请选择 进入手机版 | 继续访问电脑版
  • 设为首页
  • 点击收藏
  • 手机版
    手机扫一扫访问
    迪恩网络手机版
  • 关注官方公众号
    微信扫一扫关注
    迪恩网络公众号

xlliu7/MUSES: [CVPR 2021] Multi-shot Temporal Event Localization: a Benchmark

原作者: [db:作者] 来自: 网络 收藏 邀请

开源软件名称(OpenSource Name):

xlliu7/MUSES

开源软件地址(OpenSource Url):

https://github.com/xlliu7/MUSES

开源编程语言(OpenSource Language):

Jupyter Notebook 98.3%

开源软件介绍(OpenSource Introduction):

MUSES

PWC

This repo holds the code and the models for MUSES, introduced in the paper:
Multi-shot Temporal Event Localization: a Benchmark
Xiaolong Liu, Yao Hu, Song Bai, Fei Ding, Xiang Bai, Philip H.S. Torr
CVPR 2021.

MUSES is a large-scale video dataset, designed to spur researches on a new task called multi-shot temporal event localization. We present a baseline aproach (denoted as MUSES-Net) that achieves SOTA performance on MUSES. It also reports an mAP of 56.9% on THUMOS14 at IoU=0.5.

The code largely borrows from SSN and P-GCN. Thanks for their great work!

Find more resouces (e.g. annotation file, source videos) on our project page.

Updates

[2022.3.19] Add support for the MUSES dataset. The proposals, models, source videos of the MUSES dataset are released. Stay tuned for MUSES v2, which includes videos from more countries.
[2021.6.19] Code and the annotation file of MUSES are released. Please find the annotation file on our project page.

Contents



Usage Guide

Prerequisites

[back to top]

The code is based on PyTorch. The following environment is required.

Other minor Python modules can be installed by running

pip install -r requirements.txt

The code relies on CUDA extensions. Build them with the following command:

python setup.py develop

After installing all dependecies, run python demo.py for a quick test.

Data Preparation

[back to top]

We support experimenting with THUMOS14 and MUSES. The video features, the proposals and the reference models are provided on OneDrive.

Features and Proposals

  • THUMOS14: The features and the proposals are the same as thosed used by PGCN. Extract the archive thumos_i3d_features.tar and put the features in data/thumos14 folder. The proposal files are already contained in the repository. We expect the following structure in this folder.

    - data
      - thumos14
        - I3D_RGB
        - I3D_Flow
    
  • MUSES: Extract the archives of features and proposal files.

    # The archive does not have a directory structure
    # We need to create one
    mkdir -p data/muses/muses_i3d_features
    tar -xf muses_i3d_features.tar -C data/muses/muses_i3d_features
    tar -xf muses_proposals.tar -C data/muses

    We expect the following structure in this folder.

    - data
      - muses
        - muses_i3d_features
        - muses_test_proposal_list.txt
        - ...
    

You can also specify the path to the features/proposals in the config files data/cfgs/*.yml.

Reference Models

Put the reference_models folder in the root directory of this code:

 - reference_models
   - muses.pth.tar
   - thumos14_flow.pth.tar
   - thumos14_rgb.pth.tar

Testing Trained Models

[back to top]

You can test the reference models by running a single script

bash scripts/test_reference_models.sh DATASET

Here DATASET should be thumos14 or muses.

Using these models, you should get the following performance

MUSES

0.3 0.4 0.5 0.6 0.7 Average
mAP 26.5 23.1 19.7 14.8 9.5 18.7

Note: We re-train the network on MUSES and the performance is higher than that reported in the paper.

THUMOS14

Modality 0.3 0.4 0.5 0.6 0.7 Average
RGB 60.14 54.93 46.38 34.96 21.69 43.62
Flow 64.64 60.29 53.93 42.84 29.70 50.28
R+F 68.93 63.99 56.85 46.25 30.97 53.40

The testing process consists of two steps, detailed below.

  1. Extract detection scores for all the proposals by running
python test_net.py DATASET CHECKPOINT_PATH RESULT_PICKLE --cfg CFG_PATH

Here, RESULT_PICKLE is the path where we save the detection scores. CFG_PATH is the path of config file, e.g. data/cfgs/thumos14_flow.yml.

  1. Evaluate the detection performance by running
python eval.py DATASET RESULT_PICKLE --cfg CFG_PATH

On THUMOS14, we need to fuse the detection scores with RGB and Flow modality. This can be done by running

python eval.py DATASET RESULT_PICKLE_RGB RESULT_PICKLE_FLOW --cfg CFG_PATH --score_weights 1 1.2 --cfg CFG_PATH_RGB

Training

[back to top]

Train your own models with the following command

python train_net.py  DATASET  --cfg CFG_PATH --snapshot_pref SNAPSHOT_PREF --epochs MAX_EPOCHS

SNAPSHOT_PREF: the path to save trained models and logs, e.g outputs/snapshpts/thumos14_rgb/.

We provide a script that finishes all steps, including training, testing, and two-stream fusion. Run the script with the following command

bash scripts/do_all.sh DATASET

Note: The results may vary in different runs and differs from those of the reference models. It is encouraged to use the average mAP as the primary metric. It is more stable than mAP@0.5.

Citation

Please cite the following paper if you feel MUSES useful to your research

@InProceedings{Liu_2021_CVPR,
    author    = {Liu, Xiaolong and Hu, Yao and Bai, Song and Ding, Fei and Bai, Xiang and Torr, Philip H. S.},
    title     = {Multi-Shot Temporal Event Localization: A Benchmark},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2021},
    pages     = {12596-12606}
}

Related Projects

  • TadTR: Efficient temporal action detectioon (localization) with Transformer.

Contact

[back to top]

For questions and suggestions, file an issue or contact Xiaolong Liu at "liuxl at hust dot edu dot cn".




鲜花

握手

雷人

路过

鸡蛋
该文章已有0人参与评论

请发表评论

全部评论

热门推荐
阅读排行榜
  • ** REJECT ** DO NOT USE THIS CANDIDATE NUMBER. ConsultIDs: none. Reason: This ca

    阅读:198|2022-09-23
  • Simple Task Scheduling System v1.0 was discovered to contain a SQL injection vul

    阅读:193|2022-09-18
  • Simple Task Scheduling System v1.0 was discovered to contain a SQL injection vul

    阅读:193|2022-09-18
  • Novel-Plus v3.6.2 was discovered to contain a hard-coded JWT key located in the

    阅读:205|2022-09-18
  • Novel-Plus v3.6.2 was discovered to contain an arbitrary file download vulnerabi

    阅读:209|2022-09-18
  • Simple Task Scheduling System v1.0 was discovered to contain a SQL injection vul

    阅读:106|2022-09-18
  • An issue was discovered in the Arm Mali GPU Kernel Driver. A non-privileged user

    阅读:232|2022-09-18
  • HashiCorp Boundary up to 0.10.1 did not properly perform data integrity checks t

    阅读:173|2022-09-18
  • In D-Link DIR-816 A2_v1.10CNB04.img a command injection vulnerability occurs in

    阅读:198|2022-09-18
  • D-Link DIR-816 A2_v1.10CNB04.img is vulnerable to Command Injection via /goform/

    阅读:180|2022-09-18

扫描微信二维码

查看手机版网站

随时了解更新最新资讯

139-2527-9053

在线客服(服务时间 9:00~18:00)

在线QQ客服
地址:深圳市南山区西丽大学城创智工业园
电邮:jeky_zhao#qq.com
移动电话:139-2527-9053

Powered by 互联科技 X3.4© 2001-2213 极客世界.|Sitemap