MultiCapCLIP: Auto-Encoding Prompts for Zero-Shot Multilingual Visual Captioning

Abstract

Supervised visual captioning models typically require a large scale of images or videos paired with descriptions in a specific language (i.e., the vision-caption pairs) for training. However, collecting and labeling large-scale datasets is time-consuming and expensive for many scenarios and languages. Therefore, sufficient labeled pairs are usually not available. To deal with the label shortage problem, we present a simple yet effective zero-shot approach MultiCapCLIP that can generate visual captions for different scenarios and languages without any labeled vision-caption pairs of downstream datasets. In the training stage, MultiCapCLIP only requires text data for input. Then it conducts two main steps: 1) retrieving concept prompts that preserve the corresponding domain knowledge of new scenarios; 2) auto-encoding the prompts to learn writing styles to output captions in a desired language. In the testing stage, MultiCapCLIP instead takes visual data as input directly to retrieve the concept prompts to generate the final visual descriptions. The extensive experiments on image and video captioning across four benchmarks and four languages (i.e., English, Chinese, German, and French) confirm the effectiveness of our approach. Compared with state-of-the-art zero-shot and weakly-supervised methods, our method achieves 4.8% and 21.5% absolute improvements in terms of BLEU@4 and CIDEr metrics. Our code is available at https://github.com/yangbang18/MultiCapCLIP.

arXiv commentACL'2023, 13 pages, 4 figures

References in corpus (17)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Decoupled Weight Decay Regularization
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Representation Learning with Contrastive Predictive Coding
• Microsoft COCO Captions: Data Collection and Evaluation Server
• Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
• Recent Advances in Autoencoder-Based Representation Learning
• GIT: A Generative Image-to-text Transformer for Vision and Language
• Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language
• Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning
• Language Models Can See: Plugging Visual Controls in Text Generation
• Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations
• Cross-Lingual Cross-Modal Retrieval with Noise-Robust Learning
• DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training
• Zero-Shot Video Captioning with Evolving Pseudo-Tokens
• I Can't Believe There's No Images! Learning Visual Tasks Using only Language Supervision
• ZeroNLG: Aligning and Autoencoding Domains for Zero-Shot Multimodal and Multilingual Natural Language Generation