/HOTAD

Hierarchical Local-Global Fusion for One-stage Open-vocabulary Temporal Action Detection

HOTAD | Hierarchical Local-Global Fusion for One-stage Open-vocabulary Temporal Action Detection

This repository is the official implementation of 'Hierarchical Local-Global Fusion for One-stage Open-vocabulary Temporal Action Detection' by Trung Thanh Nguyen, Yasutomo Kawanishi, Takahiro Komamizu, and Ichiro Ide.

The source-code will be available.

Acknowledgment

This work was partly supported by the Japan Society for the Promotion of Science (JSPS) KAKENHI JP21H03519 and JP24H00733. The computation was carried out using the General Projects on supercomputer "Flow" at Information Technology Center, Nagoya University.

Contact

Trung Thanh NGUYEN - nguyent[at]cs.is.i.nagoya-u.ac.jp or thanh.nguyen.rc[at]a.riken.jp