The scene-graph-benchmark.pytorch from limgeuntaekk

limgeuntaekk / scene-graph-benchmark.pytorch Goto Github PK

View Code? Open in Web Editor NEW

A new codebase for popular Scene Graph Generation methods (2020). Visualization & Scene Graph Extraction on custom images/datasets are provided. It's also a PyTorch implementation of paper “Unbiased Scene Graph Generation from Biased Training CVPR 2020”

License: MIT License

C++ 0.12% Python 5.81% C 0.07% Cuda 0.79% Jupyter Notebook 93.19% Dockerfile 0.02%

scene-graph-benchmark.pytorch's Introduction

👋 Hi there

My research focuses on Computer Vision, specifically Video Understanding. I am deeply interested in exploring the following three key areas for a comprehensive understanding of videos:
- Human Action Understanding: I view distinguishing dynamic human behaviors as a foundational task that necessitates temporal modeling.
- Scene Graph Representation: I believe it offers essential frameworks for organizing and interpreting the intricate visual data present in videos.
- Open-Vocabulary Learning: I consider it crucial for enabling robust inference in various unseen scenarios, which is vital for practical applications.

📃 Publications

G Lim, H Kim, J Kim Y Choi, Probabilistic Vision-Language Representation for Weakly Supervised Temporal Action Localization. July 2024, ACM MM. [paper][code]
W Jo, G Lim, G Lee, H Kim, B Ko Y Choi, VVS: Video-to-Video Retrieval with Irrelevant Frame Suppression. February 2024, AAAI. [paper][code]
W Jo, G Lim, Y Hwang, G Lee, J Kim, J Yun, J Jung, Y Choi, Simultaneous Video Retrieval and Alignment. March 2023, IEEE Access. [paper]
J Kim, W Jo, G Lim, J Yun, S Kwak, S Jung, W Cheong, H Choo, J Seo, and Y Choi, Compression Method for MPEG CDVA Global Feature Descriptors CDVA, Journal of Broadcast Engineering. May 2022. [paper]
W Jo, G Lim, J Kim, J Yun, Y Choi, Exploring the Temporal Cues to Enhance Video Retrieval on Standardized CDVA. Apr 2022, IEEE Access. [paper][code]