Deep Learning

How are Transformers improving video analysis in deep learning compared to traditional 3D CNNs?

HE Asked by Heather Reynolds · 14-02-2024
0 upvotes 11,302 views 0 comments
The question

I am working on a project involving action recognition and video classification. I have traditionally used 3D Convolutional Neural Networks, but I am hearing that Video Vision Transformers are the new standard in 2024. How do these models handle the temporal dimension differently, and is the computational cost justified for real-time edge applications? 

3 answers

0
BR
Answered on 12-04-2024

In 2024, Video Vision Transformers have indeed begun to outperform 3D CNNs by treating video as a sequence of patches across both space and time. Unlike CNNs, which use fixed kernels that might miss long-range temporal dependencies, the self-attention mechanism in Transformers allows the model to attend to any frame in a sequence simultaneously. This results in a much deeper understanding of complex actions. For edge applications, however, they can be quite heavy. We are currently seeing a shift toward "Tubelet Embedding" to reduce the number of tokens, which makes these deep learning models significantly faster without losing accuracy. 

0
PA
Answered on 05-05-2024

Have you looked into the specific latency differences when running these Transformer models on NVIDIA Jetson or similar edge hardware? 

GR 10-05-2024

Patrick, that is a great question. On hardware like the Jetson Orin, we see that 3D CNNs still have a slight edge in raw frames-per-second because of their optimized CUDA kernels. However, by using TensorRT for model quantization to INT8, we’ve managed to get Video Transformers running at near real-time. The trade-off is that the Transformer provides much better accuracy for "fine-grained" actions that 3D CNNs often confuse. For deep learning developers, it really comes down to whether your use case prioritizes absolute speed or the precision of action detection.

0
MA
Answered on 20-05-2024

Transformers are definitely the future for video. Their ability to globalize context across frames is something CNNs just can't do natively without massive depth. 

HE 22-05-2024

Martha is right. The global receptive field is the biggest selling point. Even if they are slower to train, the results in 2024 for complex video understanding are undeniable.

Share your thoughts

Your email address will not be published. Required fields are marked (*)

Professional Counselling Session

Still have questions?
Schedule a free counselling session

Our experts are ready to help you with any questions about courses, admissions, or career paths. Get personalized guidance from industry professionals.

Request a Call Back

Search Online

We Accept

We Accept

Follow Us

"PMI®", "PMBOK®", "PMP®", "CAPM®" and "PMI-ACP®" are registered marks of the Project Management Institute, Inc. | "CSM", "CST" are Registered Trade Marks of The Scrum Alliance, USA. | COBIT® is a trademark of ISACA® registered in the United States and other countries.

World globe icon Country: Canada

Book Free Session