HACS Temporal Action Localization Challenge 2019

We will host HACS Temporal Action Localization Challenge at ICCV'19 Workshop on Multi-modal Video Analysis. The goal of this challenge is to detect actions in untrimmed videos. The action localization challenge uses HACS Segments dataset, which contains:

  • 200 classes, 140K action segments
  • 37.6K/6K training/validation videos, 6K testing videos
  • * Sparse annotations in HACS Clips dataset are NOT permitted. *

Data Download

Please follow instructions in THIS PAGE to download HACS Segments dataset.

Evaluation Metric

We use mAP as our evaluation metric, which is the same as ActivityNet localization metric.

Interpolated Average Precision (AP) is used as the metric for evaluating the results on each activity category. Then, the AP is averaged over all the activity categories (mAP). To determine if a detection is a true positive, we inspect the temporal intersection over union (tIoU) with a ground truth segment, and check whether or not it is greater or equal to a given threshold (e.g. tIoU > 0.5). The official metric used in this task is the average mAP, which is defined as the mean of all mAP values computed with tIoU thresholds between 0.5 and 0.95 (inclusive) with a step size of 0.05.

Submission Format

You should submit a JSON file in the following format, where each video ID has a list of predicted action segments. Submission portal will be available on August 1st.

  "results": {
    "--0edUL8zmA": [
        "label": "Dodgeball",
        "score": 0.84,
        "segment": [5.40, 11.60]
        "label": "Dodgeball",
        "score": 0.71,
        "segment": [12.60, 88.16]

Important Dates

  • July 5, 2019: Training data made available.
  • August 1, 2019: Testing videos are released and submission site opened.
  • October 12, 2019: Submission deadline.
  • October 19, 2019: Challenge results announced.
  • October 27, 2019: Winner(s) are invited to present at the workshop.

Please contact HangZhao AT csail.mit.edu for further questions.