NDLI: Multimodal object description network for dense captioning

Content Provider	IET Digital Library
Author	Wang, Weixuan Hu, Haifeng
Abstract	A new multimodal object description network (MODN) model for dense captioning is proposed. The proposed model is constructed by using a vision module and a language module. As for vision module, the modified faster regions-convolution neural network (R-CNN) is used to detect the salient objects and extract their inherited features. The language module combines the semantics features with the object features obtained from the vision module and calculate the probability distribution of each word in the sentence. Compared with existing methods, a multimodal layer in the proposed MODN framework is adopted which can effectively extract discriminant information from both object and semantic features. Moreover, MODN can generate object description rapidly without external region proposal. The effectiveness of MODN on the famous VOC2007 dataset and Visual Genome dataset is verified.
Starting Page	1041
Ending Page	1042
Page Count	2
ISSN	00135194
Volume Number	53
e-ISSN	1350911X
Issue Number	Issue 15, Jul (2017)
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/el/53/15
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/10.1049/el.2017.0326
Journal	Electronics Letters
Publisher Date	2017-06-26
Access Restriction	Open
Rights Holder	© The Institution of Engineering and Technology
Subject Keyword	Computer Vision Computer Vision And Image Processing Technique Dense Captioning Discriminant Information Extraction Feature Extraction Image Recognition Language Module MODN Model Multimodal Layer Multimodal Object Description Network Object Detection Object Feature Probability Distribution R-CNN Salient Object Detection Semantics Feature Spatial And Pictorial Database Statistical Distribution Statistics Vision Module Visual Database Visual Genome Dataset VOC2007 Dataset
Content Type	Text
Resource Type	Article
Subject	Electrical and Electronic Engineering

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Data-driven image captioning via salient region discovery

End-to-end visual grounding via region proposal networks and bilinear pooling

Multi-scale deep neural network for salient object detection

Contextual Action Recognition with R*CNN

Single-shot detector with enriched semantics for PCB tiny defect detection

Object detection based on RGC mask R-CNN

An Empirical Study of Visual Features for Part Based Model

Multi-scale object detection by bottom-up feature pyramid network

Deep convolution network for dense crowd counting

Multimodal object description network for dense captioning

Similar Documents

Data-driven image captioning via salient region discovery

End-to-end visual grounding via region proposal networks and bilinear pooling

Multi-scale deep neural network for salient object detection

Contextual Action Recognition with R*CNN

Single-shot detector with enriched semantics for PCB tiny defect detection

Object detection based on RGC mask R-CNN

An Empirical Study of Visual Features for Part Based Model

Multi-scale object detection by bottom-up feature pyramid network

Deep convolution network for dense crowd counting

Multimodal object description network for dense captioning