Lighthouse: A User-Friendly Library for Reproducible Video Moment Retrieval and Highlight Detection
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912061792976896 |
|---|---|
| author | Nishimura, Taichi Nakada, Shota Munakata, Hokuto Komatsu, Tatsuya |
| author_facet | Nishimura, Taichi Nakada, Shota Munakata, Hokuto Komatsu, Tatsuya |
| contents | We propose Lighthouse, a user-friendly library for reproducible video moment retrieval and highlight detection (MR-HD). Although researchers proposed various MR-HD approaches, the research community holds two main issues. The first is a lack of comprehensive and reproducible experiments across various methods, datasets, and video-text features. This is because no unified training and evaluation codebase covers multiple settings. The second is user-unfriendly design. Because previous works use different libraries, researchers set up individual environments. In addition, most works release only the training codes, requiring users to implement the whole inference process of MR-HD. Lighthouse addresses these issues by implementing a unified reproducible codebase that includes six models, three features, and five datasets. In addition, it provides an inference API and web demo to make these methods easily accessible for researchers and developers. Our experiments demonstrate that Lighthouse generally reproduces the reported scores in the reference papers. The code is available at https://github.com/line/lighthouse. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_02901 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Lighthouse: A User-Friendly Library for Reproducible Video Moment Retrieval and Highlight Detection Nishimura, Taichi Nakada, Shota Munakata, Hokuto Komatsu, Tatsuya Computer Vision and Pattern Recognition Computation and Language Multimedia We propose Lighthouse, a user-friendly library for reproducible video moment retrieval and highlight detection (MR-HD). Although researchers proposed various MR-HD approaches, the research community holds two main issues. The first is a lack of comprehensive and reproducible experiments across various methods, datasets, and video-text features. This is because no unified training and evaluation codebase covers multiple settings. The second is user-unfriendly design. Because previous works use different libraries, researchers set up individual environments. In addition, most works release only the training codes, requiring users to implement the whole inference process of MR-HD. Lighthouse addresses these issues by implementing a unified reproducible codebase that includes six models, three features, and five datasets. In addition, it provides an inference API and web demo to make these methods easily accessible for researchers and developers. Our experiments demonstrate that Lighthouse generally reproduces the reported scores in the reference papers. The code is available at https://github.com/line/lighthouse. |
| title | Lighthouse: A User-Friendly Library for Reproducible Video Moment Retrieval and Highlight Detection |
| topic | Computer Vision and Pattern Recognition Computation and Language Multimedia |
| url | https://arxiv.org/abs/2408.02901 |