VATEX
Multilingual
multimodal
+
+
+
+
About
VaTeX is a large-scale multilingual video captioning benchmark featuring over 41,250 videos and 825,000 captions in English and Chinese, including 206,000 parallel translation pairs. This comprehensive evaluation tests AI models' ability to generate multilingual video descriptions and perform video-guided machine translation, challenging both visual understanding and cross-lingual caption generation capabilities.
+
+
+
+
Evaluation Stats
Total Models2
Organizations1
Verified Results0
Self-Reported2
+
+
+
+
Benchmark Details
Max Score1
Language
en
+
+
+
+
Performance Overview
Score distribution and top performers
Score Distribution
2 models
Top Score
77.8%
Average Score
77.8%
High Performers (80%+)
0Top Organizations
#1Amazon
2 models
77.8%
+
+
+
+
Leaderboard
2 models ranked by performance on VATEX
| License | Links | ||||
|---|---|---|---|---|---|
| Nov 20, 2024 | Proprietary | 77.8% | |||
| Nov 20, 2024 | Proprietary | 77.8% |
