OpenGVLab/video-mamba-suite

Issues

• How to extract Features and Annotations from new dataset?

  #16 opened 3 months ago by WAYSC
  6

• Question about temporal action localization

  #19 opened 2 months ago by junwei0812
  0

• how to load pretrained model for action recognition task?

  #18 opened 2 months ago by CrazyGeG
  0

• can't find 'vim_t_midclstok_76p1acc.pth' in action recognition task

  #17 opened 3 months ago by cheng1397
  1

• About causal_conv1d_cuda library

  #15 opened 3 months ago by Xingguang-Li
  2

• Features on Thumos

  #14 opened 3 months ago by mohamedali05
  1

• Discrepancy in Video Temporal Grounding Task Results on QVHighlights Dataset

  #13 opened 4 months ago by Summer-seu
  4

• How do you create fineaction feature files?

  #12 opened 4 months ago by Kivenzhougit
  1

• "python setup.py develop" has installation error

  #5 opened 6 months ago by PeterJoe15
  9

• Scripts not found for the action recognition task

  #10 opened 4 months ago by Yifanfanfanfan
  9

• timm not included in requirements

  #11 opened 4 months ago by lennarteingunia
  0

• video temporal grounding inference issue

  #9 opened 4 months ago by PeterJoe15
  3

• ModuleNotFoundError: No module named 'mamba_ssm.modules.mamba_new

  #7 opened 5 months ago by wegigabyteinsn
  5

• Mamba compilation error

  #8 opened 5 months ago by drahciRRR
  1

• VQA code

  #6 opened 6 months ago by EricLina
  1

• Mamba for temporal action localization

  #1 opened 6 months ago by PeterJoe15
  5

• Can not import Mamba properly

  #2 opened 6 months ago by PeterJoe15
  1

• Video deepfake detection is a new use case to test for Mamba

  #4 opened 6 months ago by pchankh
  1