs for biomedical KG completion This repository contains code to run the experiments described in: Scientific Language Models for Biomedical Knowledg

41 Nov 30, 2022

Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation （ICCV2021）

Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation This is a pytorch project for the paper Dynamic Divide-and-Conquer Ad

29 Nov 21, 2022

A library for uncertainty quantification based on PyTorch

Torchuq [logo here] TorchUQ is an extensive library for uncertainty quantification (UQ) based on pytorch. TorchUQ currently supports 10 representation

96 Dec 12, 2022

Cancer metastasis detection with neural conditional random field (NCRF)

NCRF Prerequisites Data Whole slide images Annotations Patch images Model Training Testing Tissue mask Probability map Tumor localization FROC evaluat

731 Jan 01, 2023

Code for "Human Pose Regression with Residual Log-likelihood Estimation", ICCV 2021 Oral

Human Pose Regression with Residual Log-likelihood Estimation [Paper] [arXiv] [Project Page] Human Pose Regression with Residual Log-likelihood Estima

347 Dec 24, 2022

MPI Interest Group on Algorithms on 1st semester 2021

MPI Algorithms Interest Group Introduction Lecturer: Steve Yan Location: TBA Time Schedule: TBA Semester: 1 Useful URLs Typora: https://typora.io Goog

13 Sep 08, 2022

FrankMocap: A Strong and Easy-to-use Single View 3D Hand+Body Pose Estimator

FrankMocap pursues an easy-to-use single view 3D motion capture system developed by Facebook AI Research (FAIR). FrankMocap provides state-of-the-art 3D pose estimation outputs for body, hand, and bo

1.9k Jan 07, 2023

Annotate datasets with a semi-trained or fully trained YOLOv5 model

YOLOv5 Auto Annotator Annotate datasets with a semi-trained or fully trained YOLOv5 model Prerequisites Ubuntu =20.04 Python =3.7 System dependencie

3 May 14, 2022

CM building dataset Timisoara

CM_building_dataset_Timisoara Date created: Febr-2020 The Timi\c{s}oara Building Dataset - TMBuD - is composed of 160 images with the resolution of 76

5 Sep 07, 2022

Code for the paper "Next Generation Reservoir Computing"

Next Generation Reservoir Computing This is the code for the results and figures in our paper "Next Generation Reservoir Computing". They are written

105 Dec 20, 2022

Compositional and Parameter-Efficient Representations for Large Knowledge Graphs

NodePiece - Compositional and Parameter-Efficient Representations for Large Knowledge Graphs NodePiece is a "tokenizer" for reducing entity vocabulary

107 Jan 04, 2023

A distributed deep learning framework that supports flexible parallelization strategies.

FlexFlow FlexFlow is a deep learning framework that accelerates distributed DNN training by automatically searching for efficient parallelization stra

528 Dec 25, 2022

Robustness via Cross-Domain Ensembles

Robustness via Cross-Domain Ensembles [ICCV 2021, Oral] This repository contains tools for training and evaluating: Pretrained models Demo code Traini

27 Dec 23, 2022

Lama-cleaner: Image inpainting tool powered by LaMa

5.8k Jan 05, 2023

[2021][ICCV][FSNet] Full-Duplex Strategy for Video Object Segmentation

Full-Duplex Strategy for Video Object Segmentation (ICCV, 2021) Authors: Ge-Peng Ji, Keren Fu, Zhe Wu, Deng-Ping Fan*, Jianbing Shen, & Ling Shao This

55 Dec 22, 2022

ZSL-KG is a general-purpose zero-shot learning framework with a novel transformer graph convolutional network (TrGCN) to learn class representation from common sense knowledge graphs.

ZSL-KG is a general-purpose zero-shot learning framework with a novel transformer graph convolutional network (TrGCN) to learn class representa

94 Nov 21, 2022

Codebase for "Revisiting spatio-temporal layouts for compositional action recognition" (Oral at BMVC 2021).

Related tags

Overview

Revisiting spatio-temporal layouts for compositional action recognition

Owner

Gorjan

Using pretrained language models for biomedical knowledge graph completion.

Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation （ICCV2021）

A library for uncertainty quantification based on PyTorch

Cancer metastasis detection with neural conditional random field (NCRF)

Code for "Human Pose Regression with Residual Log-likelihood Estimation", ICCV 2021 Oral

MPI Interest Group on Algorithms on 1st semester 2021

FrankMocap: A Strong and Easy-to-use Single View 3D Hand+Body Pose Estimator

Annotate datasets with a semi-trained or fully trained YOLOv5 model

CM building dataset Timisoara

Code for the paper "Next Generation Reservoir Computing"

Compositional and Parameter-Efficient Representations for Large Knowledge Graphs

A distributed deep learning framework that supports flexible parallelization strategies.

Robustness via Cross-Domain Ensembles

Lama-cleaner: Image inpainting tool powered by LaMa

[2021][ICCV][FSNet] Full-Duplex Strategy for Video Object Segmentation

ZSL-KG is a general-purpose zero-shot learning framework with a novel transformer graph convolutional network (TrGCN) to learn class representation from common sense knowledge graphs.

RSC-Net: 3D Human Pose, Shape and Texture from Low-Resolution Images and Videos

ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection

Calling Julia from Python - an experiment on data loading

Malware Env for OpenAI Gym