MAPNet: Multi-modal attentive pooling network for RGB-D indoor scene classification | |
Li, Yabei1,2,3; Zhang, Zhang1,2,3; Cheng, Yanhua4; Wang, Liang1,2,3,5; Tan, Tieniu1,2,3,5 | |
发表期刊 | PATTERN RECOGNITION |
ISSN | 0031-3203 |
2019-06-01 | |
期号 | 90页码:436-449 |
摘要 | RGB-D indoor scene classification is an essential and challenging task. Although convolutional neural network (CNN) achieves excellent results on RGB-D object recognition, it has several limitations when extended towards RGB-D indoor scene classification. 1) The semantic cues such as objects of the indoor scene have high spatial variabilities. The spatially rigid global representation from CNN is suboptimal. 2) The cluttered indoor scene has lots of redundant and noisy semantic cues; thus discerning discriminative information among them should not be ignored. 3) Directly concatenating or summing global RGB and Depth information as presented in popular methods cannot fully exploit the complementarity between two modalities for complicated indoor scenarios. To address the above problems, we propose a novel unified framework named Multi-modal Attentive Pooling Network (MAPNet) in this paper. Two orderless attentive pooling blocks are constructed in MAPNet to aggregate semantic cues within and between modalities meanwhile maintain the spatial invariance. The Intra-modality Attentive Pooling (IAP) block aims to mine and pool discriminative semantic cues in each modality. The Cross-modality Attentive Pooling (CAP) block is extended to learn different contributions across two modalities, which further guides the pooling of the selected discriminative semantic cues of each modality. We further show that the proposed model is interpretable, which helps to understand mechanisms of both scene classification and multi-modal fusion in MAPNet. Extensive experiments and analysis on SUN RGB-D Dataset and NYU Depth Dataset V2 show the superiority of MAPNet over current state-of-the-art methods. (C) 2019 Elsevier Ltd. All rights reserved. |
关键词 | Indoor scene classification Multi-modal fusion RGB-D Attentive pooling |
DOI | 10.1016/j.patcog.2019.02.005 |
关键词[WOS] | IMAGE FEATURES |
收录类别 | SCI |
语种 | 英语 |
WOS研究方向 | Computer Science ; Engineering |
WOS类目 | Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:000463130400036 |
出版者 | ELSEVIER SCI LTD |
七大方向——子方向分类 | 多模态智能 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/23478 |
专题 | 智能感知与计算研究中心 |
通讯作者 | Zhang, Zhang |
作者单位 | 1.CASIA, CRIPAC, Beijing, Peoples R China 2.CASIA, NLPR, Beijing, Peoples R China 3.Univ Chinese Acad Sci, Beijing, Peoples R China 4.Tencent WeChat AI, Beijing, Peoples R China 5.CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing, Peoples R China |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Li, Yabei,Zhang, Zhang,Cheng, Yanhua,et al. MAPNet: Multi-modal attentive pooling network for RGB-D indoor scene classification[J]. PATTERN RECOGNITION,2019(90):436-449. |
APA | Li, Yabei,Zhang, Zhang,Cheng, Yanhua,Wang, Liang,&Tan, Tieniu.(2019).MAPNet: Multi-modal attentive pooling network for RGB-D indoor scene classification.PATTERN RECOGNITION(90),436-449. |
MLA | Li, Yabei,et al."MAPNet: Multi-modal attentive pooling network for RGB-D indoor scene classification".PATTERN RECOGNITION .90(2019):436-449. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
1-s2.0-S003132031930(5797KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论