VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models
Paper
•
2502.02492
•
Published
•
29
Doğuş Can Korkmaz
doguscank
AI & ML interests
Vision, LLMs, vLLMs, semantic segmentation, forecasting
Recent Activity
upvoted
a
paper
about 15 hours ago
VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion
Generation in Video Models
updated
a collection
17 days ago
integration
updated
a collection
17 days ago
integration
Organizations
None yet
doguscank's activity
upvoted
a
paper
about 15 hours ago
updated
a
collection
17 days ago
updated
a
collection
21 days ago
updated
a
collection
23 days ago
updated
a
collection
27 days ago
updated
a
collection
28 days ago
updated
a
collection
29 days ago
updated
a
collection
about 1 month ago
upvoted
a
paper
about 1 month ago
updated
a
collection
about 1 month ago
upvoted
a
paper
about 1 month ago
updated
a
collection
about 1 month ago
upvoted
a
paper
about 1 month ago
updated
a
collection
about 1 month ago
updated
a
collection
about 2 months ago