LITA: Language Instructed Temporal-Localization Assistant
Open paper
Benchmark
Model
Rank
Results
video-based-generative-performance-benchmarking-on-videoinstruct
LITA-13B
#12
mean: 3.04
Correctness of Information: 2.94
Detail Orientation: 2.98
…
video-question-answering-on-ovbench
LITA (7B)
#14
AVG: 20.4
Rank counts only results with a code link.