From dcbc728f230541cecc51ed4238d310a7a0884774 Mon Sep 17 00:00:00 2001 From: Kyle Min Date: Wed, 12 Jun 2024 13:22:45 -0400 Subject: [PATCH] Visualization example added --- README.md | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 233c05c..1f286fb 100644 --- a/README.md +++ b/README.md @@ -1,11 +1,11 @@ -# Action Scene Graphs for Long-Form Understanding of Egocentric Videos +# Action Scene Graphs for Long-Form Understanding of Egocentric Videos (CVPR 2024) ![image](https://github.com/fpv-iplab/EASG/assets/17033647/e38d266b-ba22-4fff-98b7-29046ec2611d) This repository hosts the code related to the paper -Rodin, Ivan, Antonino Furnari, Kyle Min, Subarna Tripathi, and Giovanni Maria Farinella. "Action Scene Graphs for Long-Form Understanding of Egocentric Videos." Computer Vision and Pattern Recognition Conference (CVPR). 2024. +Ivan Rodin*, Antonino Furnari*, Kyle Min*, Subarna Tripathi, and Giovanni Maria Farinella. "Action Scene Graphs for Long-Form Understanding of Egocentric Videos." Computer Vision and Pattern Recognition Conference (CVPR). 2024. [arXiv pre-print](https://arxiv.org/pdf/2312.03391.pdf) @@ -17,6 +17,9 @@ This repository provides the following components: * Code for the EASG Annotation Tool * Code for the EASG Generation baseline +#### + Example video with dynamic graphs and objects bounding boxes +[![video](http://markdown-videos-api.jorgenkh.no/youtube/Qx3UHbl08K4?width=640&height=360)](https://youtu.be/Qx3UHbl08K4) + ## EASG Labeling system Steps to reproduce the EASG labeling system: @@ -65,7 +68,7 @@ Currently, we are working on extending the dataset to include annotations for vi If you use the code/models hosted in this repository, please cite the following paper: -``` +```bibtex @article{rodin2023action, title={Action Scene Graphs for Long-Form Understanding of Egocentric Videos}, author={Rodin, Ivan and Furnari, Antonino and Min, Kyle and Tripathi, Subarna and Farinella, Giovanni Maria},