LLaVA-NeXT
LLaVA-NeXT copied to clipboard
M4 Instruct Dataset Corresponding ZIP Files
Hi, Thanks for the effort and amazing work!
I want to download some parts of the M4 Instruct dataset, hosted here.
The following .zip files are available,
AESOP.zip
ALFRED.zip
Birds-to-Words.zip
CLEVR-Change.zip
COMICS_Dialogue.zip
DocVQA.zip
FlintstonesSV.zip
HQ-Edit.zip
IEdit.zip
MIT-States_PropertyCoherence.zip
MIT-States_StateCoherence.zip
MagicBrush.zip
OCR-VQA.zip
PororoSV.zip
RAVEN_train_images.zip
RecipeQA_ImageCoherence.zip
RecipeQA_VisualCloze.zip
Spot-the-Diff.zip
TQA.zip
VISION.zip
VIST.zip
VizWiz.zip
WebQA.zip
coinstruct.zip
contrastive_caption.zip
Rename dreamsim_part0.zip
dreamsim_split.zip
Rename dreamsim_part1.zip to dreamsim_split.zip
iconqa.zip
imagecode.zip
mmchat.zip
multi_vqa.zip
nextqa.zip
nlvr2.zip
nuscenes.zip
scannet_frames_25k.zip
star.zip
However, I am NOT able to find the data for the following 3 sets (as mentioned in Fig. 4 of the paper) can you please help me identify the files for these sets?
- Video Detailed Descriptions
ShareGPTVideo-Caption
- 3D Grounding
- Scene VQA
ScanQA3D-LLM-Scene
- Scene VQA
Please help me find these 3 files data,
Thank you.
@Luodian @ZhangYuanhan-AI @FengLi-ust