English
Related papers

Related papers: Don't Learn, Ground: A Case for Natural Language I…

200 papers

Visual grounding (VG) aims to establish fine-grained alignment between vision and language. Ideally, it can be a testbed for vision-and-language models to evaluate their understanding of the images and texts and their reasoning abilities…

Computer Vision and Pattern Recognition · Computer Science 2023-07-24 Zhihong Chen , Ruifei Zhang , Yibing Song , Xiang Wan , Guanbin Li

Stimulated by the sophisticated reasoning capabilities of recent Large Language Models (LLMs), a variety of strategies for bridging video modality have been devised. A prominent strategy involves Video Language Models (VideoLMs), which…

Computer Vision and Pattern Recognition · Computer Science 2024-03-28 Wonkyun Kim , Changin Choi , Wonseok Lee , Wonjong Rhee

Recent generalist vision-language models (VLMs) have demonstrated impressive reasoning capabilities across diverse multimodal tasks. However, these models still struggle with fine-grained object-level understanding and grounding. In terms…

Computer Vision and Pattern Recognition · Computer Science 2024-06-04 Timothy Ossowski , Junjie Hu

We propose LENS, a modular approach for tackling computer vision problems by leveraging the power of large language models (LLMs). Our system uses a language model to reason over outputs from a set of independent and highly descriptive…

Computation and Language · Computer Science 2023-06-29 William Berrios , Gautam Mittal , Tristan Thrush , Douwe Kiela , Amanpreet Singh

Effectively understanding urban scenes requires fine-grained spatial reasoning about objects, layouts, and depth cues. However, how well current vision-language models (VLMs), pretrained on general scenes, transfer these abilities to urban…

Computer Vision and Pattern Recognition · Computer Science 2025-09-01 Juneyoung Ro , Namwoo Kim , Yoonjin Yoon

One-shot imitation is to learn a new task from a single demonstration, yet it is a challenging problem to adopt it for complex tasks with the high domain diversity inherent in a non-stationary environment. To tackle the problem, we explore…

Artificial Intelligence · Computer Science 2024-02-14 Sangwoo Shin , Daehee Lee , Minjong Yoo , Woo Kyung Kim , Honguk Woo

Understanding videos to localize moments with natural language often requires large expensive annotated video regions paired with language queries. To eliminate the annotation costs, we make a first attempt to train a natural language video…

Computation and Language · Computer Science 2021-10-04 Jinwoo Nam , Daechul Ahn , Dongyeop Kang , Seong Jong Ha , Jonghyun Choi

In this paper, we propose the first model to be able to generate visually grounded questions with diverse types for a single image. Visual question generation is an emerging topic which aims to ask questions in natural language based on…

Computer Vision and Pattern Recognition · Computer Science 2017-05-30 Shijie Zhang , Lizhen Qu , Shaodi You , Zhenglu Yang , Jiawan Zhang

This report presents a solution for the zero-shot referring expression comprehension task. Visual-language multimodal base models (such as CLIP, SAM) have gained significant attention in recent years as a cornerstone of mainstream research.…

Computer Vision and Pattern Recognition · Computer Science 2024-07-09 Longfei Huang , Feng Yu , Zhihao Guan , Zhonghua Wan , Yang Yang

In the field of multimodal chain-of-thought (CoT) reasoning, existing approaches predominantly rely on reasoning on pure language space, which inherently suffers from language bias and is largely confined to math or science domains. This…

Computer Vision and Pattern Recognition · Computer Science 2026-05-04 Jiacong Wang , Zijian Kang , Haochen Wang , Haiyong Jiang , Jiawen Li , Bohong Wu , Ya Wang , Jiao Ran , Xiao Liang , Chao Feng , Jun Xiao

Sample efficiency and systematic generalization are two long-standing challenges in reinforcement learning. Previous studies have shown that involving natural language along with other observation modalities can improve generalization and…

Natural Language Inference (NLI) models are known to learn from biases and artefacts within their training data, impacting how well they generalise to other unseen datasets. Existing de-biasing approaches focus on preventing the models from…

Computation and Language · Computer Science 2022-05-03 Joe Stacey , Yonatan Belinkov , Marek Rei

Images can give us insights into the contextual meanings of words, but current image-text grounding approaches require detailed annotations. Such granular annotation is rare, expensive, and unavailable in most domain-specific contexts. In…

Computation and Language · Computer Science 2020-11-02 Gregory Yauney , Jack Hessel , David Mimno

Instruction-based image editing (IIE) models have recently demonstrated strong capability in modifying specific image regions according to natural language instructions, which implicitly requires identifying where an edit should be applied.…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Jingxuan He , Xiyu Wang , Yunke Wang , Mengyu Zheng , Chang Xu

Key to tasks that require reasoning about natural language in visual contexts is grounding words and phrases to image regions. However, observing this grounding in contemporary models is complex, even if it is generally expected to take…

Computation and Language · Computer Science 2024-06-03 Noriyuki Kojima , Hadar Averbuch-Elor , Yoav Artzi

Vision-Language multimodal Models (VLMs) offer the possibility for zero-shot classification in astronomy: i.e. classification via natural language prompts, with no training. We investigate two models, GPT-4o and LLaVA-NeXT, for zero-shot…

Instrumentation and Methods for Astrophysics · Physics 2024-06-26 Dimitrios Tanoglidis , Bhuvnesh Jain

Current vision-language detection and grounding models predominantly focus on prompts with positive semantics and often struggle to accurately interpret and ground complex expressions containing negative semantics. A key reason for this…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Zesheng Yang , Xi Jiang , Bingzhang Hu , Weili Guan , Runmin Cong , Guo-Jun Qi , Feng Zheng

Pretrained language models are long known to be subpar in capturing sentence and document-level semantics. Though heavily investigated, transferring perturbation-based methods from unsupervised visual representation learning to NLP remains…

Computation and Language · Computer Science 2024-02-14 Chenghao Xiao , Zhuoxu Huang , Danlu Chen , G Thomas Hudson , Yizhi Li , Haoran Duan , Chenghua Lin , Jie Fu , Jungong Han , Noura Al Moubayed

In vision-and-language grounding problems, fine-grained representations of the image are considered to be of paramount importance. Most of the current systems incorporate visual features and textual concepts as a sketch of an image.…

Computation and Language · Computer Science 2019-11-05 Fenglin Liu , Yuanxin Liu , Xuancheng Ren , Xiaodong He , Xu Sun

Referring expression grounding aims at locating certain objects or persons in an image with a referring expression, where the key challenge is to comprehend and align various types of information from visual and textual domain, such as…

Computer Vision and Pattern Recognition · Computer Science 2019-04-03 Xihui Liu , Zihao Wang , Jing Shao , Xiaogang Wang , Hongsheng Li