Hi, love your AOT/AOST. Excellent scalability. The open-source code is another big plu

Question regarding Table 1 about aot HOT 2 CLOSED

z-x-yang commented on July 26, 2024

Question regarding Table 1

from aot.

Comments (2)

z-x-yang commented on July 26, 2024

Hi,

It's good to hear from you. STCN is a very good open-source work for VOS.

THX for pointing out that STM used all the frames! I'll correct this in a revision of AOST. The current version is only a manuscript.

I'll try to contact the authors of HMMN and KMN to know if they used all the frames. If I cannot know the exact answers by the publication of AOST, I'll use a unique symbol to denote "Unknown" in the paper of AOST.

It's unfortunate that most papers don't mention whether they use all the frames, and many of them haven't released their code.

Best.

from aot.

hkchengrex commented on July 26, 2024

Sure. Thanks!

from aot.

Related Issues (16)

About training detial HOT 2
The sampling strategy during training HOT 4
About the number of params of the model HOT 3
Example video of results HOT 2
May I ask the number of params of the LSTT block? HOT 1
Multi-view object segmentation HOT 1
May I ask when you plan to release the code? HOT 1
About the input dimensions of Long-Term Attention HOT 1
Do you realized key_padding_mask in you long-term attention and short-term Attention? HOT 3
Identification Embedding HOT 1
About the X^m_l in Long-Term Attention HOT 1
Do you use dropout in Long-Term Attention and Short-Term Attention? HOT 1
Do you directly add the output feature of the backbone to the input of decoder? HOT 3
About the LSTT block HOT 1
The performance gains from image datasets (COCO, VOC, etc.) HOT 2

Question regarding Table 1 about aot HOT 2 CLOSED

Comments (2)

Related Issues (16)

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent