中文
相关论文

相关论文: Is An Image Worth Five Sentences? A New Look into …

200 篇论文

Image-sentence retrieval has attracted extensive research attention in multimedia and computer vision due to its promising application. The key issue lies in jointly learning the visual and textual representation to accurately estimate…

计算机视觉与模式识别 · 计算机科学 2022-10-18 Xuri Ge , Fuhai Chen , Songpei Xu , Fuxiang Tao , Joemon M. Jose

Image captioning has attracted ever-increasing research attention in the multimedia community. To this end, most cutting-edge works rely on an encoder-decoder framework with attention mechanisms, which have achieved remarkable progress.…

计算机视觉与模式识别 · 计算机科学 2019-09-04 Chen Shen , Rongrong Ji , Fuhai Chen , Xiaoshuai Sun , Xiangming Li

Image captioning models are typically trained by treating all samples equally, neglecting to account for mismatched or otherwise difficult data points. In contrast, recent work has shown the effectiveness of training models by scheduling…

计算机视觉与模式识别 · 计算机科学 2024-02-05 Wenyan Li , Jonas F. Lotz , Chen Qiu , Desmond Elliott

As a scene graph compactly summarizes the high-level content of an image in a structured and symbolic manner, the similarity between scene graphs of two images reflects the relevance of their contents. Based on this idea, we propose a novel…

计算机视觉与模式识别 · 计算机科学 2021-01-01 Sangwoong Yoon , Woo Young Kang , Sungwook Jeon , SeongEun Lee , Changjin Han , Jonghun Park , Eun-Sol Kim

Semantic communication, as a revolutionary communication architecture, is considered a promising novel communication paradigm. Unlike traditional symbol-based error-free communication systems, semantic-based visual communication systems…

计算机视觉与模式识别 · 计算机科学 2024-07-11 Senran Fan , Zhicheng Bao , Chen Dong , Haotai Liang , Xiaodong Xu , Ping Zhang

Attention mechanisms have recently been introduced in deep learning for various tasks in natural language processing and computer vision. But despite their popularity, the "correctness" of the implicitly-learned attention maps has only been…

计算机视觉与模式识别 · 计算机科学 2016-11-24 Chenxi Liu , Junhua Mao , Fei Sha , Alan Yuille

Current image captioning methods are usually trained via (penalized) maximum likelihood estimation. However, the log-likelihood score of a caption does not correlate well with human assessments of quality. Standard syntactic evaluation…

计算机视觉与模式识别 · 计算机科学 2018-03-14 Siqi Liu , Zhenhai Zhu , Ning Ye , Sergio Guadarrama , Kevin Murphy

Multimodal sentence embedding models typically leverage image-caption pairs in addition to textual data during training. However, such pairs often contain noise, including redundant or irrelevant information on either the image or caption…

计算与语言 · 计算机科学 2025-08-04 Kaiyan Zhao , Zhongtao Miao , Yoshimasa Tsuruoka

Semantic correspondence methods have advanced to obtaining high-quality correspondences employing complicated networks, aiming to maximize the model capacity. However, despite the performance improvements, they may remain constrained by the…

计算机视觉与模式识别 · 计算机科学 2024-10-14 Jiwon Kim , Byeongho Heo , Sangdoo Yun , Seungryong Kim , Dongyoon Han

Attribute-based person search is the task of finding person images that are best matched with a set of text attributes given as query. The main challenge of this task is the large modality gap between attributes and images. To reduce the…

计算机视觉与模式识别 · 计算机科学 2021-08-12 Boseung Jeong , Jicheol Park , Suha Kwak

Social media is daily creating massive multimedia content with paired image and text, presenting the pressing need to automate the vision and language understanding for various multimodal classification tasks. Compared to the commonly…

计算与语言 · 计算机科学 2023-03-28 Chunpu Xu , Jing Li

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…

计算机视觉与模式识别 · 计算机科学 2016-05-04 Xirong Li , Qin Jin

We have benchmarked the maximum obtainable recognition accuracy on various word image datasets using manual segmentation and a currently available commercial OCR. We have developed a Matlab program, with graphical user interface, for…

计算机视觉与模式识别 · 计算机科学 2012-08-31 Deepak Kumar , M N Anil Prasad , A G Ramakrishnan

Recent progress on automatic generation of image captions has shown that it is possible to describe the most salient information conveyed by images with accurate and meaningful sentences. In this paper, we propose an image caption system…

计算机视觉与模式识别 · 计算机科学 2015-06-23 Junqi Jin , Kun Fu , Runpeng Cui , Fei Sha , Changshui Zhang

Remote sensing change captioning (RSICC) aims to describe changes between bitemporal images in natural language. Existing methods often fail under challenges like illumination differences, viewpoint changes, blur effects, leading to…

计算机视觉与模式识别 · 计算机科学 2025-08-26 Ali Can Karaca , M. Enes Ozelbas , Saadettin Berber , Orkhan Karimli , Turabi Yildirim , M. Fatih Amasyali

There is an increasing requirement for efficient image retargeting techniques to adapt the content to various forms of digital media. With rapid growth of mobile communications and dynamic web page layouts, one often needs to resize the…

图形学 · 计算机科学 2015-08-14 Sukrit Shankar , Pier Luigi Dragotti

We propose an end-to-end model which generates captions for images embedded in news articles. News images present two key challenges: they rely on real-world knowledge, especially about named entities; and they typically have linguistically…

计算机视觉与模式识别 · 计算机科学 2020-06-16 Alasdair Tran , Alexander Mathews , Lexing Xie

Sequence-to-sequence models have shown promising improvements on the temporal task of video captioning, but they optimize word-level cross-entropy loss during training. First, using policy gradient and mixed-loss methods for reinforcement…

计算与语言 · 计算机科学 2017-08-09 Ramakanth Pasunuru , Mohit Bansal

High-quality data is necessary for modern machine learning. However, the acquisition of such data is difficult due to noisy and ambiguous annotations of humans. The aggregation of such annotations to determine the label of an image leads to…

Providing systems the ability to relate linguistic and visual content is one of the hallmarks of computer vision. Tasks such as text-based image retrieval and image captioning were designed to test this ability but come with evaluation…

计算机视觉与模式识别 · 计算机科学 2019-04-08 Hexiang Hu , Ishan Misra , Laurens van der Maaten