Related papers: CapText: Large Language Model-based Caption Genera…
Generating novel pairs of image and text is a problem that combines computer vision and natural language processing. In this paper, we present strategies for generating novel image and caption pairs based on existing captioning datasets.…
Image captioning, a fundamental task in vision-language understanding, seeks to generate accurate natural language descriptions for provided images. Current image captioning approaches heavily rely on high-quality image-caption pairs, which…
Conditional image modeling based on textual descriptions is a relatively new domain in unsupervised learning. Previous approaches use a latent variable model and generative adversarial networks. While the formers are approximated by using…
Modern image captioning models are usually trained with text similarity objectives. However, since reference captions in public datasets often describe the most salient common objects, models trained with text similarity objectives tend to…
To address computational and memory limitations of Large Multimodal Models in the Video Question-Answering task, several recent methods extract textual representations per frame (e.g., by captioning) and feed them to a Large Language Model…
We introduce a novel meme generation system, which given any image can produce a humorous and relevant caption. Furthermore, the system can be conditioned on not only an image but also a user-defined label relating to the meme template,…
Fine-tuning image captioning models with hand-crafted rewards like the CIDEr metric has been a classical strategy for promoting caption quality at the sequence level. This approach, however, is known to limit descriptiveness and semantic…
The task of image captioning aims to generate captions directly from images via the automatically learned cross-modal generator. To build a well-performing generator, existing approaches usually need a large number of described images,…
Existing dense or paragraph video captioning approaches rely on holistic representations of videos, possibly coupled with learned object/action representations, to condition hierarchical language decoders. However, they fundamentally lack…
Recent advances in vision-language models have led to impressive progress in caption generation for images and short video clips. However, these models remain constrained by their limited temporal receptive fields, making it difficult to…
We investigate the use of multimodal information contained in images as an effective method for enhancing the commonsense of Transformer models for text generation. We perform experiments using BART and T5 on concept-to-text generation,…
Most image captioning frameworks generate captions directly from images, learning a mapping from visual features to natural language. However, editing existing captions can be easier than generating new ones from scratch. Intuitively, when…
The recent progress on image recognition and language modeling is making automatic description of image content a reality. However, stylized, non-factual aspects of the written description are missing from the current systems. One such…
Benefiting from advances in machine vision and natural language processing techniques, current image captioning systems are able to generate detailed visual descriptions. For the most part, these descriptions represent an objective…
This paper introduces a large-scale multimodal and multilingual dataset that aims to facilitate research on grounding words to images in their contextual usage in language. The dataset consists of images selected to unambiguously illustrate…
Integrating outside knowledge for reasoning in visio-linguistic tasks such as visual question answering (VQA) is an open problem. Given that pretrained language models have been shown to include world knowledge, we propose to use a unimodal…
Neural captioners are typically trained to mimic human-generated references without optimizing for any specific communication goal, leading to problems such as the generation of vague captions. In this paper, we show that fine-tuning an…
This paper proposes a network architecture to perform variable length semantic video generation using captions. We adopt a new perspective towards video generation where we allow the captions to be combined with the long-term and short-term…
Generative models have shown significant achievements in audio generation tasks. However, existing models struggle with complex and detailed prompts, leading to potential performance degradation. We hypothesize that this problem stems from…
State-of-the-art approaches for image captioning require supervised training data consisting of captions with paired image data. These methods are typically unable to use unsupervised data such as textual data with no corresponding images,…