search

fpv-iplab / rulstm

Code for the Paper: Antonino Furnari and Giovanni Maria Farinella. What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention. International Conference on Computer Vision, 2019.
http://iplab.dmi.unict.it/rulstm
133 stars 33 forks source link

Hello, may I ask how to make the format of the action prediction dataset? Is it the same as the format of the action recognition? Can you provide reference materials for making the format of the dataset in this paper? #28

Closed 1848739617 closed 1 year ago

antoninofurnari commented 1 year ago

Hello, please check this section of the README for more information on the dataset format: https://github.com/fpv-iplab/rulstm#dataset-trainingvalidaiton-splits-and-features

1848739617 commented 1 year ago

您好，请查看自述文件的此部分以获取有关数据集格式的更多信息：https://github.com/fpv-iplab/rulstm#dataset-trainingvalidaiton-splits-and-features Thank you very much for your reply. Is there a detailed tutorial on making a motion prediction dataset?

1848739617 commented 1 year ago

Hello, please check this section of the README for more information on the dataset format: https://github.com/fpv-iplab/rulstm#dataset-trainingvalidaiton-splits-and-features

I'm making my own action prediction dataset, but I don't know how to do it in a specific format. I can only make it into a data set format for action recognition。

antoninofurnari commented 1 year ago

您好，请查看自述文件的此部分以获取有关数据集格式的更多信息：https://github.com/fpv-iplab/rulstm#dataset-trainingvalidaiton-splits-and-features Thank you very much for your reply. Is there a detailed tutorial on making a motion prediction dataset?

This code is related to the paper "Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video" (see https://arxiv.org/pdf/2005.02190.pdf), which considers the problem of action anticipation.

The codebase is not directly exploitable for motion prediction (it could be maybe extended, but this is out of the scope of this repository at the moment).

Hello, please check this section of the README for more information on the dataset format: https://github.com/fpv-iplab/rulstm#dataset-trainingvalidaiton-splits-and-features

I'm making my own action prediction dataset, but I don't know how to do it in a specific format. I can only make it into a data set format for action recognition。

In our setting, we use the same format for action recognition and prediction. You can check our paper for more details: https://arxiv.org/pdf/2005.02190.pdf

1848739617 commented 1 year ago

thank you for your reply.