Skip to yearly menu bar Skip to main content


LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment

Bin Zhu · Bin Lin · Munan Ning · YANG YAN · Jiaxi Cui · WANG HongFa · Yatian Pang · Wenhao Jiang · Junwu Zhang · Zongwei Li · Cai Zhang · Zhifeng Li · Wei Liu · Yuan Li

Halle B #265
[ ]
Wed 8 May 7:30 a.m. PDT — 9:30 a.m. PDT


The video-language (VL) pretraining has achieved remarkable improvement in multiple downstream tasks. However, the current VL pretraining framework is hard to extend to multiple modalities (N modalities, N ≥ 3) beyond vision and language. We thus propose LanguageBind, taking the language as the bind across different modalities because the language modality is well-explored and contains rich semantics. Specifically, we freeze the language encoder acquired by VL pretraining and then train encoders for other modalities with contrastive learning. As a result, all modalities are mapped to a shared feature space, implementing multi-modal semantic alignment. While LanguageBind ensures that we can extend VL modalities to N modalities, we also need a high-quality dataset with alignment data pairs centered on language. We thus propose VIDAL-10M with 10 Million data with Video, Infrared, Depth, Audio and their corresponding Language. In our VIDAL-10M, all videos are from short video platforms with complete semantics rather than truncated segments from long videos, and all the video, depth, infrared, and audio modalities are aligned to their textual descriptions. LanguageBind has achieved superior performance on a wide range of 15 benchmarks covering video, audio, depth, and infrared. Moreover, multiple experiments have provided evidence for the effectiveness of LanguageBind in achieving indirect alignment and complementarity among diverse modalities.

Chat is not available.