Pei Liu
Pei Liu
Hi, as discussed in paper, the larger input resolution results in better performnace. But I can not find a link to download the pre-trained model (image or pose-estimation, the latter...
I am planning to download videochat2 related video dataset, there are some confusing points. As mentioned in [DATA.md,](https://github.com/OpenGVLab/Ask-Anything/blob/main/video_chat2/DATA.md) the videochat1, videochat2, videochatgpt are based [Intervideo](https://huggingface.co/datasets/OpenGVLab/InternVid). The train.json form videochat1/videochat2/videochatgpt, video...
as mention on [here](https://github.com/Luodian/Otter/blob/main/docs/mimicit_format.md), failed to load the LA_RLHF.parquet (about 22GB) file, which is downloaded from shared Onedrive. Error msg: pyarrow.lib.ArrowCapacityError: array cannot contain more than 2147483646 bytes, have 2368257792....
when the code could be released?
Before downloading the dataset, an experiment was conducted using 200 videos. While these 200 videos could be downloaded (I got 193 videos finally) correctly without the argument "--clip_col="timestamp". But an...
I wonder what the "32K" signifies when using the "lmms-lab/LLaVA-NeXT-Video-7B-32K" checkpoint.
As mentioned in the paper (see Fig. 3 on page 3), the question-answer pairs were generated by a Large Language Model (LLM). What prompts were used by the LLM to...
as mentioned as title, Is there a plan to release the TQA dataset used to train CogVLM2-Video?
as mentioned as title, the json file downloaded from huggingFace, occurs loading error. File "", line 1, in File "/Users/peiliu/Library/Python/3.9/lib/python/site-packages/mmengine/fileio/io.py", line 853, in load obj = handler.load_from_fileobj(f, **kwargs) File "/Users/peiliu/Library/Python/3.9/lib/python/site-packages/mmengine/fileio/handlers/json_handler.py",...