From a0fdfaba98c500a8859ae06b2322080e7ed60ceb Mon Sep 17 00:00:00 2001 From: welix Date: Tue, 24 Sep 2024 13:10:06 +0900 Subject: [PATCH 1/2] Update README.md; fix tiny --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index b18b2fc..4922697 100755 --- a/README.md +++ b/README.md @@ -198,7 +198,7 @@ python training/train.py --model MODEL --dataset DATASET --feature FEATURE [--re | | Options | |---------|----------------------------------------------------------------------------------------------------------| | Model | moment_detr, qd_detr, eatr, cg_detr, uvcom, tr_detr, taskweave_mr2hd, taskweave_hd2mr | -| Feature | resnet_glove, clip, clip_slowfast, clip_slowfast_pann, i3d_clip, clap (AMR) | +| Feature | resnet_glove, clip, clip_slowfast, clip_slowfast_pann, i3d_clip, clap | | Dataset | qvhighlight, qvhighlight_pretrain, activitynet, charades, tacos, tvsum, youtube_highlight, clotho-moment | (**Example 1**) Moment DETR w/ CLIP+Slowfast on QVHighlights: From 765f3cdf7aac94c80bb63283b0b8cb8f83f88f6a Mon Sep 17 00:00:00 2001 From: welix Date: Tue, 24 Sep 2024 13:11:37 +0900 Subject: [PATCH 2/2] Update README.md; fix small --- README.md | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/README.md b/README.md index 4922697..1d529e1 100755 --- a/README.md +++ b/README.md @@ -8,7 +8,7 @@ Lighthouse is a user-friendly library for reproducible video moment retrieval and highlight detection (MR-HD). It supports seven models, four features (video and audio features), and six datasets for reproducible MR-HD, MR, and HD. In addition, we prepare an inference API and Gradio demo for developers to use state-of-the-art MR-HD approaches easily. -Furthermore, Lighthouse supports [audio moment retrieval](https://h-munakata.github.io/Language-based-Audio-Moment-Retrieval/), a task a task that identifies relevant moments from an audio input based on a given text query. +Furthermore, Lighthouse supports [audio moment retrieval](https://h-munakata.github.io/Language-based-Audio-Moment-Retrieval/), a task to identify relevant moments from an audio input based on a given text query. **News**: Our demo paper is available on arXiv. Any comments are welcome: [Lighthouse: A User-Friendly Library for Reproducible Video Moment Retrieval and Highlight Detection](https://www.arxiv.org/abs/2408.02901). @@ -168,7 +168,6 @@ lighthouse/ │ │ ├── resnet │ │ └── slowfast │ ├── tvsum -│ │ ├── audio │ │ ├── clip │ │ ├── clip_text │ │ ├── i3d