showlab/videollm-online
VideoLLM-online: Online Video Large Language Model for Streaming Video (CVPR 2024)
PythonApache-2.0
Issues
- 8
About reproducing Table 2
#49 opened by SeongRyong0726 - 1
Assertion error with app demo
#43 opened by KW-NJU - 14
Cannot reproduce COIN dataset result
#26 opened by bluehawk2k - 0
Why data incompatible with tuples format?
#50 opened by FlyerW - 4
where to find video dataset ?
#48 opened by dyyoungg - 0
- 0
- 0
problem about URL
#46 opened by Hotpottttt - 0
- 1
- 0
Model trained on training+validation set
#30 opened by yankee624 - 0
reproduce the training process
#42 opened by QimingLee - 0
Cannot reproduce COIN result
#41 opened by nguyentthong - 0
How to Achieve Real-Time Continuous Narration as Shown in Figure 2 of the Paper?
#40 opened by hongming21 - 0
Question about finetuning VideoLLM
#39 opened by steveice - 0
Edge device support?
#38 opened by dianyo - 2
no adapter_model.bin weight on hf
#36 opened by nanamma - 0
COIN narration performance
#37 opened by zhangyl4 - 1
coin conversation data
#34 opened by kffeng - 1
- 3
About Evaluate.py
#35 opened by jun0wanan - 3
- 9
Coin Stream Set
#18 opened by shachoi - 6
Strange output for demo/assets/cooking.mp4
#21 opened by Kiki2049 - 4
- 1
Problem with video-streaming
#29 opened by AmberJar - 24
Dataset Downloading and Usage
#10 opened by YiwuZhong - 0
Problem with demo
#27 opened by HARISKHAN-1729 - 12
Error with the demo
#15 opened by wenyuqing - 2
- 10
Installation Issue
#24 opened by chaichana-t - 8
Cost of the GPU memory
#22 opened by memoiry - 9
Training for Ego4D Narration Stream
#20 opened by XiangTodayEatsWhat - 2
error in demo/cli.py
#17 opened by alpacaduby - 2
About ego4d dataset version
#23 opened by Jiashu-Yu - 8
- 11
Evaluation on COIN
#2 opened by pha-nguyen - 14
Demo error about torchvision
#16 opened by jun0wanan - 7
How large is the dataset?
#14 opened by wenyuqing - 2
Assertion on _call_for_response
#12 opened by eternalding - 1
How many GPUs do you use for training?
#13 opened by shachoi - 3
Meaning of Llama-3 Upgraded Version
#11 opened by Lvvv11 - 5
Does this model generalize to other scenarios?
#7 opened by yjhdhr - 4
Streaming EOS Prediction
#9 opened by zeyun-zhong - 3
Load in 4 bit?
#4 opened by johnwick123f - 2
Demo on HuggingFace is down
#5 opened by hbx233 - 3
What is the cost of reproducing the results?
#8 opened by yjhdhr - 1
- 3
RUN "Please describe what I am doing." error
#3 opened by Rane2021 - 2