Comments (6)
@lonngxiang It is not a clear question for me. Can you describe clearer?
I guess your problem is that if there is a lot of videos as retrieval candidates, how to deal with the memory cost. If that is the case, I think the loose type can solve this problem naturally with cached video features. Then the retrieval scores can be calculated via the off-the-shelf feature. Besides, some other hash methods can also be used to speed the retrieval.
from clip4clip.
@lonngxiang It is not a clear question for me. Can you describe clearer?
I guess your problem is that if there is a lot of videos as retrieval candidates, how to deal with the memory cost. If that is the case, I think the loose type can solve this problem naturally with cached video features. Then the retrieval scores can be calculated via the off-the-shelf feature. Besides, some other hash methods can also be used to speed the retrieval.
I meaning: A video is divided into many frames of images. Each query is based on image dimension, so the result will be very complicated. I don't know if I can get the video vector directly, so I can directly recall the whole video content that conforms to Query
from clip4clip.
Yes, we aggregate all frame features via mean pooling, LSTM, Transformer, etc. in our paper. Thus, a video is indeed encoded as a vector. See section 3.3 for more information, please.
from clip4clip.
Yes, we aggregate all frame features via mean pooling, LSTM, Transformer, etc. in our paper. Thus, a video is indeed encoded as a vector. See section 3.3 for more information, please.
OK, thank you for your patient reply
from clip4clip.
Thank you for your attention. Reopen this issue if any other questions.
from clip4clip.
use mean pooling, LSTM, Transformer to generate a video vector;Does this paper end up as a similar recall of text vector dot videos vector?
from clip4clip.
Related Issues (20)
- Use my own videos HOT 1
- Question about the calculation method of loss when there are multiple gpus HOT 1
- Results on MSRVTT and MSVD HOT 3
- running the project HOT 1
- Problem about reproducing the model HOT 1
- Reproduction on LSMDC DataSet HOT 6
- What do Pair, L, T stand for in the code? HOT 3
- How to use this repo to retrieve clips among videos by text?
- train dataset is shuffled regardless of seed
- AttributeError: Caught AttributeError in DataLoader worker process 0.
- Video-to-video retrieval?
- ValueError: Parameter config in `CLIP4Clip(config)` should be an instance of class `PretrainedConfig`. To create a model from a Google pretrained model use `model = CLIP4Clip.from_pretrained(PRETRAINED_MODEL_NAME)`
- Problem about Multi-GPU-Train architecture
- post-pretrain or downstream tasks parameters
- Evaluation Procedure for Reporting Performance
- About 3D Patch Linear
- Large performance drop if trained with fp32. HOT 1
- [PAD_TOKEN] is not used, but just adding 0
- train files HOT 1
- Directly pass the entire config as a argument to a function
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 clip4clip.