This model was trained using 16 frames per video, at a resolution of 224x224.
Disclaimer: The team releasing X-CLIP did not write a model card for this model so this model card has been written by the Hugging Face team.
Model description
X-CLIP is a minimal extension of
CLIP
for general video-language understanding. The model is trained in a contrastive way on (video, text) pairs.
This allows the model to be used for tasks like zero-shot, few-shot or fully supervised video classification and video-text retrieval.
Intended uses & limitations
You can use the raw model for determining how well text goes with a given video. See the
model hub
to look for
fine-tuned versions on a task that interests you.
The exact details of preprocessing during training can be found
here
.
The exact details of preprocessing during validation can be found
here
.
During validation, one resizes the shorter edge of each frame, after which center cropping is performed to a fixed-size resolution (like 224x224). Next, frames are normalized across the RGB channels with the ImageNet mean and standard deviation.
Evaluation results
This model achieves a top-1 accuracy of 81.1% and a top-5 accuracy of 95.5%.
Runs of microsoft xclip-base-patch32-16-frames on huggingface.co
7.6K
Total runs
0
24-hour runs
-50
3-day runs
-8.4K
7-day runs
-9.0K
30-day runs
More Information About xclip-base-patch32-16-frames huggingface.co Model
More xclip-base-patch32-16-frames license Visit here:
xclip-base-patch32-16-frames huggingface.co is an AI model on huggingface.co that provides xclip-base-patch32-16-frames's model effect (), which can be used instantly with this microsoft xclip-base-patch32-16-frames model. huggingface.co supports a free trial of the xclip-base-patch32-16-frames model, and also provides paid use of the xclip-base-patch32-16-frames. Support call xclip-base-patch32-16-frames model through api, including Node.js, Python, http.
microsoft xclip-base-patch32-16-frames online free
xclip-base-patch32-16-frames huggingface.co is an online trial and call api platform, which integrates xclip-base-patch32-16-frames's modeling effects, including api services, and provides a free online trial of xclip-base-patch32-16-frames, you can try xclip-base-patch32-16-frames online for free by clicking the link below.
microsoft xclip-base-patch32-16-frames online free url in huggingface.co:
xclip-base-patch32-16-frames is an open source model from GitHub that offers a free installation service, and any user can find xclip-base-patch32-16-frames on GitHub to install. At the same time, huggingface.co provides the effect of xclip-base-patch32-16-frames install, users can directly use xclip-base-patch32-16-frames installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
xclip-base-patch32-16-frames install url in huggingface.co: