中文
相关论文

相关论文: Patch Matters: Training-free Fine-grained Image Ca…

200 篇论文

Visual recognition in a low-data regime is challenging and often prone to overfitting. To mitigate this issue, several data augmentation strategies have been proposed. However, standard transformations, e.g., rotation, cropping, and…

计算机视觉与模式识别 · 计算机科学 2023-11-08 Aniket Roy , Anshul Shah , Ketul Shah , Anirban Roy , Rama Chellappa

Image captioning is a computer vision task that involves generating natural language descriptions for images. This method has numerous applications in various domains, including image retrieval systems, medicine, and various industries.…

计算机视觉与模式识别 · 计算机科学 2023-08-08 Sai Suprabhanu Nallapaneni , Subrahmanyam Konakanchi

Multimodal Large Language Models (MLLMs) have made significant progress in bridging the gap between visual and language modalities. However, hallucinations in MLLMs, where the generated text does not align with image content, continue to be…

人工智能 · 计算机科学 2024-08-05 Kohou Wang , Xiang Liu , Zhaoxiang Liu , Kai Wang , Shiguo Lian

Text-to-image models have rapidly evolved from casual creative tools to professional-grade systems, achieving unprecedented levels of image quality and realism. Yet, most models are trained to map short prompts into detailed images,…

计算机视觉与模式识别 · 计算机科学 2025-11-11 Eyal Gutflaish , Eliran Kachlon , Hezi Zisman , Tal Hacham , Nimrod Sarid , Alexander Visheratin , Saar Huberman , Gal Davidi , Guy Bukchin , Kfir Goldberg , Ron Mokady

Open-vocabulary semantic segmentation aims at segmenting arbitrary categories expressed in textual form. Previous works have trained over large amounts of image-caption pairs to enforce pixel-level multimodal alignments. However, captions…

计算机视觉与模式识别 · 计算机科学 2024-04-11 Luca Barsellotti , Roberto Amoroso , Marcella Cornia , Lorenzo Baraldi , Rita Cucchiara

Multimodal Large Language Models (MLLMs) excel in vision--language tasks by pre-training solely on coarse-grained concept annotations (e.g., image captions). We hypothesize that integrating fine-grained concept annotations (e.g., object…

计算机视觉与模式识别 · 计算机科学 2024-12-10 Xiao Xu , Tianhao Niu , Yuxi Xie , Libo Qin , Wanxiang Che , Min-Yen Kan

CLIP is a seminal multimodal model that maps images and text into a shared representation space through contrastive learning on billions of image-caption pairs. Inspired by the rapid progress of large language models (LLMs), we investigate…

计算机视觉与模式识别 · 计算机科学 2026-02-26 Weiquan Huang , Aoqi Wu , Yifan Yang , Xufang Luo , Yuqing Yang , Usman Naseem , Chunyu Wang , Chunyu Wang , Qi Dai , Xiyang Dai , Dongdong Chen , Chong Luo , Lili Qiu , Liang Hu

Recent advances in instruction-tuned Large Vision-Language Models (LVLMs) have imbued the models with the ability to generate high-level, image-grounded explanations with ease. While such capability is largely attributed to the rich world…

计算机视觉与模式识别 · 计算机科学 2025-01-08 Jeonghwan Kim , Heng Ji

Figure captions are crucial for helping readers understand and remember a figure's key message. Many models have been developed to generate these captions, helping authors compose better quality captions more easily. Yet, authors almost…

Recent progress on image captioning has made it possible to generate novel sentences describing images in natural language, but compressing an image into a single sentence can describe visual content in only coarse detail. While one new…

计算机视觉与模式识别 · 计算机科学 2017-04-11 Jonathan Krause , Justin Johnson , Ranjay Krishna , Li Fei-Fei

This article focuses on large language models (LLMs) fine-tuning in the scarce data regime (also known as the "few-shot" learning setting). We propose a method to increase the generalization capabilities of LLMs based on neural network…

机器学习 · 计算机科学 2023-10-25 Louis Falissard , Vincent Guigue , Laure Soulier

A large-scale vision and language model that has been pretrained on massive data encodes visual and linguistic prior, which makes it easier to generate images and language that are more natural and realistic. Despite this, there is still a…

计算机视觉与模式识别 · 计算机科学 2025-02-20 Hao Huang , Shuaihang Yuan , Yu Hao , Congcong Wen , Yi Fang

Recently, Multimodal Large Language Models (MLLMs) encounter two key issues in multi-image contexts: (1) a lack of fine-grained perception across disparate images, and (2) a diminished capability to effectively reason over and synthesize…

计算机视觉与模式识别 · 计算机科学 2025-11-06 Kuei-Chun Kao , Hsu Tzu-Yin , Yunqi Hong , Ruochen Wang , Cho-Jui Hsieh

Recent research increasingly focuses on training vision-language models (VLMs) with long, detailed image captions. However, small-scale VLMs often struggle to balance the richness of these captions with the risk of hallucinating content…

计算机视觉与模式识别 · 计算机科学 2025-08-13 Moran Yanuka , Assaf Ben Kish , Yonatan Bitton , Idan Szpektor , Raja Giryes

High-resolution content creation is rapidly emerging as a central challenge in both the vision and graphics communities. Images serve as the most fundamental modality for visual expression, and content generation that aligns with the user…

计算机视觉与模式识别 · 计算机科学 2026-04-02 Junsung Lee , Hyunsoo Lee , Yong Jae Lee , Bohyung Han

Image captioning models tend to describe images in an object-centric way, emphasising visible objects. But image descriptions can also abstract away from objects and describe the type of scene depicted. In this paper, we explore the…

计算与语言 · 计算机科学 2022-11-11 Michele Cafagna , Kees van Deemter , Albert Gatt

Image Captioning is a fundamental task to join vision and language, concerning about cross-modal understanding and text generation. Recent years witness the emerging attention on image captioning. Most of existing works follow a traditional…

计算机视觉与模式识别 · 计算机科学 2022-04-15 Ziyang Luo , Yadong Xi , Rongsheng Zhang , Jing Ma

The Multimodal Large Language Models (MLLMs) are continually pre-trained on a mixture of image-text caption data and interleaved document data, while the high-quality data filtering towards image-text interleaved document data is…

计算机视觉与模式识别 · 计算机科学 2025-10-20 Weizhi Wang , Rongmei Lin , Shiyang Li , Colin Lockard , Ritesh Sarkhel , Sanket Lokegaonkar , Jingbo Shang , Xifeng Yan , Nasser Zalmout , Xian Li

Multimodal Large Language Models (MLLM) often struggle to interpret high-resolution images accurately, where fine-grained details are crucial for complex visual understanding. We introduce Zoom-Refine, a novel training-free method that…

计算机视觉与模式识别 · 计算机科学 2025-08-12 Xuan Yu , Dayan Guan , Yanfeng Gu

An emerging family of language models (LMs), capable of processing both text and images within a single visual view, has the promise to unlock complex tasks such as chart understanding and UI navigation. We refer to these models as…

计算与语言 · 计算机科学 2024-02-27 Tianyu Gao , Zirui Wang , Adithya Bhaskar , Danqi Chen