# AVA Challenge@ICME 2023 — Data

来源：https://www.kaggle.com/competitions/ava-challenge/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

Your challenge in this competition is to forecast the car accident. In this dataset, we provide the videos of roads and freeways to let you train the model.

Please use training dataset to create your own model, and make classification on testing dataset. The name of each film is generated randomly. For your convenience, we named the road data after 20001 to 20157, while freeway is 30001 to 30155. Each film has a jpg folder and a xml folder to show annotations.

Remember to fill out the request form that we will send you the data link. 

Request Form: https://docs.google.com/forms/d/1f30zkr9iVMoYbLq9sFD8t5LCmMdd_7NT7Hgkr8pJJLE/edit

## Files

*   **TRAIN DATASET** - the training set
         |-------  **freeway train** - the training set of freeway
         |            |-------  **jpgs** - the videos
         |            |-------  **xmls** - the annotations
         |-------  **road train** - the training set of road
         |            |-------  **jpgs** - the videos
         |            |-------  **xmls** - the annotations
         |-------  **freeway train.csv** - labels of videos in the freeway folder
         |-------  **road train.csv** - labels of videos in the road folder
*   **TEST DATASET** - the testing set
         |-------  **freeway test** - the testing set of freeway
         |            |-------  **jpgs** - the videos
         |            |-------  **xmls** - the annotations
         |-------  **road test** - the testing set of road
         |            |-------  **jpgs** - the videos
         |            |-------  **xmls** - the annotations
*   **sample submission.csv** - the example of submission format

## Columns

*   `film name` - name of video (randomly generated)
*   `car accident` - the anwsers, show there will be a car accident or not. 1 indicates yes, while 0 indicates no.