Cross-Modal Hybrid Feature Fusion for Image-Sentence Matching

计算机科学 人工智能 判决 特征(语言学) 相似性(几何) 模态(人机交互) 匹配(统计) 模式识别(心理学) 自然语言处理 图像(数学) 排名(信息检索) 情态动词 特征向量 数学 语言学 统计 哲学 化学 高分子化学
作者
Xing Xu,Yifan Wang,Yixuan He,Yang Yang,Alan Hanjalić,Heng Tao Shen
出处
期刊:ACM Transactions on Multimedia Computing, Communications, and Applications [Association for Computing Machinery]
卷期号:17 (4): 1-23 被引量:23
标识
DOI:10.1145/3458281
摘要

Image-sentence matching is a challenging task in the field of language and vision, which aims at measuring the similarities between images and sentence descriptions. Most existing methods independently map the global features of images and sentences into a common space to calculate the image-sentence similarity. However, the image-sentence similarity obtained by these methods may be coarse as (1) an intermediate common space is introduced to implicitly match the heterogeneous features of images and sentences in a global level, and (2) only the inter-modality relations of images and sentences are captured while the intra-modality relations are ignored. To overcome the limitations, we propose a novel Cross-Modal Hybrid Feature Fusion (CMHF) framework for directly learning the image-sentence similarity by fusing multimodal features with inter- and intra-modality relations incorporated. It can robustly capture the high-level interactions between visual regions in images and words in sentences, where flexible attention mechanisms are utilized to generate effective attention flows within and across the modalities of images and sentences. A structured objective with ranking loss constraint is formed in CMHF to learn the image-sentence similarity based on the fused fine-grained features of different modalities bypassing the usage of intermediate common space. Extensive experiments and comprehensive analysis performed on two widely used datasets—Microsoft COCO and Flickr30K—show the effectiveness of the hybrid feature fusion framework in CMHF, in which the state-of-the-art matching performance is achieved by our proposed CMHF method.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
大卫在分享应助晚风采纳,获得10
刚刚
搜集达人应助人类之光采纳,获得10
刚刚
刚刚
汪哈七发布了新的文献求助10
1秒前
小田心发布了新的文献求助10
1秒前
阿巴阿巴完成签到,获得积分20
1秒前
温磊关注了科研通微信公众号
1秒前
1秒前
天天快乐应助WHT采纳,获得30
2秒前
2秒前
pbc完成签到,获得积分10
3秒前
萧水白应助跳跃奇迹采纳,获得10
4秒前
5秒前
5秒前
6秒前
yymm完成签到,获得积分10
7秒前
友好驳完成签到,获得积分10
8秒前
汉堡包应助techteam采纳,获得10
8秒前
张腾雕发布了新的文献求助10
8秒前
9秒前
10秒前
10秒前
张宇宁完成签到,获得积分10
10秒前
lw完成签到,获得积分10
10秒前
wanci应助辛涩采纳,获得10
12秒前
12秒前
子车茗应助孙玉采纳,获得10
13秒前
岁月静好发布了新的文献求助10
14秒前
14秒前
沈星燃发布了新的文献求助10
15秒前
友好驳发布了新的文献求助10
16秒前
CodeCraft应助科研通管家采纳,获得10
16秒前
在水一方应助科研通管家采纳,获得10
16秒前
16秒前
ding应助科研通管家采纳,获得10
16秒前
科研通AI2S应助科研通管家采纳,获得10
17秒前
Orange应助科研通管家采纳,获得10
17秒前
17秒前
17秒前
17秒前
高分求助中
Sustainability in Tides Chemistry 2800
The Young builders of New china : the visit of the delegation of the WFDY to the Chinese People's Republic 1000
юрские динозавры восточного забайкалья 800
English Wealden Fossils 700
Foreign Policy of the French Second Empire: A Bibliography 500
Chen Hansheng: China’s Last Romantic Revolutionary 500
Classics in Total Synthesis IV 400
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3145912
求助须知:如何正确求助?哪些是违规求助? 2797359
关于积分的说明 7823805
捐赠科研通 2453697
什么是DOI,文献DOI怎么找? 1305818
科研通“疑难数据库(出版商)”最低求助积分说明 627574
版权声明 601491