HMN

HMN copied to clipboard

Download Links

2

Thank you for sharing your work. I downloaded your MSVD data 2 weeks ago, but now I can not download data from your links. I think there problem with your...

adeljalalyousif

Hi! I read in Section3.1 of your paper that > Specifically, we first obtain the “synonymy label” in WordNet2 of each noun in groundtruth captions. And then, we choose nouns...

davidluciolu

embedding_weights.pkl vid2fillmask_MSVD_official.pkl vid2language.pkl 这三个文件都是用Sbert提取得到的吗？分别对应什么特征呢？？

fsh2017

特征提取文件

2

我拜读了您的论文，因为我需要训练自己的数据集，所以很好奇是如何对object feather聚类以及如何对视频切片的，还望您分享一下相关代码，谢谢

Jack2Lu

I want to train my own dataset, and I'm unsure about how many of the text features are generated. Could you provide some specific guidance on this? Thank you very...

fsh2017

Thank you very much for your contribution. I ran it on my computer and used the same configuration in the code for training on MSVD, but the cider metric score...

tjumc

BradenJoson

when I use main.py to train the code, The memory of computer will rise quickly and eventurally out of memory(my computer is 30G memory), please help me and how to...

Ri-Bai

How to build data?

2

The paper provides datasets to readers,while it doesn't tell us how to build data.For example,I want to imitate the format of MSVD to build my own data. I have raw...

Fredham

想问一下FasterRCNN模型提取的特征问题

1

FasterRcnn网络提取的对象特征文件里 是保存的每个视频帧中检测到的对象特征吗？例如MSVD_vg_objects_test文件里，每个视频id对应的特征是FasterRcnn网络检测的目标框中的对象特征吗？ 我想用FasterRcnn网络提取自己视频里的对象特征，但是我不知道这个对象特征是怎么保存的，能麻烦您告诉一下吗？非常感谢您！

syl0107