vividle / a2net Goto Github PK
View Code? Open in Web Editor NEWRevisiting Anchor Mechanisms for Temporal Action Localization (TIP 2020)
Revisiting Anchor Mechanisms for Temporal Action Localization (TIP 2020)
Hello, thank you very much for sharing. I have some questions about I3D feature extraction.
I extract features through the links provided by you. I feel that the dimension of output features is not well understood. Assuming that the scale of the input I3D is [4,3,256,224,224] and the dimension of the final output is [4,1024,31,1,1], in the code you provide, the feature extracted by I3D should get a value in each frame. if its need to upsample?
Hi, thanks for your excellent and inspiring work.
The anchor-based part got a promising result on on thumos14 dataset. However, when I tried it on anet dataset, only got a average map of about 13, which is much lower than the result reported on paper.
So I wonder if you adpoted the same network architecture in anet as in thumos14, looking forward to your reply, thanks.
I'm having a bit of a problem reproducing my dataset with your code. Multiple GT messages are required under lib/dataset/prepare_data/construct_feature_thumos.py. I didn't find the corresponding place in your code to modify which prevented me from proceeding.
Hi, I read your paper A2Net and it is really amazing work on action localization.
However, when I downloaded the feature on ActivityNet and tried to run it, it has the error that:
'begin_frame' is not a file in the archive.
and I manually looked into the feature file, it seems that for ActivityNet, the file does not have the 'begin_frame' key.
Can you explain that part?
Also, I want to know that the material you provides including 'cuhk_simple_share.json'. It is the classification result for ActivityNet. I want to know where does it come from? Is it come from the anet-cuhk 2016 or anet-cuhk 2017?
Thanks!
@VividLe Hi,thanks for your sharing, I have download the ActivityNett1.3 feature.And how do you get 'cls_label', 'reg_label'? Could you share me the preprocess script? Thank you very much!!
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.