Comments (5)
sparkstj
commented on June 23, 2024
Hi, these are the actionness, starting, and ending probabilities in the corresponding frame.
from rtd-action.
DoublePan-Oh
commented on June 23, 2024
I have some questions about feature extraction.
in the paper, the frame stride is set to 8 for I3D , which means you divided each video into non-overlapping snippets
with consecutive 8 frames, and 8 frames is a chuck? For example, if a video has N frames, after the I3D model, the final feature dimension is (N//8, C) ?
Looking forward to your reply!
…------------------ 原始邮件 ------------------
发件人: "MCG-NJU/RTD-Action" ***@***.***>;
发送时间: 2022年3月2日(星期三) 下午2:41
***@***.***>;
***@***.******@***.***>;
主题: Re: [MCG-NJU/RTD-Action] TEM_scores (Issue #17)
Hi, these are the actionness, starting, and ending probabilities in the corresponding frame.
—
Reply to this email directly, view it on GitHub, or unsubscribe.
Triage notifications on the go with GitHub Mobile for iOS or Android.
You are receiving this because you authored the thread.Message ID: ***@***.***>
from rtd-action.
sparkstj
commented on June 23, 2024
Yes, but the final feature dimension is co-determined by the final avg3dpooling layer in I3D. The pooling kernel we used is (8,7,7) and the stride is (1,1,1), therefore the feature dimension should be (N//8-7, C).
from rtd-action.
Rishitha1234
commented on June 23, 2024
How to implement this code??
Can you explain me in detail (step by step)??
from rtd-action.
sparkstj
commented on June 23, 2024
You can check this repo for detailed code. It is the exact code we use to generate thumos features, with a mild modification on the avgpooling layer after Mixed_5c (kernel from (2,7,7) to (8,7,7)) .
from rtd-action.
Related Issues (20)
- mAP evaluation HOT 3
- RTD code for ActivityNet-1.3 HOT 4
- from datasets import build_dataset ;from models import build_model HOT 1
- I have a problem HOT 1
- A question about reproducibility~
- a question for training HOT 1
- labe issue HOT 4
- about activitynet feature HOT 4
- about anet code HOT 4
- a problem HOT 2
- about thumos14 annotation HOT 3
- Results HOT 3
- Hello, may I ask, in the paper, the training is carried out in two stages, but in the code at that time, the training is carried out in three stages, why? How do they correspond to each other HOT 2
- ActivityNet HOT 8
- ANet HOT 10
- about TEM HOT 1
- about RTD in Anet HOT 1
- temporal action detection HOT 1
- how to change the stride of THUMOS features
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from rtd-action.