English
Related papers

Related papers: Dense and Aligned Captions (DAC) Promote Compositi…

200 papers

Visual inputs are often assumed to improve language understanding in multimodal models. We examine this assumption by asking whether vision-language models (VLMs) can distinguish useful visual evidence from incidental image context in…

Computation and Language · Computer Science 2026-05-27 Yifan Jiang , Ruoxi Ning , Sheng Yao , Freda Shi

Compositional generalization, the ability to reason about novel combinations of familiar concepts, is fundamental to human cognition and a critical challenge for machine learning. Object-centric (OC) representations, which encode a scene as…

Computer Vision and Pattern Recognition · Computer Science 2026-02-19 Ferdinand Kapl , Amir Mohammad Karimi Mamaghan , Maximilian Seitzer , Karl Henrik Johansson , Carsten Marr , Stefan Bauer , Andrea Dittadi

Contrastive Language-Image Pre-training (CLIP)~\citep{radford2021learning} has emerged as a pivotal model in computer vision and multimodal learning, achieving state-of-the-art performance at aligning visual and textual representations…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Shaoan Xie , Lingjing Kong , Yujia Zheng , Yu Yao , Zeyu Tang , Eric P. Xing , Guangyi Chen , Kun Zhang

We investigate compositional structures in data embeddings from pre-trained vision-language models (VLMs). Traditionally, compositionality has been associated with algebraic operations on embeddings of words from a pre-existing vocabulary.…

Machine Learning · Computer Science 2024-01-12 Matthew Trager , Pramuditha Perera , Luca Zancato , Alessandro Achille , Parminder Bhatia , Stefano Soatto

Recent advances in vision language models (VLM) have been driven by contrastive models such as CLIP, which learn to associate visual information with their corresponding text descriptions. However, these models have limitations in…

Computer Vision and Pattern Recognition · Computer Science 2025-02-21 Rim Assouel , Pietro Astolfi , Florian Bordes , Michal Drozdzal , Adriana Romero-Soriano

Vision-language models (VLMs) allow to embed texts and images in a shared representation space. However, it has been shown that these models are subject to a modality gap phenomenon meaning there exists a clear separation between the…

Computer Vision and Pattern Recognition · Computer Science 2025-05-07 François Role , Sébastien Meyer , Victor Amblard

Compositional reasoning is a hallmark of human visual intelligence. Yet, despite the size of large vision-language models, they struggle to represent simple compositions by combining objects with their attributes. To measure this lack of…

Computer Vision and Pattern Recognition · Computer Science 2023-11-06 Arijit Ray , Filip Radenovic , Abhimanyu Dubey , Bryan A. Plummer , Ranjay Krishna , Kate Saenko

Recent advances in vision-language models (VLMs) have greatly improved cross-modal semantic understanding, yet significant limitations remain in fine-grained discrimination and deep causal reasoning tasks. Existing VLMs often rely on…

Machine Learning · Computer Science 2025-06-24 Jusheng Zhang , Kaitong Cai , Yijia Fan , Jian Wang , Keze Wang

Video captioning is a critical task in the field of multimodal machine learning, aiming to generate descriptive and coherent textual narratives for video content. While large vision-language models (LVLMs) have shown significant progress,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Ji-jun Park , Soo-joon Choi

How well can Multimodal Large Language Models (MLLMs) understand composite images? Composite images (CIs) are synthetic visuals created by merging multiple visual elements, such as charts, posters, or screenshots, rather than being captured…

Computer Vision and Pattern Recognition · Computer Science 2024-12-09 Xiaohui Chen , Satya Narayan Shukla , Mahmoud Azab , Aashu Singh , Qifan Wang , David Yang , ShengYun Peng , Hanchao Yu , Shen Yan , Xuewen Zhang , Baosheng He

Vision-language models (VLMs) achieve strong performance on spatial reasoning benchmarks, yet it remains unclear whether this reflects structured 3D understanding or reliance on statistical shortcuts in natural images. We introduce a…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Cheolhong Min , Jaeyun Jung , Daeun Lee , Hyeonseong Jeon , Yu Su , Jonathan Tremblay , Chan Hee Song , Jaesik Park

Open-vocabulary vision-language models (VLMs) like CLIP, trained using contrastive loss, have emerged as a promising new paradigm for text-to-image retrieval. However, do VLMs understand compound nouns (CNs) (e.g., lab coat) as well as they…

Computer Vision and Pattern Recognition · Computer Science 2024-04-02 Sonal Kumar , Sreyan Ghosh , S Sakshi , Utkarsh Tyagi , Dinesh Manocha

Multimodal large language models (MLLMs) can process text presented as images, yet they often perform worse than when the same content is provided as textual tokens. We systematically diagnose this "modality gap" by evaluating seven MLLMs…

Computation and Language · Computer Science 2026-05-26 Kaiser Sun , Xiaochuang Yuan , Hongjun Liu , Chen Zhao , Cheng Zhang , Mark Dredze , Fan Bai

Audio-visual captioning aims to generate holistic scene descriptions by jointly modeling sound and vision. While recent methods have improved performance through sophisticated modality fusion, it remains unclear to what extent the two…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-29 Yuchi Ishikawa , Toranosuke Manabe , Tatsuya Komatsu , Yoshimitsu Aoki

The advent of large Vision-Language Models (VLMs) has significantly advanced multimodal understanding, enabling more sophisticated and accurate integration of visual and textual information across various tasks, including image and video…

Computer Vision and Pattern Recognition · Computer Science 2024-10-15 Hang Hua , Yunlong Tang , Ziyun Zeng , Liangliang Cao , Zhengyuan Yang , Hangfeng He , Chenliang Xu , Jiebo Luo

A key solution to visual question answering (VQA) exists in how to fuse visual and language features extracted from an input image and question. We show that an attention mechanism that enables dense, bi-directional interactions between the…

Computer Vision and Pattern Recognition · Computer Science 2018-12-04 Duy-Kien Nguyen , Takayuki Okatani

Image captioning is a fundamental task that bridges the visual and linguistic domains, playing a critical role in pre-training Large Vision-Language Models (LVLMs). Current state-of-the-art captioning models are typically trained with…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Long Xing , Xiaoyi Dong , Yuhang Zang , Yuhang Cao , Jianze Liang , Qidong Huang , Jiaqi Wang , Feng Wu , Dahua Lin

Compositional visual reasoning has emerged as a key research frontier in multimodal AI, aiming to endow machines with the human-like ability to decompose visual scenes, ground intermediate concepts, and perform multi-step logical inference.…

Computer Vision and Pattern Recognition · Computer Science 2025-08-28 Fucai Ke , Joy Hsu , Zhixi Cai , Zixian Ma , Xin Zheng , Xindi Wu , Sukai Huang , Weiqing Wang , Pari Delir Haghighi , Gholamreza Haffari , Ranjay Krishna , Jiajun Wu , Hamid Rezatofighi

Evaluations of image compression performance which include human preferences have generally found that naive distortion functions such as MSE are insufficiently aligned to human perception. In order to align compression models to human…

Computer Vision and Pattern Recognition · Computer Science 2025-12-18 Kyle Sargent , Ruiqi Gao , Philipp Henzler , Charles Herrmann , Aleksander Holynski , Li Fei-Fei , Jiajun Wu , Jason Zhang

Existing open-vocabulary object detection (OVD) develops methods for testing unseen categories by aligning object region embeddings with corresponding VLM features. A recent study leverages the idea that VLMs implicitly learn compositional…

Computer Vision and Pattern Recognition · Computer Science 2024-12-25 Hojun Choi , Junsuk Choe , Hyunjung Shim