-
### Model description
Hey,
as discussed with @NielsRogge a few weeks back, I'd like to work on adding the "VATT: Transformers for Multimodal
Self-Supervised Learning from Raw Video, Audio and Text"…
johko updated
9 months ago
-
Hi,
Thanks for your great work.
I am interested in the embedding arithmetic and image retrieval, as the example shown in Figure 4 of the paper.
In the paper, the embedding arithmetic is described…
-
Here is the development roadmap for 2024 Q4. Contributions and feedback are welcome ([**Join Bi-weekly Development Meeting**](https://t.co/4BFjCLnVHq)). Previous 2024 Q3 roadmap can be found in #634.
…
-
[[WYZE Cam v3 with Color Night Vision, Wired 1080p HD Indoor/Outdoor Video Camera, 2-Way Audio, Works with Alexa, Google Assistant, and IFTTT]](https://www.amazon.com/Vision-Indoor-Outdoor-Camera-Assi…
-
As you can see above, I use the original assets(text, image, audio) in main branch, and fi…
-
Hi! I'm trying to use QSVEnc 7.70 with an Arc A380 to transcode my 4K HEVC HDR10Plus files to 4K AV1 HDR10Plus. I've extracted the HDR10Plus metadata to a file using [hdr10plus_tool](https://github.co…
-
There are a number of possibly accessibility concerns for this project. The ones that came to mind include:
Captioning for videos, and any other audio-only things should be transcribed.
For blind …
-
### 🚀 The feature, motivation and pitch
Discussed in context of scriptable base64 decoding here: https://github.com/pytorch/vision/issues/6878#issuecomment-1343439120, http://www.alfredklomp.com/pr…
-
### 🥰 需求描述 | Feature Description
Have an option for the agent to automatically convert every interaction to TTS.
### 🧐 解决方案 | Proposed Solution
On the Agent Panel Creation, have a switch button tha…
-
### Description
@andrewheard
1. As we upgraded to 1.5 Flash (https://github.com/firebase/firebase-ios-sdk/pull/12979), is it possible to achieve like [Project Astra](https://youtu.be/nXVvvRhiGjI) no…