RenShuhuai-Andy/TimeChat
[CVPR 2024] TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding
PythonBSD-3-Clause
Issues
- 2
Weight for QA benchmarks
#36 opened by NIneeeeeem - 1
Asking for the Fine-tuned Checkpoint
#35 opened by minjoong507 - 1
Could you test TimeChat on the EgoShema dataset?
#34 opened by EricLina - 2
Can this model do qa tasks?
#26 opened by leexinhao - 5
- 2
- 1
- 0
用自己的数据集finetune,如何在train的过程中进行eval?
#32 opened by changqinyao - 3
- 7
Question about fune-tune
#25 opened by zhengxingmao - 2
Inference with audio
#29 opened by lakshya-frontera - 5
Question about prompt
#20 opened by Ironieser - 3
- 0
When conducting SFT experiments, setting batch_size_train to 1 or 2 has the same memory usage.
#27 opened by tiesanguaixia - 5
For different video datasets, is the frame density always drawn at intervals of 1 second?
#2 opened by DuoLong - 5
the performance is very low on my own dataset.
#22 opened by onlyonewater - 1
Subset of YT-Temporal
#24 opened by patrick-tssn - 1
Question about batch size
#23 opened by gyxxyg - 5
Question about the tokenizer
#19 opened by gyxxyg - 3
Experiment-related question
#21 opened by zhaodongliang678 - 2
RAM and VRAM requirement
#13 opened by Coronal-Halo - 2
Question about prompts.
#18 opened by gyxxyg - 2
Inquiry on training cost
#16 opened by HenryHZY - 1
Demo can‘t show the same desult
#15 opened by xiaoxiaoli666 - 1
Bad performance of Charades
#14 opened by soyeonhong - 14
Do we need to crop the HiREST videos?
#10 opened by yeliudev - 2
- 1
Details of sliding qformer operation
#11 opened by jihwanp - 1
- 4
torch.load raise TypeError: 'strict' is an invalid keyword argument for Unpickler()
#9 opened by wwq66 - 1
- 2
- 3
how to evaluation on activitynet-DVC?
#6 opened by TXH-mercury - 4
UnsatisfiableError
#4 opened by LarryLeeee - 1
Checkpoints to run demo and dataset
#3 opened by fazlicodes - 1
A very good video-related work, it is convenient to open source the data set?
#1 opened by Xujianzhong