Comments (8)
We directly use the video-level label as the supervision signals for each snippet. To be specific, you can refer to https://github.com/yjxiong/temporal-segment-networks/blob/master/data/ucf101_splits/trainlist01.txt to understand the input format. In fact, we make no modification to the implementation of TSN and C3D at the first step. Therefore, we just briefly introduce the first step, and the detailed implementation is exactly the same as their original implementations.
from gcn-anomaly-detection.
- All labels are taken into consideration, which may introduce predictive noises. How to clean the noises is one of the key contributions of this paper.
- We have elaborated the experiment section of our paper.
from gcn-anomaly-detection.
You understand correctly.
As for the details:
- Not exactly the same as the original TSN, and we mainly utilize hyper-parameters from its TPAMI-2018 version, https://arxiv.org/abs/1705.02953. In my mind, it should be 7 or 9.
- Not the same, the input unit of TSN is 5?10? frames and that of C3D is 16 frames. For short videos (eg. UCSD-Peds with only about100 frames), it matters more, and using the same number is not a good choice.
- We simply duplicate the snippet-level ground truth into frame-level scores, as the authors of UCF-Crime do https://github.com/WaqasSultani/AnomalyDetectionCVPR2018/blob/master/Evaluate_Anomaly_Detector.m.
from gcn-anomaly-detection.
@jx-zhong-for-academic-purpose .Hi,I have two questiones.
- When step =1, input snippet and its corresponding video-level label ,in other words,input the normal snippets(in normal video) and the corresponding label=0, and the snippets of abnormal video and the corresponding label=1. However, for the snippets of the abnormal video, the video level label 1 is not be used(only used the normal snippets of normal video and its corresponding label 0),because this will affect the parameter update of the classifier.I don't know if I understand it right.Looking forward to your reply.
- Is this pre-trained classifier a feature extraction module or an anomaly detection module, and what data is used for pre-training?
Looking forward to your reply.
Thanks
Best wishes
from gcn-anomaly-detection.
Thanks for your patience very much.I'm very glad to receive your reply in time!
- That is, when t=1, the snippets and the corresponding video-level labels are input into the classifier, and a rough probability estimate is obtained. When t>=2, the video-level label given in the first step is no longer used. ,Is that so?
- Sorry, I ignored this detail. I thought that after pre-training the feature extraction module, that the classifier was also pre-trained with UCF-crime dataset and video-level label. Now I feel that there is no need for pre-training the UCF-crime before t=1.
Looking forward to your reply.
Thanks
Best wishes
from gcn-anomaly-detection.
Good Luck~
from gcn-anomaly-detection.
- Yes, as shown in Fig1.
- The pre-training can boost the performance as many researchers point out.
from gcn-anomaly-detection.
Thank you for your patience. It solved my confusion, thank you very much.
Best wishes
from gcn-anomaly-detection.
Related Issues (20)
- About run extract_c3d_all.py HOT 12
- About code releasing HOT 1
- Can you give a detailed usage of your code? HOT 2
- Installation guide HOT 1
- AboutUCFCrimeTest function
- About UCFCrimeTest class HOT 3
- About the class UCFCirme
- About the optimization mechanism of classifier and graph convolution
- About the number of video segment
- About the training codes of classifier HOT 1
- Missing the Testing Codes?
- Could you please provide fpr and ptr of your ROC curve? HOT 1
- How to get per-frame test result?
- Problem in reproducing the experiments
- ROC-curve for ShanghaiTech dataset
- Where is the feature similarity module?
- Trained model out from Baidu
- about detail train
- UCSD Ped2 HOT 1
- 您好,请问能提供划分好的数据集吗?(已解决,我是sb)
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 gcn-anomaly-detection.