English
Related papers

Related papers: Revisit Large-Scale Image-Caption Data in Pre-trai…

200 papers

Recent advancements in text-to-image generation using diffusion models have significantly improved the quality of generated images and expanded the ability to depict a wide range of objects. However, ensuring that these models adhere…

Computer Vision and Pattern Recognition · Computer Science 2024-05-20 Michail Tarasiou , Stylianos Moschoglou , Jiankang Deng , Stefanos Zafeiriou

The topic diversity of open-domain videos leads to various vocabularies and linguistic expressions in describing video contents, and therefore, makes the video captioning task even more challenging. In this paper, we propose an unified…

Computer Vision and Pattern Recognition · Computer Science 2023-02-15 Shizhe Chen , Jia Chen , Qin Jin , Alexander Hauptmann

Effective token compression remains a critical challenge for scaling models to handle increasingly complex and diverse datasets. A novel mechanism based on contextual reinforcement is introduced, dynamically adjusting token importance…

Computation and Language · Computer Science 2025-08-11 Naderdel Piero , Zacharias Cromwell , Nathaniel Wainwright , Matthias Nethercott

While multimodal large language models excel at tasks that integrate visual perception with symbolic reasoning, their performance is often undermined by a critical vulnerability: perception-induced errors that propagate through the…

Multimedia · Computer Science 2025-09-29 Songjun Tu , Qichao Zhang , Jingbo Sun , Yuqian Fu , Linjing Li , Xiangyuan Lan , Dongmei Jiang , Yaowei Wang , Dongbin Zhao

In this paper, we show different fine-tuning methods for Stable Diffusion XL; this includes inference steps, and caption customization for each image to align with generating images in the style of a commercial 2D icon training set. We also…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Youssef Sultan , Jiangqin Ma , Yu-Ying Liao

Recent multimodal models such as Contrastive Language-Image Pre-training (CLIP) have shown remarkable ability to align visual and linguistic representations. However, domains where small visual differences carry large semantic significance,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Hiroshi Sasaki

Stylized image captioning as presented in prior work aims to generate captions that reflect characteristics beyond a factual description of the scene composition, such as sentiments. Such prior work relies on given sentiment identifiers,…

Computer Vision and Pattern Recognition · Computer Science 2022-05-05 Franz Klein , Shweta Mahajan , Stefan Roth

Learning specific hands-on skills such as cooking, car maintenance, and home repairs increasingly happens via instructional videos. The user experience with such videos is known to be improved by meta-information such as time-stamped…

Computer Vision and Pattern Recognition · Computer Science 2020-11-25 Gabriel Huang , Bo Pang , Zhenhai Zhu , Clara Rivera , Radu Soricut

Image captioning as a multimodal task has drawn much interest in recent years. However, evaluation for this task remains a challenging problem. Existing evaluation metrics focus on surface similarity between a candidate caption and a set of…

Computation and Language · Computer Science 2019-12-20 Huiyuan Xie , Tom Sherborne , Alexander Kuhnle , Ann Copestake

Most text-to-image customization techniques fine-tune models on a small set of \emph{personal concept} images captured in minimal contexts. This often results in the model becoming overfitted to these training images and unable to…

Computer Vision and Pattern Recognition · Computer Science 2024-10-15 Taewook Kim , Wei Chen , Qiang Qiu

Large vision-language contrastive models (VLCMs), such as CLIP, have become foundational, demonstrating remarkable success across a variety of downstream tasks. Despite their advantages, these models, akin to other foundational systems,…

Computer Vision and Pattern Recognition · Computer Science 2025-07-10 Haocheng Dai , Sarang Joshi

Generative vision-language models (VLMs) exhibit strong high-level image understanding but lack spatially dense alignment between vision and language modalities, as our findings indicate. Orthogonal to advancements in generative VLMs,…

Computer Vision and Pattern Recognition · Computer Science 2025-09-16 Tim Lebailly , Vijay Veerabadran , Satwik Kottur , Karl Ridgeway , Michael Louis Iuzzolino

There are a thousand ways to caption an image. Contrastive Language Pretraining (CLIP) on the other hand, works by mapping an image and its caption to a single vector -- limiting how well CLIP-like models can represent the diverse ways to…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Samuel Lavoie , Polina Kirichenko , Mark Ibrahim , Mahmoud Assran , Andrew Gordon Wilson , Aaron Courville , Nicolas Ballas

Multimodal misinformation, such as miscaptioned images, where captions misrepresent an image's origin, context, or meaning, poses a growing challenge in the digital age. Due to the scarcity of large-scale annotated datasets for multimodal…

Computer Vision and Pattern Recognition · Computer Science 2026-01-14 Stefanos-Iordanis Papadopoulos , Christos Koutlis , Symeon Papadopoulos , Panagiotis C. Petrantonakis

Supervised image captioning approaches have made great progress, but it is challenging to collect high-quality human-annotated image-text data. Recently, large-scale vision and language models (e.g., CLIP) and large-scale generative…

Computer Vision and Pattern Recognition · Computer Science 2024-03-29 Yiyu Wang , Hao Luo , Jungang Xu , Yingfei Sun , Fan Wang

Automatic image captioning, a multifaceted task bridging computer vision and natural language processing, aims to generate descriptive textual content from visual input. While Convolutional Neural Networks (CNNs) and Long Short-Term Memory…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Amanuel Tafese Dufera

Video captioning is an essential technology to understand scenes and describe events in natural language. To apply it to real-time monitoring, a system needs not only to describe events accurately but also to produce the captions as soon as…

Computer Vision and Pattern Recognition · Computer Science 2021-08-05 Chiori Hori , Takaaki Hori , Jonathan Le Roux

The goal of text-to-image synthesis is to generate a visually realistic image that matches a given text description. In practice, the captions annotated by humans for the same image have large variance in terms of contents and the choice of…

Machine Learning · Computer Science 2021-11-30 Hui Ye , Xiulong Yang , Martin Takac , Rajshekhar Sunderraman , Shihao Ji

Over the years, state-of-the-art (SoTA) image captioning methods have achieved promising results on some evaluation metrics (e.g., CIDEr). However, recent findings show that the captions generated by these methods tend to be biased toward…

Computer Vision and Pattern Recognition · Computer Science 2023-08-16 Qi Chen , Chaorui Deng , Qi Wu

Image captioning models are usually trained according to human annotated ground-truth captions, which could generate accurate but generic captions. In this paper, we focus on generating distinctive captions that can distinguish the target…

Computer Vision and Pattern Recognition · Computer Science 2022-08-30 Youyuan Zhang , Jiuniu Wang , Hao Wu , Wenjia Xu