arxiv:2306.12886
Gullal Singh Cheema
gullalc
AI & ML interests
Multimodality, Vision and Language, Cross-modal relations, Video Understanding
Recent Activity
upvoted
an
article
6 days ago
nanoVLM: The simplest repository to train your VLM in pure PyTorch
upvoted
an
article
6 days ago
Efficient MultiModal Data Pipeline
upvoted
a
paper
6 days ago
FineVision: Open Data Is All You Need
Organizations
None yet
models
7
gullalc/videomae-base-finetuned-kinetics-movieshots-multitask
Video Classification
•
86.2M
•
Updated
•
100
•
3
gullalc/convnextv2-base-22k-224-cinescale-level
Image Classification
•
87.7M
•
Updated
gullalc/convnextv2-base-22k-384-cinescale-level
Image Classification
•
87.7M
•
Updated
•
1
gullalc/convnextv2-base-22k-224-cinescale-angle
Image Classification
•
87.7M
•
Updated
gullalc/convnextv2-base-22k-384-cinescale-angle
Image Classification
•
87.7M
•
Updated
•
48
gullalc/videomae-base-finetuned-kinetics-movieshots-movement
Video Classification
•
86.2M
•
Updated
•
89
•
2
gullalc/videomae-base-finetuned-kinetics-movieshots-scale
Video Classification
•
86.2M
•
Updated
datasets
0
None public yet