Skip to content
/ MATR Public

Official Implementation of Moment Alignment Transformer

License

vl2g/MATR

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

59 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

MATR: Aligning Moments in Time using Video Queries (ICCV 2025)

ICCV2025 YouTube Slides arXiv

Overview

This repository contains the official code for training, inference, and evaluation of MATR from the ICCV'25 paper "Aligning Moments in Time using Video Queries".

To setup environment

# create new env MATR
$ conda create -n MATR python=3.10.4

# activate MATR
$ conda activate MATR

# install pytorch, torchvision
$ conda install -c pytorch pytorch torchvision

# install other dependencies
$ pip install -r requirements.txt

Training

In order to train MATR on our proposed dataset or your own dataset please prepare your dataset annotations following the format in data. The dataset directory should have the following structure:

data/
├── sportsmoment/
│   ├── metadata/
│   │   ├── train.jsonl
│   │   └── val.jsonl
│   ├── txt_clip/
│   ├── target_vid_clip/
│   └── query_vid_clip/
└── ActivityNet/
    ├── metadata/
    │   ├── train.jsonl
    │   └── val.jsonl
    ├── txt_clip/
    ├── target_vid_clip/
    └── query_vid_clip/
# set the path and required parameters in the train.sh
$ bash train.sh

Inference

checkpoint

# set the path and required parameters in the inference.py
$ python inference.py

Evaluation

# set the path and required parameters in the eval.py
$ python eval.py

Qualitative Results

Citation

If you find this work useful, please consider citing it as:

@inproceedings{kumar2025matr,
  title={Aligning Moments in Time using Video Queries},
  author={Yogesh Kumar and Uday Agarwal and Manish Gupta and Anand Mishra},
  booktitle={International Conference on Computer Vision, ICCV},
  year={2025},
}

Acknowledgement

Our codebase is built upon the following open-source repositories:

  1. https://github.com/showlab/UniVTG
  2. https://github.com/SamsungLabs/Drop-DTW
  3. https://github.com/jayleicn/moment_detr

Contact

Please feel free to open an issue or email us at yogesh.mcs17.du@gmail.com / ndc.uday@gmail.com

About

Official Implementation of Moment Alignment Transformer

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 3

  •  
  •  
  •