GitHub·Code

Dotori-HJ/Dotori-HJ

0 stars·Updated Feb 2026
Open on GitHub

Authors

Repository owner

Linked papers

Code

DiGIT: Multi-Dilated Gated Encoder and Central-Adjacent Region Integrated Decoder for Temporal Action Detection Transformer

cvpr · 2025

Why Lacuna links this resource
Repository names this paper

## Hello, I'm Ho-Joong Kim 👋 I am a Ph.D. candidate in the Department of Artificial Intelligence at Korea University. My research focuses on computer vision and video understanding, particularly temporal action detection and object detection. I've worked on various video-related tasks, and more recently, I've been exploring vision-language modeling to integrate visual and language representations for various video applications. [![Google Scholar](https://img.shields.io/badge/Google%20Scholar-428

README:focal_exact_title·Open evidence