-
Hey,
When calling `_encode_image` from CoCa, it should return two tensors, the image-level features (cls token/global avg) and the individual token features, so `(image_size / 14) ** 2`, right? Howev…
-
Hello, I want to reproduce the results on RefCOCO, RefCOCO+ and RefCOCOg, but I found that VLMEvalKit doesn't support these datasets, and lmms-eval only support REG(Grounded Captioning) evaluation on …
-
## 🚀 Feature
I was wondering if pretrained models on the Visual Genome dataset will be released? Right now, all the models in the MODEL_ZOO are trained and evaluated on MS-COCO.
## Motivation &…
-
This function call is already in gdeltPyR; but I need to isolate it.
I also have a hard coded table; likely just download this and make it reachable via a method:
* https://github.com/linwood…
-
Hi! I am exploring sentence transformers for a visual scene detection application, to correct automated close captioning according to what is found in the analyzed video frame. For example, if the vid…
-
@ZwormZ
Hi,
This is an update of our new experiment regarding the data leakage of the PubChem324k dataset. I chose to inform you in a new GitHub issue because I do not have your Email address.
…
-
Filed on behalf of John Paton RNIB (original email to RQTF list https://lists.w3.org/Archives/Public/public-rqtf/2020Nov/0016.html)
* AD is normally used by people with vision loss so it may be…
-
## Instructions
1. Click or press the gear icon next to the "Labels" heading on the right. Search for your team in the labels list. If your team is not listed in the Labels menu, please leave a com…
-
I'm a first-time contributor and wanted to get everybody's suggestions regarding the sort of examples they'd like to see. I'm thinking something in the NLP domain, but I'm open to all sorts of ideas
-
```
Loading subtitle (in SRT file) in a movie works great!
But then what is the problem?
I can't change the font size(loaded from a SRT file) even when editing the
*\streambaby-svn-r239\stylesheets …