相关论文: Multi-language Video Subtitle Dataset for Image-ba…

Textual overlays are often used in social media videos as people who watch them without the sound would otherwise miss essential information conveyed in the audio stream. This is why extraction of those overlays can serve as an important…

Curation methods for massive vision-language datasets trade off between dataset size and quality. However, even the highest quality of available curated captions are far too short to capture the rich visual detail in an image. To show the…

An outstanding image-text retrieval model depends on high-quality labeled data. While the builders of existing image-text retrieval datasets strive to ensure that the caption matches the linked image, they cannot prevent a caption from…

Multi-modal retrieval is an important problem for many applications, such as recommendation and search. Current benchmarks and even datasets are often manually constructed and consist of mostly clean samples where all modalities are…

Video transcript summarization is a fundamental task for video understanding. Conventional approaches for transcript summarization are usually built upon the summarization data for written language such as news articles, while the domain…

Automatic generation of video descriptions in natural language, also called video captioning, aims to understand the visual content of the video and produce a natural language sentence depicting the objects and actions in the scene. This…

A key requirement for leveraging supervised deep learning methods is the availability of large, labeled datasets. Unfortunately, in the context of RGB-D scene understanding, very little data is available -- current datasets cover a small…

Scene text recognition is essential in many applications, including automated translation, information retrieval, driving assistance, and enhancing accessibility for individuals with visual impairments. Much research has been done to…

Neural networks trained on datasets such as ImageNet have led to major advances in visual object classification. One obstacle that prevents networks from reasoning more deeply about complex scenes and situations, and from integrating visual…

Nowadays document analysis and recognition remain challenging tasks. However, only a few datasets designed for text detection (TD) and optical character recognition (OCR) problems exist. In this paper we present Distorted Document Images…

As computers have become efficient at understanding visual information and transforming it into a written representation, research interest in tasks like automatic image captioning has seen a significant leap over the last few years. While…

While progress has been made in the domain of video-language understanding, current state-of-the-art algorithms are still limited in their ability to understand videos at high levels of abstraction, such as news-oriented videos.…

Deepfakes have become a growing concern in recent years, prompting researchers to develop benchmark datasets and detection algorithms to tackle the issue. However, existing datasets suffer from significant drawbacks that hamper their…

The surge of audiovisual content on streaming platforms and social media has heightened the demand for accurate and accessible subtitles. However, existing subtitle generation methods primarily speech-based transcription or OCR-based…

The quality of the video dataset (image quality, resolution, and fine-grained caption) greatly influences the performance of the video generation model. The growing demand for video applications sets higher requirements for high-quality…

The increasing use of machine learning models has amplified the demand for high-quality, large-scale multimodal datasets. However, the availability of such datasets, especially those combining acoustic, visual and textual data, remains…

A lot of research has been devoted to identity documents analysis and recognition on mobile devices. However, no publicly available datasets designed for this particular problem currently exist. There are a few datasets which are useful for…

Translating visual data into natural language is essential for machines to understand the world and interact with humans. In this work, a comprehensive study is conducted on video paragraph captioning, with the goal to generate…

Significant progress has been made recently on challenging tasks in automatic sign language understanding, such as sign language recognition, translation and production. However, these works have focused on datasets with relatively few…

Recently, the AI community has made significant strides in developing powerful foundation models, driven by large-scale multimodal datasets. However, for audio representation learning, existing datasets suffer from limitations in the…