相关论文: QACE: Asking Questions to Evaluate an Image Captio…
Video question-answering (QA) is a core task in video understanding. Evaluating the quality of video QA and video caption data quality for training video large language models (VideoLLMs) is an essential challenge. Although various methods…
This paper introduces a new data-driven, non-parametric method for image quality and aesthetics assessment, surpassing existing approaches and requiring no prompt engineering or fine-tuning. We eliminate the need for expressive textual…
Despite significant progress in generative AI, comprehensive evaluation remains challenging because of the lack of effective metrics and standardized benchmarks. For instance, the widely-used CLIPScore measures the alignment between a…
Recent works in image captioning have shown very promising raw performance. However, we realize that most of these encoder-decoder style networks with attention do not scale naturally to large vocabulary size, making them difficult to be…
The prevalence of user-generated content (UGC) on platforms such as YouTube and TikTok has rendered no-reference (NR) perceptual video quality assessment (VQA) vital for optimizing video delivery. Nonetheless, the characteristics of…
Recent retrieval-augmented image captioning methods incorporate external knowledge to compensate for the limitations in comprehending complex scenes. However, current approaches face challenges in relation modeling: (1) the representation…
Image aesthetic quality assessment (AQA) aims to assign numerical aesthetic ratings to images whilst image aesthetic captioning (IAC) aims to generate textual descriptions of the aesthetic aspects of images. In this paper, we study image…
Distinctive Image Captioning (DIC) -- generating distinctive captions that describe the unique details of a target image -- has received considerable attention over the last few years. A recent DIC method proposes to generate distinctive…
Humor, deeply rooted in societal meanings and cultural details, poses a unique challenge for machines. While advances have been made in natural language processing, real-world humor often thrives in a multi-modal context, encapsulated…
Video captions play a crucial role in text-to-video generation tasks, as their quality directly influences the semantic coherence and visual fidelity of the generated videos. Although large vision-language models (VLMs) have demonstrated…
QuestEval is a reference-less metric used in text-to-text tasks, that compares the generated summaries directly to the source text, by automatically asking and answering questions. Its adaptation to Data-to-Text tasks is not…
Image captioning models are usually evaluated on their ability to describe a held-out set of images, not on their ability to generalize to unseen concepts. We study the problem of compositional generalization, which measures how well a…
Most pre-trained learning systems are known to suffer from bias, which typically emerges from the data, the model, or both. Measuring and quantifying bias and its sources is a challenging task and has been extensively studied in image…
Visual question answering is an important task in both natural language and vision understanding. However, in most of the public visual question answering datasets such as VQA, CLEVR, the questions are human generated that specific to the…
Image Captioning is one of the vision-language tasks that still interest the research community worldwide in the 2020s. MS-COCO Caption benchmark is commonly used to evaluate the performance of advanced captioning models, although it was…
Current metrics for video captioning are mostly based on the text-level comparison between reference and candidate captions. However, they have some insuperable drawbacks, e.g., they cannot handle videos without references, and they may…
Visual Question Generation (VQG) is a task to generate questions from images. When humans ask questions about an image, their goal is often to acquire some new knowledge. However, existing studies on VQG have mainly addressed question…
We introduce a new large-scale dataset that links the assessment of image quality issues to two practical vision tasks: image captioning and visual question answering. First, we identify for 39,181 images taken by people who are blind…
This paper introduces QCaption, a novel video captioning and Q&A pipeline that enhances video analytics by fusing three models: key frame extraction, a Large Multimodal Model (LMM) for image-text analysis, and a Large Language Model (LLM)…
Image captioning, which generates natural language descriptions of the visual information in an image, is a crucial task in vision-language research. Previous models have typically addressed this task by aligning the generative capabilities…