相关论文: CAPability: A Comprehensive Visual Caption Benchma…

Video detailed captioning aims to generate comprehensive video descriptions to facilitate video understanding. Recently, most efforts in the video detailed captioning community have been made towards a local-to-global paradigm, which first…

Automatically generating a human-like description for a given image is a potential research in artificial intelligence, which has attracted a great of attention recently. Most of the existing attention methods explore the mapping…

Image captioning models require the high-level generalization ability to describe the contents of various images in words. Most existing approaches treat the image-caption pairs equally in their training without considering the differences…

Joint vision-language models have shown great performance over a diverse set of tasks. However, little is known about their limitations, as the high dimensional space learned by these models makes it difficult to identify semantic errors.…

The rapid development of Multi-modality Large Language Models (MLLMs) has navigated a paradigm shift in computer vision, moving towards versatile foundational models. However, evaluating MLLMs in low-level visual perception and…

The recent development of Multimodal Large Language Models (MLLMs) has significantly advanced AI's ability to understand visual modalities. However, existing evaluation benchmarks remain limited to single-turn question answering,…

Evaluating text-to-vision content hinges on two crucial aspects: visual quality and alignment. While significant progress has been made in developing objective models to assess these dimensions, the performance of such models heavily relies…

Vision Large Language Models (VLLMs) are widely acknowledged to be prone to hallucinations. Existing research addressing this problem has primarily been confined to image inputs, with limited exploration of video-based hallucinations.…

Automatic image captioning evaluation is critical for benchmarking and promoting advances in image captioning research. Existing metrics only provide a single score to measure caption qualities, which are less explainable and informative.…

Large Vision-Language Models (LVLMs) have achieved remarkable performance in many vision-language tasks, yet their capabilities in fine-grained visual understanding remain insufficiently evaluated. Existing benchmarks either contain limited…

Humans develop perception through a bottom-up hierarchy: from basic primitives and Gestalt principles to high-level semantics. In contrast, current Multimodal Large Language Models (MLLMs) are trained directly on complex downstream tasks,…

Video detailed captioning is a key task which aims to generate comprehensive and coherent textual descriptions of video content, benefiting both video understanding and generation. In this paper, we propose AuroraCap, a video captioner…

The advent of vision-language pre-training techniques enhanced substantial progress in the development of models for image captioning. However, these models frequently produce generic captions and may omit semantically important image…

Scientific figure captioning is a complex task that requires generating contextually appropriate descriptions of visual content. However, existing methods often fall short by utilizing incomplete information, treating the task solely as…

Multimodal Large Language Models (MLLMs) are evaluated on various benchmarks, such as image captioning, visual question answering, and reasoning. However, many of these benchmarks include overly simple or uninformative samples, complicating…

Image-Text matching (ITM) is a common task for evaluating the quality of Vision and Language (VL) models. However, existing ITM benchmarks have a significant limitation. They have many missing correspondences, originating from the data…

Inspired by human categorization, object property reasoning involves identifying and recognizing low-level details and higher-level abstractions. While current visual question answering (VQA) studies consider multiple object properties,…

Recently, video captioning has been attracting an increasing amount of interest, due to its potential for improving accessibility and information retrieval. While existing methods rely on different kinds of visual features and model…

Evaluation metric of visual captioning is important yet not thoroughly explored. Traditional metrics like BLEU, METEOR, CIDEr, and ROUGE often miss semantic depth, while trained metrics such as CLIP-Score, PAC-S, and Polos are limited in…

Multimodal large language models (MLLMs) have achieved rapid progress, yet their scaling behavior remains less clearly characterized and often less predictable than that of text-only LLMs. Increasing model size and task diversity often…