-
I evaluated the VQA and scene cls tasks on the model fine-tuned using GeoChatInstruct, and the results are pretty close to the metrics reported in the paper, however, the region captioning result is …
-
the generated results only describe the content and not the answer for the specified prompt.
result:
-
Thank you very much for your work.
But I have a question about RefCOCO|+|g. Is it a region caption task? Why is it divided into seg and bbox?
Looking forward to your answer.
-
Hi Jerome,
We have some text files we are trying to validate and the validation is capturing subtitle lines that do not have text.
```
CAPTIONING MADE POSSIBLE BY
WARNER BROS. ANIM…
-
@mikedo and I were discussing (my alleged) lack of specificity in the standards about whether the IMSC1 document is or is not required/recommended to keep captions within the safe title area or not. …
-
Hi,
Thank you for sharing the code. How can I use the model to evaluate the model on the Visual Genome dataset? One missing file image_b64.tsv for the scripts/tools/eval_suite.sh. How to obtain the f…
-
We started to experiment with EditContext API in CKEditor 5 and encountered an issue. There are so-called "nested editables" inside the editor – smaller editable regions inside the main editable regio…
-
Great work!
I am confused with Tab .6 result, the performance is Alpha-CLIP with LLaVA-1.5 or fine-tune this model with vicuna-7b on these datasets(RefCOCOg or VG)？
-
### What happened?
I have a windows node with a pod running as a host process container, and therefore with hostNetwork:true. I have the pod exposed as a ClusterIP service. I have a separate pod on t…
-
We use the semantic segmentation subset of OpenImage v6[15] as the main dataset for multi-task prompt tuning. In addition, following Smartbrush [32], we use segmentation labels and BLIP captions[16] a…