| license: apache-2.0 | |
| language: | |
| - en | |
| **VLE** (**V**isual-**L**anguage **E**ncoder) is an image-text multimodal understanding model built on the pre-trained text and image encoders. It can be used for multimodal discriminative tasks such as visual question answering and image-text retrieval. Especially on the visual commonsense reasoning (VCR) task, which requires high-level language understanding and reasoning skills, VLE achieves the best performance among the public methods. | |
| For more details see [https://github.com/iflytek/VLE](https://github.com/iflytek/VLE). | |
| Online VLE demo on Visual Question Answering: [https://huggingface.co/spaces/hfl/VQA_VLE_LLM](https://huggingface.co/spaces/hfl/VQA_VLE_LLM) | |