VATEX

VATEX is a large-scale multilingual video description dataset, which contains over 41,250 videos and 825,000 captions in both English and Chinese. VATEX is characterized by the following major unique properties. First, it contains both English and Chinese descriptions at scale, which can support many multilingual studi

Papers using VATEX (6)

ABMAMBA: Multimodal Large Language Model with Aligned Hierarchical Bidirectional Scan for Efficient Video Captioning2026GAIS: Frame-level Gated Audio-visual Integration With Semantic Variance-scaled Perturbation For Text-video Retrieval2025CLIP2Video: Mastering Video-Text Retrieval via Image CLIP2021 · 131 citesAccommodating Audio Modality in CLIP for Multimodal Processing2023 · 10 citesMultilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Models2021 · 5 citesCL2CM: Improving Cross-Lingual Cross-Modal Retrieval via Cross-Lingual Knowledge Transfer2023