Home

Awesome

NExT-QA <img src="images/logo.png" height="64" width="128">

We reproduce some SOTA VideoQA methods to provide benchmark results for our NExT-QA dataset accepted to CVPR2021.

NExT-QA is a VideoQA benchmark targeting the explanation of video contents. It challenges QA models to reason about the causal and temporal actions and understand the rich object interactions in daily activities. We set up both multi-choice and open-ended QA tasks on the dataset. <strong>This repo. provides resources for open-ended QA</strong>; multi-choice QA is found in NExT-QA. For more details, please refer to our dataset page.

Todo

  1. Raw Videos are the same with NExT-QA(MC).
  2. <s>Open online evaluation server</s> and release test data.
  3. RoI features are the same with NExT-QA(MC).

Environment

Anaconda 4.8.4, python 3.6.8, pytorch 1.6 and cuda 10.2. For other libs, please refer to the file requirements.txt.

Install

Please create an env for this project using anaconda (should install anaconda first)

>conda create -n videoqa python==3.6.8
>conda activate videoqa
>git clone https://github.com/doc-doc/NExT-OE.git
>pip install -r requirements.txt

Data Preparation

Please download the pre-computed features and QA annotations from here. There are 3 zip files:

After downloading the data, please create a folder ['data/feats'] at the same directory as ['NExT-OE'], then unzip the video features into it. You will have directories like ['data/feats/vid_feat/', and 'NExT-OE/'] in your workspace. Please unzip the files in ['nextqa.zip'] into ['NExT-OE/dataset/nextqa'] and ['models.zip'] into ['NExT-OE/models/'].

Usage

Once the data is ready, you can easily run the code. First, to test the environment and code, we provide the prediction and model of the SOTA approach (i.e., HGA) on NExT-QA. You can get the results reported in the paper by running:

>python eval_oe.py

The command above will load the prediction file under ['results/'] and evaluate it. You can also obtain the prediction by running:

>./main.sh 0 val #Test the model with GPU id 0

The command above will load the model under ['models/'] and generate the prediction file. If you want to train the model, please run

>./main.sh 0 train # Train the model with GPU id 0

It will train the model and save to ['models']. (The results may be slightly different depending on the environments)

Results on Val

MethodsText Rep.WUPS_CWUPS_TWUPS_DWUPS
BlindQAGloVe12.1414.8540.4118.88
STVQA (CVPR17)GloVe12.5214.5745.6420.08
UATT (TIP17)GloVe13.6216.2343.4120.65
HME (CVPR19)GloVe12.8314.7645.1320.18
HCRN (CVPR20)GloVe12.5315.3745.2920.25
HGA (AAAI20)GloVe14.7614.9046.6021.48

Please refer to our paper for results on the test set.

Multi-choice QA vs. Open-ended QA

vis mc_oe

Some Latest Results

MethodsPublicationHighlightVal (WUPS@All)Test (WUPS@All)
Emu(0-shot) by BAAIarXiv'23VL foundation model-23.4
Flamingo(0-shot) by DeepMindNeurIPS'22VL foundation model-26.7
KcGA by BaiduAAAI'23Knowledge base, GPT-2-28.2
Flamingo(32-shot) by DeepMindNeurIPS'22VL foundation model-33.5
PaLI-X by Google ResearcharXiv'23VL foundation model-38.3

Citation

@InProceedings{xiao2021next,
    author    = {Xiao, Junbin and Shang, Xindi and Yao, Angela and Chua, Tat-Seng},
    title     = {NExT-QA: Next Phase of Question-Answering to Explaining Temporal Actions},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2021},
    pages     = {9777-9786}
}

Acknowledgement

Our reproduction of the methods is based on the respective official repositories, we thank the authors to release their code. If you use the related part, please cite the corresponding paper commented in the code.