相关论文: GLAMI-1M: A Multilingual Image-Text Fashion Datase…

Object grasping is critical for many applications, which is also a challenging computer vision problem. However, for the clustered scene, current researches suffer from the problems of insufficient training data and the lacking of…

Developing effective scene text detection and recognition models hinges on extensive training data, which can be both laborious and costly to obtain, especially for low-resourced languages. Conventional methods tailored for Latin characters…

We introduce The Benchmark of Linguistic Minimal Pairs (shortened to BLiMP), a challenge set for evaluating what language models (LMs) know about major grammatical phenomena in English. BLiMP consists of 67 sub-datasets, each containing…

Representing a true label as a one-hot vector is a common practice in training text classification models. However, the one-hot representation may not adequately reflect the relation between the instances and labels, as labels are often not…

Vision-language datasets are vital for both text-to-image (T2I) and image-to-text (I2T) research. However, current datasets lack descriptions with fine-grained detail that would allow for richer associations to be learned by models. To fill…

The fusion of AI and fashion design has emerged as a promising research area. However, the lack of extensive, interrelated data on clothing and try-on stages has hindered the full potential of AI in this domain. Addressing this, we present…

In-context learning (ICL) facilitates Large Language Models (LLMs) exhibiting emergent ability on downstream tasks without updating billions of parameters. However, in the area of multi-modal Large Language Models (MLLMs), two problems…

Recently, multimodal large language models (MLLMs) have achieved significant advancements across various domains, and corresponding evaluation benchmarks have been continuously refined and improved. In this process, benchmarks in the…

Text-based safety classifiers are widely used for content moderation and increasingly to tune generative language model behavior - a topic of growing concern for the safety of digital assistants and chatbots. However, different policies…

We introduce SIFT (Speech Instruction Fine-Tuning), a 50M-example dataset designed for instruction fine-tuning and pre-training of speech-text large language models (LLMs). SIFT-50M is built from publicly available speech corpora, which…

Language models (LMs) have excelled in various broad domains. However, to ensure their safe and effective integration into real-world educational settings, they must demonstrate proficiency in specific, granular areas of knowledge. Existing…

With the rapid advancement of Multimodal Large Language Models (MLLMs), a variety of benchmarks have been introduced to evaluate their capabilities. While most evaluations have focused on complex tasks such as scientific comprehension and…

ImageNet has been arguably the most popular image classification benchmark, but it is also the one with a significant level of label noise. Recent studies have shown that many samples contain multiple classes, despite being assumed to be a…

Text-to-image generation models have achieved strong performance in culturally homogeneous settings, yet their ability to generate multicultural scenes, where people and landmarks originate from different cultures, remains largely…

Recent works have shown that unstructured text (documents) from online sources can serve as useful auxiliary information for zero-shot image classification. However, these methods require access to a high-quality source like Wikipedia and…

Massive web-crawled image-text datasets lay the foundation for recent progress in multimodal learning. These datasets are designed with the goal of training a model to do well on standard computer vision benchmarks, many of which, however,…

Multi-emotion sentiment classification is a natural language processing (NLP) problem with valuable use cases on real-world data. We demonstrate that large-scale unsupervised language modeling combined with finetuning offers a practical…

This paper aims to re-assess scene text recognition (STR) from a data-oriented perspective. We begin by revisiting the six commonly used benchmarks in STR and observe a trend of performance saturation, whereby only 2.91% of the benchmark…

The importance of Scene Text Recognition (STR) in today's increasingly digital world cannot be overstated. Given the significance of STR, data intensive deep learning approaches that auto-learn feature mappings have primarily driven the…

The Multi-language Video Subtitle Dataset is a comprehensive collection designed to support research in text recognition across multiple languages. This dataset includes 4,224 subtitle images extracted from 24 videos sourced from online…