NDLI: Multimodal tag localization based on deep learning

Please wait, while we are loading the content...

A Fourier theory of the light field with the resolution of the sampling camera

Discriminative voting for activity prediction

Vehicle detection and classification based on convolutional neural network

Exposure fusion based on sparse coding in pyramid transform domain

The AdaBoost algorithm for vehicle detection based on CNN features

Dual-mode video stabilization based on adaptive motion clustering

Image deconvolution using $ℓ^{1}$ sparse regularization

Exploiting the locality information of dense trajectory feature for human action recognition

Concurrent group activity classification with context modeling

Multi-layer supervised dictionary learning for visual classification

Information diffusion model based on k-core for social networks

Automatic image annotation based on fuzzy association rule and decision tree

Feature fusion for 3D model retrieval based on fuzzy clustering

Person re-identification fusing via ranking consensus

Semi-supervised learning via nonnegative least squares regression

A discriminative classifier for in-air handwritten Chinese characters recognition

Sparse canonical correlation analysis for recognition

Evaluation on fusion of saliency and objectness for salient object segmentation

A new single image dehazing method with MSRCR algorithm

Flickr group recommendation via heterogeneous information networks

A general method for sensitive identification detection in the terrorist video

Online shared dictionary learning for visual tracking

Person re-identification by the marriage of KISS metric learning and post-rank optimization: KISSPOP

Deep sparse coding network for image classification

Accurate non-rigid registration of point set with large deformation via heuristic tree

A semi-supervised clustering ensemble approach integrated constraint-based and metric-based

Visual saliency based automatic road extraction from high-resolution multispectral satellite images

Sparse principle motion component for one-shot gesture recognition

Boost sparse coding based abnormal event detection via explicitly applying temporal continuity constraint

Improved structured sparse PCA for cluster-based co-saliency detection

Manifold learning in sparse selected feature subspaces

A pedestrian and vehicle rapid identification model based on convolutional neural network

Hyperspectral image compression based on DLWT and PCA

A patch-based affinity measurement method for online multiple pedestrian tracking

Real-time high resolution 2D-plus-depth video generation using time-of-flight sensor

A novel video dehazing method based on temporal visual coherence

Why does the sketch look so vivid?

Method of switching video track using composition information over MMT

An improved approach of lung image segmentation based on watershed algorithm

Centroid location algorithm in three dimensions based on big data

Spatial grouping coding for three-dimensional multichannel audio system

Visual saliency detection based on gradient contrast and color complexity

Joint-based multi-task sparse learning for human action recognition

Human action recognition based on dense of spatio-temporal interest points and HOG-3D descriptor

Game suspension boundary detection by reading two clocks for broadcast basketball video

Color image segmentation based on a modified k-means algorithm

What makes the stego image undetectable?

An automatic detection and segmentation algorithm of video multiple moving targets for computer vision

Combining RGB and depth features for action recognition based on sparse representation

Multimodal tag localization based on deep learning

Improving bag-of-words representation with efficient twin feature integration

Timestamp removal for panorama video surveillance

A fast pedestrians counting method based on haar features and spatio-temporal correlation analysis

Parallel surface reconstruction on GPU

Combination of region and contour models for interactive image segmentation

Review on underwater image restoration and enhancement algorithms

Attack trajectory extraction based on focus player detection in broadcast sports videos

Photo linker: a system for finding your old photos based on fragmentary memories

Salient object detection in RGB-D image based on saliency fusion and propagation

A visual tracker based on improved kernel correlation filter

3-D models merging based on cost optimization

Exploring the influence of motion boundary sampling to improved dense trajectories for action recognition

Dimensionality reduction strategy based on auto-encoder

PVSS: portable visual search service for researchers

Scene character recognition using PCANet

Face recognition using nonlinear locality preserving with deep networks

Timbre identification of instrumental music via energy distribution modeling

Human head detection based on multi-stage CNN with voting strategy

A novel supporting structure generation scheme to 3D printing

A fine-grain nonlocal weighted average method for image CS reconstruction

Compressive imaging based on coefficients cutting in DLWT domain and approximate message passing

Saliency detection for RGBD images

Hand gesture recognition for a virtual mouse application using geometric feature of finger's trajectories

Lace fabric image retrieval based on multi-scale and rotation invariant LBP

Exploring the heterogeneity of social media: dataset and a pilot study

Image-regulated graph topic model for cross-media topic detection

Robust gender classification on unconstrained face images

60 Hz self-tuning background modeling

Using user generated online photos to estimate and monitor air pollution in major cities

Understanding-oriented visual representation learning

Beyond pixel: context defines everything in saliency

Social media distribution: a data-driven approach

Scalable local feature matching without visual codebook training

Heterogeneous data alignment for cross-media computing

Towards structured semantic embedding of multimedia

Efficient indexing for large-scale image search

Application-specific visual quality assessment: current status and future trends

Multimodal tag localization based on deep learning

Content Provider	ACM Digital Library
Author	Li, JinTao Liu, Wu Tang, Sheng Zhang, Rui
Abstract	Tag localization which localizes the relevant video clips for an associated semantic tag has become an important research topic in the field of video retrieval and recommendation. Most existing approaches adopt and depend in large degree on carefully selected features which are manually designed by experts and do not take into consideration of multimodality. In order to take into account complementarity of different modalities and take advantage of learned features, in this paper, we propose a multimodal tag localization framework by exploiting deep learning to learn both visual and textual features of videos for tag localization, followed by the multimodal fusion of both visual and textual results. Extensive experiments on the public dataset show that our proposed approach achieves promising results. The tag localization based on visual deep learning greatly improves the precision of tag localization, and the multi-modal fusion of both visual and textual modalities further improves the precision despite the low performances of single textual modality.
Starting Page	1
Ending Page	4
Page Count	4
File Format	PDF
ISBN	9781450335287
DOI	10.1145/2808492.2808542
Language	English
Publisher	Association for Computing Machinery (ACM)
Publisher Date	2015-08-19
Publisher Place	New York
Access Restriction	Subscribed
Subject Keyword	Deep learning Semantic tag localization Multi-modal fusion
Content Type	Text
Resource Type	Article

Central Library (ISO-9001:2015 Certified)
Indian Institute of Technology Kharagpur
Kharagpur, West Bengal, India | PIN - 721302

See location in the Map
03222 282435
Mail: support@ndl.gov.in

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