Name
Abstract | ||
|---|---|---|
We present VX2TEXT, a framework for text generation from multimodal inputs consisting of video plus text, speech, or audio. In order to leverage transformer networks, which have been shown to be effective at modeling language, each modality is first converted into a set of language embeddings by a learnable tokenizer. This allows our approach to perform multimodal fusion in the language space, thus eliminating the need for ad-hoc cross-modal fusion modules. To address the non-differentiability of tokenization on continuous inputs (e.g., video or audio), we utilize a relaxation scheme that enables end-to-end training. Furthermore, unlike prior encoder-only models, our network includes an autoregressive decoder to generate open-ended text from the multimodal embeddings fused by the language encoder. This renders our approach fully generative and makes it directly applicable to different "video+x to text" problems without the need to design specialized network heads for each task. The proposed framework is not only conceptually simple but also remarkably effective: experiments demonstrate that our approach based on a single architecture outperforms the state-of-the-art on three video-based text-generation tasks-captioning, question answering and audio-visual scene-aware dialog. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/CVPR46437.2021.00693 | 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 |
DocType | ISSN | Citations |
Conference | 1063-6919 | 0 |
PageRank | References | Authors |
0.34 | 0 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xudong Lin | 1 | 5 | 2.77 |
| Gedas Bertasius | 2 | 169 | 10.38 |
| Jue Wang | 3 | 18 | 3.78 |
| Shih-Fu Chang | 4 | 13015 | 1101.53 |
| Devi Parikh | 5 | 2929 | 132.01 |
| Lorenzo Torresani | 6 | 2756 | 120.63 |