Related papers: ClapperText: A Benchmark for Text Recognition in L…
Few-shot text classification has recently been promoted by the meta-learning paradigm which aims to identify target classes with knowledge transferred from source classes with sets of small tasks named episodes. Despite their success,…
Understanding movies and their structural patterns is a crucial task in decoding the craft of video editing. While previous works have developed tools for general analysis, such as detecting characters or recognizing cinematography…
Retrieving target videos based on text descriptions is a task of great practical value and has received increasing attention over the past few years. Despite recent progress, imperfect annotations in existing video retrieval datasets have…
Automatic Speech Recognition (ASR) systems, such as Whisper, achieve high transcription accuracy but struggle with named entities and numerical data, especially when proper formatting is required. These issues increase word error rate (WER)…
There has been a recent surge in methods that aim to decompose and segment scenes into multiple objects in an unsupervised manner, i.e., unsupervised multi-object segmentation. Performing such a task is a long-standing goal of computer…
Training automatic speech recognition (ASR) systems requires large amounts of well-curated paired data. However, human annotators usually perform "non-verbatim" transcription, which can result in poorly trained models. In this paper, we…
Crowdsourcing annotations has created a paradigm shift in the availability of labeled data for machine learning. Availability of large datasets has accelerated progress in common knowledge applications involving visual and language data.…
Large-scale pretrained image-text models have shown incredible zero-shot performance in a handful of tasks, including video ones such as action recognition and text-to-video retrieval. However, these models have not been adapted to video,…
Historical documents present many challenges for offline handwriting recognition systems, among them, the segmentation and labeling steps. Carefully annotated textlines are needed to train an HTR system. In some scenarios, transcripts are…
The objective of the paper is to recognize handwritten samples of lower case Roman script using Tesseract open source Optical Character Recognition (OCR) engine under Apache License 2.0. Handwritten data samples containing isolated and…
Recent works in the text recognition area have pushed forward the recognition results to the new horizons. But for a long time a lack of large human-labeled natural text recognition datasets has been forcing researchers to use synthetic…
Most existing text-video retrieval methods focus on cross-modal matching between the visual content of videos and textual query sentences. However, in real-world scenarios, online videos are often accompanied by relevant text information…
Recently, Vision-Language Pre-training (VLP) techniques have greatly benefited various vision-language tasks by jointly learning visual and textual representations, which intuitively helps in Optical Character Recognition (OCR) tasks due to…
Handwritten document recognition (HDR) is one of the most challenging tasks in the field of computer vision, due to the various writing styles and complex layouts inherent in handwritten texts. Traditionally, this problem has been…
Talking-head videos constitute a predominant content type in real-time communication, yet publicly available datasets for video processing research in this domain remain scarce and limited in signal fidelity. In this paper, we open-source a…
There is little to no data available to build natural language processing models for most endangered languages. However, textual data in these languages often exists in formats that are not machine-readable, such as paper books and scanned…
While state-of-the-art Handwritten Text Recognition (HTR) models perform well on standard benchmarks, they frequently struggle with writers exhibiting highly specific styles that are underrepresented in the training data. To handle unseen…
Advancements in multimodal learning, particularly in video understanding and generation, require high-quality video-text datasets for improved model performance. Vript addresses this issue with a meticulously annotated corpus of 12K…
We introduce new techniques for extracting, analyzing, and visualizing textual contents from instructional videos of low production quality. Using Automatic Speech Recognition, approximate transcripts (H75% Word Error Rate) are obtained…
A large fraction of textual data available today contains various types of 'noise', such as OCR noise in digitized documents, noise due to informal writing style of users on microblogging sites, and so on. To enable tasks such as…