NDLI: Exploring Pooling Strategies based on Idiosyncrasies of Spatio-Temporal Interest Points

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

Dense Models from Videos: Can YouTube be the Font of All Knowledge Bases?

Image Classification and Retrieval are ONE

Fast Democratic Aggregation and Query Fusion for Image Search

Facial Action Unit Classification with Hidden Knowledge under Incomplete Annotation

Fine-Grained Image Categorization by Localizing TinyObject Parts from Unannotated Images

Semi-Supervised Image Classification by Nonnegative Sparse Neighborhood Propagation

Bundling Centre for Landmark Image Discovery

Attribute Guided Dictionary Learning

A Privacy-Preserving Bipartite Graph Matching Framework for Multimedia Analysis and Retrieval

Content-based Image Retrieval Using Rotation-invariant Histograms of Oriented Gradients

End-to-End Photo-Sketch Generation via Fully Convolutional Representation Learning

Music Positioning and Annotation For Television Videos

Social Event Mining in Large Photo Collections

DeepIndex for Accurate and Efficient Image Retrieval

Extracting 3D Trajectories of Objects from 2D Videos using Particle Filter

Robust and Discriminative Concept Factorization for Image Representation

Hierarchical Encoding of Binary Descriptors for Image Matching

To Keep or not to Keep: An Expectation-oriented Photo Selection Method for Personal Photo Collections

Online Multimodal Co-indexing and Retrieval of Weakly Labeled Web Image Collections

Describing Images with Hierarchical Concepts and Object Class Localization

Augmented Feature Fusion for Image Retrieval System

Teaching Video Analytics Based on Student Spatial and Temporal Behavior Mining

KinectSBR: A Kinect-Assisted 3D Sketch-Based 3D Model Retrieval System

Unified YouTube Video Recommendation via Cross-network Collaboration

Effective, Efficient, and Scalable Unsupervised Distance Learning in Image Retrieval Tasks

Space-time Histograms And Their Application To Person Re-identification In TV Shows

Encoding Concept Prototypes for Video Event Detection and Summarization

Kernelizing Spatially Consistent Visual Matches for Fine-Grained Classification

Latent Factors of Visual Popularity Prediction

Weakly Supervised Random Forest for Multi-Label Image Clustering and Segmentation

Supervised Multi-scale Locality Sensitive Hashing

Parallel AP Clustering and Re-ranking for Automatic Image-Text Alignment and Large-Scale Web Image Search

Multi-view Face Detection Using Deep Convolutional Neural Networks

An Improved System For Real-Time Scene Text Recognition

Bridging the Ultimate Semantic Gap: A Semantic Search Engine for Internet Videos

Twin Feature and Similarity Maximal Matching for Image Retrieval

Temporal Order-Preserving Dynamic Quantization for Human Action Recognition from Multimodal Sensor Streams

Discovering Semantic Vocabularies for Cross-Media Retrieval

High-Dimensional Indexing by Sparse Approximation

Visual Event Summarization on Social Media using Topic Modelling and Graph-based Ranking Algorithms

Harvesting Multiple Sources for User Profile Learning: a Big Data Study

A Novel Visual-Region-Descriptor-based Approach to Sketch-based Image Retrieval

Accio: A Data Set for Face Track Retrieval in Movies Across Age

DigInPix: Visual Named-Entities Identification in Images and Videos

Fusing Pointwise and Pairwise Labels for Supporting User-adaptive Image Retrieval

Diffusion-on-Manifold Aggregation of Local Features for Shape-based 3D Model Retrieval

Location Prediction of Social Images via Generative Model

A Two-step Approach to Cross-modal Hashing

Mobile Media Thumbnailing

Scalable Multimodal Search with Distributed Indexing by Sparse Hashing

Cross-Scenario Eyeglasses Retrieval via EGYPT Model

IdeaPanel: A Large Scale Interactive Sketch-based Image Search System

Insight in Image Collections by Multimedia Pivot Tables

People News Search via Name-Face Association Analysis

A Sparse Ensemble Learning System For Efficient Semantic Indexing

Distribution Regularized Nonnegative Matrix Factorization for Transfer Visual Feature Learning

Discovering the Latent Similarities of the KNN Graph by Metric Transformation

A Multi-Sensory Gesture-Based Occupational Therapy Environment for Controlling Home Appliances

Heterogeneous Semantic Level Features Fusion for Action Recognition

Formation Period Matters: Towards Socially Consistent Group Detection via Dense Subgraph Seeking

Incremental Multimodal Query Construction for Video Search

Social Friend Recommendation Based on Network Correlation and Feature Co-Clustering

Memory Vectors for Particular Object Retrieval with Multiple Queries

Improving Diversity in Image Search via Supervised Relevance Scoring

Semantic-aware Hashing for Social Image Retrieval

Unsupervised Distance Learning by Rank Correlation Measures for Image Retrieval

Zero-shot Image Categorization by Image Correlation Exploration

Exploring Pooling Strategies based on Idiosyncrasies of Spatio-Temporal Interest Points

Deep Bottleneck Feature for Image Classification

Image-Text Cross-Modal Retrieval via Modality-Specific Feature Learning

Maximally Visual-Homogeneous Region Detector for Large Scale Image Retrieval

Location-Based Parallel Tag Completion for Geo-tagged Social Image Retrieval

Rapid Clothing Retrieval via Deep Learning of Binary Codes and Hierarchical Search

Exploiting Spatial Relationship between Scenes for Hierarchical Video Geotagging

Information Gain Study for Visual Vocabulary Construction

Using Viewer's Facial Expression and Heart Rate for Sports Video Highlights Detection

Discriminative Latent Feature Space Learning for Cross-Modal Retrieval

A Deep Neural Network for Modeling Music

Image Retrieval by User-oriented Ranking

Robust Seed Localization and Growing with Deep Convolutional Features for Scene Text Detection

Spatial Constraint for Image Location Estimation

Swap Retrieval: Retrieving Images of Cats When the Query Shows a Dog

Shape-based Object Matching Using Point Context

Graph Learning on K Nearest Neighbours for Automatic Image Annotation

Large Scale Image Annotation via Deep Representation Learning and Tag Embedding Learning

Scalable Organization of Collections of Motion Capture Data via Quantitative and Qualitative Analysis

Probabilistic Matrix Factorization With Semantic And Visual Neighborhoods For Image Tag Completion

Content-Based Video Search over 1 Million Videos with 1 Core in 1 Second

Exploiting Multiple Web Resources towards Collecting Positive Training Samples for Visual Concept Learning

Bag-of-Fragments: Selecting and Encoding Video Fragments for Event Detection and Recounting

CRMActive: An Active Learning Based Approach for Effective Video Annotation and Retrieval

Evaluating Two-Stream CNN for Video Classification

Personalized Egocentric Video Summarization for Cultural Experience

EMIF: Towards a Scalable and Effective Indexing Framework for Large Scale Music Retrieval

Specific Person Retrieval via Incomplete Text Description

Combining Generic and Specific Information for Cross-modal Retrieval

3D Sketch-Based 3D Model Retrieval

Boosting Prediction of Geo-location for Web Images Through Integrating Multiple Knowledge Sources

Expression Recognition from Visible Images with the Help of Thermal Images

Multi-facet Learning using Deep Convolutional Neural Network for Person-Related Categories in Photos

Sketch-based Image Retrieval via Shape Words

Multiple Aesthetic Attribute Assessment by Exploiting Relations Among Aesthetic Attributes

Emotion Recognition from EEG Signals using Hierarchical Bayesian Network with Privileged Information

Multi-Label Active Learning with Chi-Square Statistics for Image Classification

Multiple Measurements and Joint Dimensionality Reduction for Large Scale Image Search with Short Vectors

Exploring EEG for Object Detection and Retrieval

Kernel Local Descriptors with Implicit Rotation Matching

Semantic Concept Annotation For User Generated Videos Using Soundtracks

Automatic Image Annotation using Deep Learning Representations

"My Day in Review": Visually Summarising Noisy Lifelog Data

Audio-Based Multimedia Event Detection with DNNs and Sparse Sampling

Learning Binary Codes for Hashing via Feature Decomposition

Mutlimodal Learning with Deep Boltzmann Machine for Emotion Prediction in User Generated Videos

Improving Automatic Name-Face Association using Celebrity Images on the Web

Exploring Pooling Strategies based on Idiosyncrasies of Spatio-Temporal Interest Points

Content Provider	ACM Digital Library
Author	Yang, Xiaodong Ye, Yuancheng Tian, Yingli
Abstract	Recent studies have demonstrated that the implementation of local space-time interest points has good competence and robustness in the area of human action recognition, which has become one of the challenging problems in multimedia analysis. While most research focuses on the techniques of detecting feature points or capturing spatial and temporal information around those points, there has been very limited research on delving into the pooling strategies which are also important components of action recognition algorithms. In this paper, we propose a novel pooling framework by categorizing the interest points with respect to their idiosyncrasies. Specifically, we discuss three pooling strategies based on the optical flow orientation, foreground weight and spatio-temporal locations respectively and further investigate the fusion of different pooling strategies. For the encoding process, instead of the popular bag-of-visual words (BoV) method, we adopt the improved Fisher Vector (FV) approach. Our proposed methods are evaluated on a benchmark dataset with controlled settings (KTH), and two more challenging datasets with realistic background (HMDB51 and UCF101). The experimental results demonstrate that pooling strategies based on the appropriate idiosyncrasies of individual interest points can improve the performance of action classification.
Starting Page	339
Ending Page	346
Page Count	8
File Format	PDF
ISBN	9781450332743
DOI	10.1145/2671188.2749339
Language	English
Publisher	Association for Computing Machinery (ACM)
Publisher Date	2015-06-22
Publisher Place	New York
Access Restriction	Subscribed
Subject Keyword	Action recognition Spatio-temporal pyramid Local interest points Pooling strategy Foreground weight Optical flow
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