English
Related papers

Related papers: Simple Token-Level Confidence Improves Caption Cor…

200 papers

News Image Captioning aims to create captions from news articles and images, emphasizing the connection between textual context and visual elements. Recognizing the significance of human faces in news images and the face-name co-occurrence…

Computer Vision and Pattern Recognition · Computer Science 2024-03-22 Tingyu Qu , Tinne Tuytelaars , Marie-Francine Moens

The evaluation of machine-generated image captions is a complex and evolving challenge. With the advent of Multimodal Large Language Models (MLLMs), image captioning has become a core task, increasing the need for robust and reliable…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 Sara Sarto , Marcella Cornia , Rita Cucchiara

In this paper, we introduce a model designed to improve the prediction of image-text alignment, targeting the challenge of compositional understanding in current visual-language models. Our approach focuses on generating high-quality…

Computer Vision and Pattern Recognition · Computer Science 2024-10-02 Yuheng Li , Haotian Liu , Mu Cai , Yijun Li , Eli Shechtman , Zhe Lin , Yong Jae Lee , Krishna Kumar Singh

Recent advances in multimodal large language models (MLLMs) have greatly improved image understanding and captioning capabilities. However, existing image captioning benchmarks typically suffer from limited diversity in caption length, the…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Zitong Xu , Huiyu Duan , Shengyao Qin , Guangyu Yang , Guangji Ma , Xiongkuo Min , Ke Gu , Guangtao Zhai , Patrick Le Callet

Fine-grained understanding of objects, attributes, and relationships between objects is crucial for visual-language models (VLMs). Existing benchmarks primarily focus on evaluating VLMs' capability to distinguish between two very similar…

Computer Vision and Pattern Recognition · Computer Science 2025-01-23 Rabiul Awal , Saba Ahmadi , Le Zhang , Aishwarya Agrawal

Multimodal large language models (MLLMs) have achieved remarkable progress, yet the object hallucination remains a critical challenge for reliable deployment. In this paper, we present an in-depth analysis of instruction token embeddings…

Machine Learning · Computer Science 2026-05-13 Runhe Lai , Xinhua Lu , Yanqi Wu , Jinlun Ye , Weijiang Yu , Ruixuan Wang

Concept Bottleneck Models (CBMs) provide interpretable prediction by introducing an intermediate Concept Bottleneck Layer (CBL), which encodes human-understandable concepts to explain models' decision. Recent works proposed to utilize Large…

Computer Vision and Pattern Recognition · Computer Science 2025-01-17 Divyansh Srivastava , Ge Yan , Tsui-Wei Weng

Recent advances in Multi-modal Large Language Models (MLLMs) have predominantly focused on enhancing visual perception to improve accuracy. However, a critical question remains unexplored: Do models know when they do not know? Through a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Yuetian Du , Yucheng Wang , Rongyu Zhang , Zhijie Xu , Boyu Yang , Ming Kong , Jie Liu , Qiang Zhu

Having the difficulty of solving the semantic gap between images and texts for the image captioning task, conventional studies in this area paid some attention to treating semantic concepts as a bridge between the two modalities and…

Computer Vision and Pattern Recognition · Computer Science 2023-11-29 Ting Wang , Weidong Chen , Yuanhe Tian , Yan Song , Zhendong Mao

Large Vision-Language Models (LVLMs) typically align visual features from an encoder with a pre-trained Large Language Model (LLM). However, this makes the visual perception module a bottleneck, which constrains the overall capabilities of…

Artificial Intelligence · Computer Science 2025-11-18 Wenhao Zhou , Hao Zheng , Rong Zhao

Tokenization is a foundational step in the text process of Large Language Models (LLMs). Texts must be first tokenized into token IDs, which are then input to LLMs. Inefficient tokenization results in long token-ID sequences and will slow…

Computation and Language · Computer Science 2026-05-14 Chong Li , Yingzhuo Deng , Wen Yang , Jiajun Zhang , Chengqing Zong

This paper describes our winning entry in the ImageCLEF 2015 image sentence generation task. We improve Google's CNN-LSTM model by introducing concept-based sentence reranking, a data-driven approach which exploits the large amounts of…

Computer Vision and Pattern Recognition · Computer Science 2016-05-04 Xirong Li , Qin Jin

Vision-Language Models (VLMs) leverage aligned visual encoders to transform images into visual tokens, allowing them to be processed similarly to text by the backbone large language model (LLM). This unified input paradigm enables VLMs to…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Bangzheng Li , Fei Wang , Wenxuan Zhou , Nan Xu , Ben Zhou , Sheng Zhang , Hoifung Poon , Muhao Chen

Visual token pruning is a widely used strategy for efficient inference in multimodal large language models (MLLMs), but existing work mainly evaluates it with task accuracy. In this paper, we study how visual token pruning affects model…

Computer Vision and Pattern Recognition · Computer Science 2026-04-15 Kaizhen Tan

Vision-Language Models (VLMs) are powerful tools for processing and understanding text and images. We study the processing of visual tokens in the language model component of LLaVA, a prominent VLM. Our approach focuses on analyzing the…

Computer Vision and Pattern Recognition · Computer Science 2025-04-29 Clement Neo , Luke Ong , Philip Torr , Mor Geva , David Krueger , Fazl Barez

Large vision-language models (LVLMs) achieve impressive performance on multimodal tasks but often suffer from hallucination, and confidently describe objects or attributes not present in the image. Current training-free interventions…

Computer Vision and Pattern Recognition · Computer Science 2026-04-13 Mehrdad Fazli , Bowen Wei , Ahmet Sari , Ziwei Zhu

While advanced image captioning systems are increasingly describing images coherently and exactly, recent progress in continual learning allows deep learning models to avoid catastrophic forgetting. However, the domain where image…

Computer Vision and Pattern Recognition · Computer Science 2020-04-22 Giang Nguyen , Tae Joon Jun , Trung Tran , Tolcha Yalew , Daeyoung Kim

Vision language (VL) models like CLIP are robust to natural distribution shifts, in part because CLIP learns on unstructured data using a technique called caption supervision; the model inteprets image-linked texts as ground-truth labels.…

Computer Vision and Pattern Recognition · Computer Science 2022-12-09 Benjamin Feuer , Ameya Joshi , Chinmay Hegde

In this work, we study the problem of word-level confidence calibration for scene-text recognition (STR). Although the topic of confidence calibration has been an active research area for the last several decades, the case of structured and…

Computer Vision and Pattern Recognition · Computer Science 2020-12-24 Ron Slossberg , Oron Anschel , Amir Markovitz , Ron Litman , Aviad Aberdam , Shahar Tsiper , Shai Mazor , Jon Wu , R. Manmatha

Uncertainty quantification is essential for assessing the reliability and trustworthiness of modern AI systems. Among existing approaches, verbalized uncertainty, where models express their confidence through natural language, has emerged…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Weihao Xuan , Qingcheng Zeng , Heli Qi , Junjue Wang , Naoto Yokoya