NDLI: Image Classification via fusing the latent deep CNN feature

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

Direction based Graphical Model for Face Sketch Synthesis

Adaptively Weighted Graph Fusion for Image Retrieval

TSMV: Task-Specific Multi-View Feature Learning

Adaptive Metric Learning with the Low Rank Constraint

Fast Horizon Estimation via Deep Hashing

Image Classification via fusing the latent deep CNN feature

A depth recovery algorithm for using the maximum likelihood estimation

Recommending Followees Based on Content Weighted User Interest Homophily

Blind Watermarking Arithmetic for Color Image Based on Discrete Wavelet Transform

An adaptive virtual sample generation method for one sample problem in face recognition

Plane Geometry Diagram Retrieval By Using Hierarchical Searching Strategy

An Image Copy Move Forgery Detection Method Using QDCT

Discriminative-Element-Aware Sparse Representation for Action Recognition

Compressed Video Coding with Multi-Kernel Gaussian Process Regression

Algorithm of Attribute Reduction in Dominance Based Rough Sets Combined with Dominance Discernibility Matrix

GKSH: Graph based Image Retrieval using Supervised Kernel Hashing

Coupled Autoencoder Network with Joint Regularizations for image super-resolution

Towards Building Abstraction by Using Line Segment Descriptor

Comparison of Three Segmentation Techniques for Auroral Arc Detection

A Simple and Fast Method for Face Sketch Synthesis

A New Level Set Segmentation Based on Fuzzy Theory with Application on MRI and Infrared Images

Scene Adaptive Object Tracking Combining Local Feature and Color Feature

Novel Robust Audio Watermarking Scheme against Synchronization Attacks

Local Similarity based Linear Graph Embedding: A Robust Face Recognition Framework for SSPP problem

Multi-view dimensionality reduction via similarity or reconstruction

An Improvement of Affine Iterative Closest Point Algorithm for Partial Registration

Fast Video Deduplication via Locality Sensitive Hashing with Similarity Ranking

Deep Neural Network Boosted Large Scale Image Recognition Using User Click Data

A Novel algorithm for Planar Extracting of 3D Point Clouds

Multi-Pedestrian Detection from Effective Proposal in Crowd Scene

Creating Descriptive Visual Word Tree for Tag Ranking of Social Image

Extensive Comparison of Visual Features for Person Re-identification

Efficient Web Video Classification via Cross-modality Knowledge Transferring

Tree-guided Group Sparse based Representation for Person Re-identification

RGB-D Object Recognition from Hand-Held Object Teaching

Automatic Integrity Checking of IFC Models relative to building Regulations

SAR Image Change Detection method of MDS-SRM Based on Hybrid Cascade Merging

Multiple-Feature Kernel Hashing for Mass Detection

Continuous Vehicle Detection and Tracking for Non-overlapping Multi-camera Surveillance System

Recognition Oriented Facial Image Quality Assessment via Deep Convolutional Neural Network

Anchored Neighbor Embedding based Image Super-Resolution with Locality Constraints

Ringing Reduction in Image Restoration Using Cyclic Boundary

SimH: A Supervised Cross-View Hashing Framework Preserving Semantic Similarities in Hamming Space

Joint Coupled-Hashing Representation for Cross-Modal Retrieval

Deep People Counting with Faster R-CNN and Correlation Tracking

Evaluating Actors' Promotion Behaviors for TV Series on Social Networks

Image Search Reranking with Relevance, Diversity and Topic Coverage

A multi-label Hyperspectral image classification method with deep learning features

Dense Matching Based on Subspace Learning for Non-Rigid Object

Accurate Modified Normal Based ICP for 3D Mapping

Enhanced lung segmentation in chest CT images based on kernel graph cuts

Vessel Extraction by Graph Cut Method based on Centerline Estimation

Learning Low-Rank Representation with Block-Sparse Structure for Single Sample Face Recognition

Improve Visual Tracking by End-to-end Multi-Tracker Selection

A Survey of Background Modeling Based on Robust Subspace Learning via Sparse and Low-rank Matrix Decomposition

Feature Selection and Analysis of Powdery Mildew of Winter Wheat based on Multi-Temporal Satellite Imagery

Human Action Recognition by Fusion of Convolutional Neural Networks and spatial-temporal Information

Multiple image arrangement for subjective quality assessment

A Saliency-Guided Method for Automatic Photo Refocusing

Bands Sensitive Convolutional Network for Hyperspectral Image Classification

Personal Photo Enhancement via Saliency Driven Color Transfer

Robust Blind Image Watermarking Algorithm Based On Singular Value Quantization

Shadow Detection in High-Resolution Remote Sensing Image Based on Improved K-means

Asymmetry Analysis with Sparse Autoencoder in Mammography

Mammographic Mass Detection Based on Saliency with Deep Features

Heterogeneous Iris Segmentation Based on Active Contour Model and Prior Noise Characteristics

Activity Detection With Discriminative Patches

Beyond Sliding Windows: Saliency Prior Based Random Partition for Fast Pedestrian Detection

Spatial Pyramid Pooling in Structured Sparse Representation for Flame Detection

Auroral Video Temporal Segmentation Based on Time-constrained Spectral Clustering

Region-based CNN for Logo Detection

Query Rewriting for Archived Information Retrieval

A Method Combining Active Stereo with Global Matching Algorithm for Accurate Depth Extraction

Optimization of AVS+ Software Decoder for High-definition Video

Spatiotemporal Saliency Detection based Video Quality Assessment

STV2k: A New Benchmark for Scene Text Detection and Recognition

A Comparative Study On Features for Similar Image Search

Image Classification via fusing the latent deep CNN feature

Content Provider	ACM Digital Library
Author	Hong, Richang Liu, Xueliang Yan, He
Abstract	In recent years, the convolutional neural network (CNN) has made great achievements in image classification. It can extract features of image and classify them from a large number of image data automatically. Compared with these traditional feature extraction techniques (e.g., SIFT, HOG, GIST), the convolutional neural network can make better performance and does not need hand designed image features. However, how to further enhance the algorithm performance is still a hot spot in academic research. Therefore, in this paper, we propose a method to fuse the latent features extracted from the middle layers in a CNN to train a more robust classifier. First, we utilize the pretrained CNN models by caffe to extract visual features of 3-layer.Then, we use the SVM classifier for 3-layer features respectively, and we get their trained classifier. Finally, we combine three pretrained classifier into a classifier which is compared with 3-layer SVM classifier. The experiment is performed on Caltech-256 datasets. The experimental result shows that the combined classifier obtains good performance compared with the conventional CNN.
Starting Page	110
Ending Page	113
Page Count	4
File Format	PDF
ISBN	9781450348508
DOI	10.1145/3007669.3007706
Language	English
Publisher	Association for Computing Machinery (ACM)
Publisher Date	2016-08-19
Publisher Place	New York
Access Restriction	Subscribed
Subject Keyword	Extraction features Convolutional neural network Support vector machine Classifier
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