Related papers: SPECS: Specificity-Enhanced CLIP-Score for Long Im…
Image captioning is conventionally formulated as the task of generating captions for images that match the distribution of reference image-caption pairs. However, reference captions in standard captioning datasets are short and may not…
In this paper we deal with image classification tasks using the powerful CLIP vision-language model. Our goal is to advance the classification performance using the CLIP's image encoder, by proposing a novel Large Multimodal Model (LMM)…
Image captioning models are usually trained according to human annotated ground-truth captions, which could generate accurate but generic captions. In this paper, we focus on generating distinctive captions that can distinguish the target…
Few images on the Web receive alt-text descriptions that would make them accessible to blind and low vision (BLV) users. Image-based NLG systems have progressed to the point where they can begin to address this persistent societal problem,…
Recent advances in large language models and vision-language models have led to growing interest in explainable evaluation metrics for image captioning. However, these metrics generate explanations without standardized criteria, and the…
Despite the success of Vision-Language Models (VLMs) like CLIP in aligning vision and language, their proficiency in detailed, fine-grained visual comprehension remains a key challenge. We present CLIP-IN, a novel framework that bolsters…
There is considerable interest in the task of automatically generating image captions. However, evaluation is challenging. Existing automatic evaluation metrics are primarily sensitive to n-gram overlap, which is neither necessary nor…
Although Multimodal Large Language Models (MLLMs) have demonstrated proficiency in video captioning, practical applications require captions that follow specific user instructions rather than generating exhaustive, unconstrained…
Recently, Large Vision-Language Models (LVLMs) show remarkable performance across various domains. However, these models suffer from object hallucination. In this work, we study object hallucination primarily in a discriminative,…
High-quality image captions play a crucial role in improving the performance of cross-modal applications such as text-to-image generation, text-to-video generation, and text-image retrieval. To generate long-form, high-quality captions,…
Generating detailed captions comprehending text-rich visual content in images has received growing attention for Large Vision-Language Models (LVLMs). However, few studies have developed benchmarks specifically tailored for detailed…
Convolutional Neural Networks (CNNs) have significantly advanced Image Super-Resolution (SR), yet most CNN-based methods rely solely on pixel-based transformations, often leading to artifacts and blurring, particularly under severe…
We establish THumB, a rubric-based human evaluation protocol for image captioning models. Our scoring rubrics and their definitions are carefully developed based on machine- and human-generated captions on the MSCOCO dataset. Each caption…
Vulnerability to lexical perturbation is a critical weakness of automatic evaluation metrics for image captioning. This paper proposes Perturbation Robust Multi-Lingual CLIPScore(PR-MCS), which exhibits robustness to such perturbations, as…
With advances in the quality of text-to-image (T2I) models has come interest in benchmarking their prompt faithfulness -- the semantic coherence of generated images to the prompts they were conditioned on. A variety of T2I faithfulness…
Previous works show that noisy, web-crawled image-text pairs may limit vision-language pretraining like CLIP and propose learning with synthetic captions as a promising alternative. Our work continues this effort, introducing two simple yet…
Recently, vision-language models like CLIP have advanced the state of the art in a variety of multi-modal tasks including image captioning and caption evaluation. Many approaches leverage CLIP for cross-modal retrieval to condition…
State-of-The-Art (SoTA) image captioning models are often trained on the MicroSoft Common Objects in Context (MS-COCO) dataset, which contains human-annotated captions with an average length of approximately ten tokens. Although effective…
The performance of vision-language models (VLMs), such as CLIP, in visual classification tasks, has been enhanced by leveraging semantic knowledge from large language models (LLMs), including GPT. Recent studies have shown that in zero-shot…
Recent advances in vision-language models have led to impressive progress in caption generation for images and short video clips. However, these models remain constrained by their limited temporal receptive fields, making it difficult to…