中文
相关论文

相关论文: Cross-aware Early Fusion with Stage-divided Vision…

200 篇论文

Vision Transformers can achieve high accuracy and strong generalization across various contexts, but their practical applicability on real-world robotic systems is limited due to their quadratic attention complexity. Recent works have…

计算机视觉与模式识别 · 计算机科学 2026-05-04 Fabio Montello , Ronja Güldenring , Lazaros Nalpantidis

Contemporary Vision-Language Models (VLMs) achieve strong performance on a wide range of tasks by pairing a vision encoder with a pre-trained language model, fine-tuned for visual-text inputs. Yet despite these gains, it remains unclear how…

计算机视觉与模式识别 · 计算机科学 2026-02-10 Lachin Naghashyar , Hunar Batra , Ashkan Khakzar , Philip Torr , Ronald Clark , Christian Schroeder de Witt , Constantin Venhoff

Vision-language pre-training (VLP) on large-scale image-text pairs has achieved huge success for the cross-modal downstream tasks. The most existing pre-training methods mainly adopt a two-step training procedure, which firstly employs a…

计算机视觉与模式识别 · 计算机科学 2021-06-07 Haiyang Xu , Ming Yan , Chenliang Li , Bin Bi , Songfang Huang , Wenming Xiao , Fei Huang

With the achievements of Transformer in the field of natural language processing, the encoder-decoder and the attention mechanism in Transformer have been applied to computer vision. Recently, in multiple tasks of computer vision (image…

计算机视觉与模式识别 · 计算机科学 2022-03-03 Rui-Yang Ju , Ting-Yu Lin , Jen-Shiun Chiang , Jia-Hao Jian , Yu-Shian Lin , Liu-Rui-Yi Huang

3D Visual Grounding (3DVG) aims to localize the referent of natural language referring expressions through two core tasks: Referring Expression Comprehension (3DREC) and Segmentation (3DRES). While existing methods achieve high accuracy in…

计算机视觉与模式识别 · 计算机科学 2026-03-19 Wenbin Tan , Jiawen Lin , Fangyong Wang , Yuan Xie , Yong Xie , Yachao Zhang , Yanyun Qu

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…

计算机视觉与模式识别 · 计算机科学 2019-04-03 Xihui Liu , Zihao Wang , Jing Shao , Xiaogang Wang , Hongsheng Li

Textual-visual matching aims at measuring similarities between sentence descriptions and images. Most existing methods tackle this problem without effectively utilizing identity-level annotations. In this paper, we propose an identity-aware…

计算机视觉与模式识别 · 计算机科学 2017-08-08 Shuang Li , Tong Xiao , Hongsheng Li , Wei Yang , Xiaogang Wang

Recent Large Vision Language Models (LVLMs) demonstrate promising capabilities in unifying visual understanding and generative modeling, enabling both accurate content understanding and flexible editing. However, current approaches treat…

计算机视觉与模式识别 · 计算机科学 2025-09-23 Fan Yang , Yousong Zhu , Xin Li , Yufei Zhan , Hongyin Zhao , Shurong Zheng , Yaowei Wang , Ming Tang , Jinqiao Wang

Multimodal visual information fusion aims to integrate the multi-sensor data into a single image which contains more complementary information and less redundant features. However the complementary information is hard to extract, especially…

计算机视觉与模式识别 · 计算机科学 2024-06-18 Hui Li , Xiao-Jun Wu

Humans possess a remarkable ability to integrate auditory and visual information, enabling a deeper understanding of the surrounding environment. This early fusion of audio and visual cues, demonstrated through cognitive psychology and…

计算机视觉与模式识别 · 计算机科学 2023-12-05 Shentong Mo , Pedro Morgado

Robot vision has greatly benefited from advancements in multimodal fusion techniques and vision-language models (VLMs). We adopt a task-oriented perspective to systematically review the applications and advancements of multimodal fusion…

The recently developed vision transformer (ViT) has achieved promising results on image classification compared to convolutional neural networks. Inspired by this, in this paper, we study how to learn multi-scale feature representations in…

计算机视觉与模式识别 · 计算机科学 2021-08-24 Chun-Fu Chen , Quanfu Fan , Rameswar Panda

Existing work in multilingual pretraining has demonstrated the potential of cross-lingual transferability by training a unified Transformer encoder for multiple languages. However, much of this work only relies on the shared vocabulary and…

计算与语言 · 计算机科学 2021-06-03 Fuli Luo , Wei Wang , Jiahao Liu , Yijia Liu , Bin Bi , Songfang Huang , Fei Huang , Luo Si

Medical vision-and-language pre-training (Med-VLP) has received considerable attention owing to its applicability to extracting generic vision-and-language representations from medical images and texts. Most existing methods mainly contain…

计算与语言 · 计算机科学 2022-09-16 Zhihong Chen , Guanbin Li , Xiang Wan

As bird's-eye-view (BEV) semantic segmentation is simple-to-visualize and easy-to-handle, it has been applied in autonomous driving to provide the surrounding information to downstream tasks. Inferring BEV semantic segmentation conditioned…

计算机视觉与模式识别 · 计算机科学 2023-08-21 Naiyu Fang , Lemiao Qiu , Shuyou Zhang , Zili Wang , Kerui Hu , Kang Wang

Pretrained vision-and-language BERTs aim to learn representations that combine information from both modalities. We propose a diagnostic method based on cross-modal input ablation to assess the extent to which these models actually…

计算与语言 · 计算机科学 2021-09-10 Stella Frank , Emanuele Bugliarello , Desmond Elliott

To bridge the gap between supervised semantic segmentation and real-world applications that acquires one model to recognize arbitrary new concepts, recent zero-shot segmentation attracts a lot of attention by exploring the relationships…

计算机视觉与模式识别 · 计算机科学 2022-11-01 Quande Liu , Youpeng Wen , Jianhua Han , Chunjing Xu , Hang Xu , Xiaodan Liang

Current pre-trained vison-language models (PVLMs) achieve excellent performance on a range of multi-modal datasets. Recent work has aimed at building multilingual models, and a range of novel multilingual multi-modal datasets have been…

计算与语言 · 计算机科学 2023-10-25 Hanxu Hu , Frank Keller

Modern retrieval systems often struggle with upgrading to new and more powerful models due to the incompatibility of embeddings between the old and new models. This necessitates a costly process known as backfilling, which involves…

计算机视觉与模式识别 · 计算机科学 2025-10-07 Young Kyun Jang , Ser-nam Lim

Open-vocabulary semantic segmentation attempts to classify and outline objects in an image using arbitrary text labels, including those unseen during training. Self-supervised learning resolves numerous visual and linguistic processing…

计算机视觉与模式识别 · 计算机科学 2025-07-03 Muhammad Atta ur Rahman , Dooseop Choi , Seung-Ik Lee , KyoungWook Min