A multimodal, memory-augmented multi-agent system for video subtitling and translation, plus a new 17-hour benchmark, reports large BLEU/SubER gains on its own benchmark but not consistently on existing benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ViDove: A Translation Agent System with Multimodal Context and Memory-Augmented Reasoning
A multimodal, memory-augmented multi-agent system for video subtitling and translation, plus a new 17-hour benchmark, reports large BLEU/SubER gains on its own benchmark but not consistently on existing benchmarks.