2D-TAN

we are hiring talented interns: [email protected]

In this paper, we study the problem of moment localization with natural language, and propose a novel 2D Temporal Adjacent Networks(2D-TAN) method. The core idea is to retrieve a moment on a two-dimensional temporal map, which considers adjacent moment candidates as the temporal context. 2D-TAN is capable of encoding adjacent temporal relation, while learning discriminative feature for matching video moments with referring expressions. Our model is simple in design and achieves competitive performance in comparison with the state-of-the-art methods on three benchmark datasets.

Arxiv Preprint

For journal reviewers: please download and unzip

journal.zip

News

• :wrench: A third-party optimized implementation by @ChenJoya.
• :sunny: Our paper was accepted by AAAI-2020. Arxiv Preprint
• :trophy: We extend our 2D-TAN approach to the temporal action localization task and win the 1st place in HACS Temporal Action Localization Challenge at ICCV 2019. For more details please refer to our technical report.

Framework

Main Results

Main results on Charades-STA

| Method | [email protected] | [email protected] | [email protected] | [email protected] | | ---- |:-------------:| :-----:|:-----:|:-----:| | Pool | 40.94 | 22.85 | 83.84 | 50.35 | | Conv | 42.80 | 23.25 | 80.54 | 54.14 |

I fixed a bug for loading charades visual features, the updated performance is listed above. Please use these results when comparing with our AAAI paper.

Main results on ActivityNet Captions

| Method | [email protected] | [email protected] | [email protected] | [email protected] | [email protected] | [email protected] | | ---- |:-------------:| :-----:|:-----:|:-----:|:-----:|:-----:| | Pool | 59.45 | 44.51 | 26.54 | 85.53 | 77.13 | 61.96 | | Conv | 58.75 | 44.05 | 27.38 | 85.65 | 76.65 | 62.26 |

Main results on TACoS

| Method | [email protected] | [email protected] | [email protected] | [email protected] | [email protected] | [email protected] | | ---- |:-------------:| :-----:|:-----:|:-----:|:-----:|:-----:| | Pool | 47.59 | 37.29 | 25.32 | 70.31 | 57.81 | 45.04 | | Conv | 46.39 | 35.17 | 25.17 | 74.46 | 56.99 | 44.24 |

Prerequisites

• pytorch 1.1.0
• python 3.7
• torchtext
• easydict
• terminaltables

Quick Start

Please download the visual features from google drive and save it to the

data/

Training

Use the following commands for training: ```

Evaluate "Pool" in Table 1

python moment_localization/train.py --cfg experiments/charades/2D-TAN-16x16-K5L8-pool.yaml --verbose

Evaluate "Conv" in Table 1

python moment_localization/train.py --cfg experiments/charades/2D-TAN-16x16-K5L8-conv.yaml --verbose

Evaluate "Pool" in Table 2

python moment_localization/train.py --cfg experiments/activitynet/2D-TAN-64x64-K9L4-pool.yaml --verbose

Evaluate "Conv" in Table 2

python moment_localization/train.py --cfg experiments/activitynet/2D-TAN-64x64-K9L4-conv.yaml --verbose

Evaluate "Pool" in Table 3

python moment_localization/train.py --cfg experiments/tacos/2D-TAN-128x128-K5L8-pool.yaml --verbose

Evaluate "Conv" in Table 3

python moment_localization/train.py --cfg experiments/tacos/2D-TAN-128x128-K5L8-conv.yaml --verbose ```

Testing

Our trained model are provided in google drive. Please download them to the

checkpoints

Then, run the following commands for evaluation: ```

Evaluate "Pool" in Table 1

python moment_localization/test.py --cfg experiments/charades/2D-TAN-16x16-K5L8-pool.yaml --verbose --split test

Evaluate "Conv" in Table 1

python moment_localization/test.py --cfg experiments/charades/2D-TAN-16x16-K5L8-conv.yaml --verbose --split test

Evaluate "Pool" in Table 2

python moment_localization/test.py --cfg experiments/activitynet/2D-TAN-64x64-K9L4-pool.yaml --verbose --split test

Evaluate "Conv" in Table 2

python moment_localization/test.py --cfg experiments/activitynet/2D-TAN-64x64-K9L4-conv.yaml --verbose --split test

Evaluate "Pool" in Table 3

python moment_localization/test.py --cfg experiments/tacos/2D-TAN-128x128-K5L8-pool.yaml --verbose --split test

Evaluate "Conv" in Table 3

python moment_localization/test.py --cfg experiments/tacos/2D-TAN-128x128-K5L8-conv.yaml --verbose --split test ```

Citation

If any part of our paper and code is helpful to your work, please generously cite with:

@InProceedings{2DTAN_2020_AAAI,
author = {Zhang, Songyang and Peng, Houwen and Fu, Jianlong and Luo, Jiebo},
title = {Learning 2D Temporal Adjacent Networks forMoment Localization with Natural Language},
booktitle = {AAAI},
year = {2020}
}