Loading
0 Follower
0 Following
lljjol
Li

Location

US

Badges

2
0
0

Activity

Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
Dec
Mon
Wed
Fri

Ratings Progression

Loading...

Challenge Categories

Loading...

Challenges Entered

Automating Building Data Classification

Latest submissions

See All
graded 277784
graded 277087

Generate Synchronised & Contextually Accurate Videos

Latest submissions

See All
graded 275859
graded 275850
graded 275769

Improve RAG with Real-World Benchmarks

Latest submissions

See All
graded 267149
graded 267148
graded 267128

Generate Videos with Temporal and Semantic Audio Sync

Latest submissions

See All
graded 275638
failed 275637
failed 275636

Create Videos with Spatially Aligned Stereo Audio

Latest submissions

See All
graded 275859
graded 275850
graded 275769
Participant Rating
Participant Rating
  • Future Meta Comprehensive RAG Benchmark: KDD Cup 2024
    View

Temporal Alignment Track

About the Temporal Alignment Track category

About 1 month ago

According the documentation:

β€œβ€"
To adapt this dataset for text-conditional sounding video generation, captions for all video clips were automatically generated using LLaVA-Next. These captions are provided along with the video clips.
β€œβ€"

But I could not find the captions in the dataset provided.

lljjol has not provided any information yet.