English
Related papers

Related papers: SPECS: Specificity-Enhanced CLIP-Score for Long Im…

200 papers

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…

Computer Vision and Pattern Recognition · Computer Science 2023-08-01 Simon Kornblith , Lala Li , Zirui Wang , Thao Nguyen

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)…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Maria Tzelepi , Vasileios Mezaris

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…

Computer Vision and Pattern Recognition · Computer Science 2022-08-30 Youyuan Zhang , Jiuniu Wang , Hao Wu , Wenjia Xu

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,…

Computation and Language · Computer Science 2022-10-31 Elisa Kreiss , Cynthia Bennett , Shayan Hooshmand , Eric Zelikman , Meredith Ringel Morris , Christopher Potts

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…

Computation and Language · Computer Science 2025-07-01 Hyunjong Kim , Sangyeop Kim , Jongheon Jeong , Yeongjae Cho , Sungzoon Cho

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…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Ziteng Wang , Siqi Yang , Limeng Qiao , Lin Ma

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…

Computer Vision and Pattern Recognition · Computer Science 2016-08-01 Peter Anderson , Basura Fernando , Mark Johnson , Stephen Gould

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,…

Computer Vision and Pattern Recognition · Computer Science 2026-01-05 Hongseok Oh , Wonseok Hwang

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,…

Computer Vision and Pattern Recognition · Computer Science 2025-04-10 Ruotian Peng , Haiying He , Yake Wei , Yandong Wen , Di Hu

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…

Computer Vision and Pattern Recognition · Computer Science 2025-03-27 Fan Lu , Wei Wu , Kecheng Zheng , Shuailei Ma , Biao Gong , Jiawei Liu , Wei Zhai , Yang Cao , Yujun Shen , Zheng-Jun Zha

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…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Bingwen Hu , Heng Liu , Zhedong Zheng , Ping Liu

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…

Computation and Language · Computer Science 2022-05-20 Jungo Kasai , Keisuke Sakaguchi , Lavinia Dunagan , Jacob Morrison , Ronan Le Bras , Yejin Choi , Noah A. Smith

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…

Computation and Language · Computer Science 2023-03-16 Yongil Kim , Yerin Hwang , Hyeongu Yun , Seunghyun Yoon , Trung Bui , Kyomin Jung

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…

Computer Vision and Pattern Recognition · Computer Science 2024-11-01 Michael Saxon , Fatima Jahara , Mahsa Khoshnoodi , Yujie Lu , Aditya Sharma , William Yang Wang

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…

Computer Vision and Pattern Recognition · Computer Science 2024-11-27 Yanqing Liu , Xianhang Li , Zeyu Wang , Bingchen Zhao , Cihang Xie

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…

Computer Vision and Pattern Recognition · Computer Science 2025-02-11 Fabian Paischer , Markus Hofmarcher , Sepp Hochreiter , Thomas Adler

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…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Luigi Celona , Simone Bianco , Marco Donzella , Paolo Napoletano

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…

Computer Vision and Pattern Recognition · Computer Science 2024-11-12 Hankyeol Lee , Gawon Seo , Wonseok Choi , Geunyoung Jung , Kyungwoo Song , Jiyoung Jung

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…

Computer Vision and Pattern Recognition · Computer Science 2025-07-08 Sanghyeok Chu , Seonguk Seo , Bohyung Han