CapEnrich: Enriching Caption Semantics for Web Images via Cross-modal Pre-trained Knowledge
Open Access
- 30 April 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 2392-2401
Abstract
Automatically generating textual descriptions for massive unlabeled images on the web can greatly benefit realistic web applications, e.g. multimodal retrieval and recommendation. However, existing models suffer from the problem of generating “over-generic” descriptions, such as their tendency to generate repetitive sentences with common concepts for different images. These generic descriptions fail to provide sufficient textual semantics for ever-changing web images. Inspired by the recent success of Vision-Language Pre-training (VLP) models that learn diverse image-text concept alignment during pretraining, we explore leveraging their cross-modal pre-trained knowledge to automatically enrich the textual semantics of image descriptions. With no need for additional human annotations, we propose a plug-and-play framework, i.e CapEnrich, to complement the generic image descriptions with more semantic details. Specifically, we first propose an automatic data-building strategy to get desired training sentences, based on which we then adopt prompting strategies, i.e. learnable and template prompts, to incentivize VLP models to generate more textual details. For learnable templates, we fix the whole VLP model and only tune the prompt vectors, which leads to two advantages: 1) the pre-training knowledge of VLP models can be reserved as much as possible to describe diverse visual concepts; 2) only lightweight trainable parameters are required, so it is friendly to low data resources. Extensive experiments show that our method significantly improves the descriptiveness and diversity of generated sentences for web images. The code is available at https://github.com/yaolinli/CapEnrich.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62072462)
- National Key R&D Program of China (2020AAA0108600)
This publication has 24 references indexed in Scilit:
- Show, Tell and Discriminate: Image Captioning by Self-retrieval with Partially Labeled Data2018
- Discriminability Objective for Training Descriptive Captions2018
- GroupCap: Group-Based Image Captioning with Structured Relevance and Diversity Constraints2018
- Speaking the Same Language: Matching Machine to Human Captions by Adversarial Training2017
- Self-Critical Sequence Training for Image Captioning2017
- SPICE: Semantic Propositional Image Caption Evaluation2016
- Deep visual-semantic alignments for generating image descriptions2015
- Show and tell: A neural image caption generator2015
- CIDEr: Consensus-based image description evaluation2015
- From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptionsTransactions of the Association for Computational Linguistics, 2014