NDLI: Improving multiview face detection with multi-task deep convolutional neural networks

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

IEEE Winter Conference on Applications of Computer Vision

A discriminative parts based model approach for fiducial points free and shape constrained head pose normalisation in the wild

Data-driven road detection

Segmentation and tracking of partial planar templates

Robust tracking and mapping with a handheld RGB-D camera

Plant classification system for crop /weed discrimination without segmentation

Scale-Space SIFT flow

A lp-norm MTMKL framework for simultaneous detection of multiple facial action units

Fully automatic 3D facial expression recognition using local depth features

Relative facial action unit detection

A novel method for post-surgery face recognition using sum of facial parts recognition

Matching image sets via adaptive multi convex hull

Simultaneous recognition of facial expression and identity via sparse representation

Predicting movie ratings from audience behaviors

AutoCaption: Automatic caption generation for personal photos

Exploring the geo-dependence of human face appearance

Improving multiview face detection with multi-task deep convolutional neural networks

A discriminative parts based model approach for fiducial points free and shape constrained head pose normalisation in the wild

The effectiveness of face detection algorithms in unconstrained crowd scenes

Extending explicit shape regression with mixed feature channels and pose priors

Comparison of face detection and image classification for detecting front seat passengers in vehicles

Writer identification and verification using GMM supervectors

Finger-knuckle-print verification based on vector consistency of corresponding interest points

Adaptive representations for video-based face recognition across pose

Iris crypts: Multi-scale detection and shape-based matching

Active Clustering with Ensembles for Social structure extraction

Estimating cloudmaps from outdoor image sequences

Repeated constrained sparse coding with partial dictionaries for hyperspectral unmixing

Ant tracking with occlusion tunnels

Data association based ant tracking with interactive error correction

Materials discovery: Fine-grained classification of X-ray scattering images

Spatial inference for coherent geophysical fluids by appearance and geometry

Rotation estimation from cloud tracking

Determining underwater vehicle movement from sonar data in relatively featureless seafloor tracking missions

Object tracking via non-Euclidean geometry: A Grassmann approach

Information theoretic sensor management for multi-target tracking with a single pan-tilt-zoom camera

Urban Tracker: Multiple object tracking in urban mixed traffic

Structure-aware keypoint tracking for partial occlusion handling

Automatic tracker selection w.r.t object detection performance

Consensus-based matching and tracking of keypoints for object tracking

Online discriminative dictionary learning for visual tracking

Robust tracking of articulated human movements through Component-Based Multiple Instance Learning with particle filtering

Real-time multi-target tracking at 210 megapixels/second in Wide Area Motion Imagery

Video segmentation with joint object and trajectory labeling

A fully implicit alternating direction method of multipliers for the minimization of convex problems with an application to motion segmentation

Linear regression motion analysis for unsupervised temporal segmentation of human actions

Video alignment to a common reference

Combining semantic scene priors and haze removal for single image depth estimation

Robust optical flow estimation for continuous blurred scenes using RGB-motion imaging and directional filtering

Interactive video segmentation using occlusion boundaries and temporally coherent superpixels

Video text detection and recognition: Dataset and benchmark

Summarisation of short-term and long-term videos using texture and colour

Exploring context information for inter-camera multiple target tracking

Smart surveillance framework: A versatile tool for video analysis

Multi class boosted random ferns for adapting a generic object detector to a specific video

Joint semantic and geometric segmentation of videos with a stage model

Image parsing with graph grammars and Markov Random Fields applied to facade analysis

Object co-labeling in multiple images

Introspective semantic segmentation

Scene recognition by jointly modeling latent topics

Unsupervised Non-parametric Geospatial Modeling from Ground Imagery

Understanding the 3D layout of a cluttered room from multiple images

Task-based control of articulated human pose detection for OpenVL

Understanding and analyzing a large collection of archived swimming videos

Pedestrian detection in low resolution videos

Real-time 3-D face tracking and modeling framework for mid-res cam

Play type recognition in real-world football video

“Important stuff, everywhere!” Activity recognition with salient proto-objects as context

A combination of generative and discriminative models for fast unsupervised activity recognition from traffic scene videos

Mining discriminative 3D Poselet for cross-view action recognition

Real time action recognition using histograms of depth gradients and random decision forests

Coupling video segmentation and action recognition

Action in chains: A chains model for action localization and classification

Multi-view action recognition one camera at a time

A joint perspective towards image super-resolution: Unifying external- and self-examples

Bayesian Optimization with an Empirical Hardness Model for approximate Nearest Neighbour Search

Max residual classifier

Unsupervised iterative manifold alignment via local feature histograms

Composite Discriminant Factor analysis

Multimodal fusion using dynamic hybrid models

Unsupervised dictionary learning with double-layer sparse representation

Is my new tracker really better than yours?

Benchmarking large-scale Fine-Grained Categorization

Small Hand-held Object Recognition Test (SHORT)

Image segmentation of mesenchymal stem cells in diverse culturing conditions

Improving background subtraction using Local Binary Similarity Patterns

Large-scale semantic co-labeling of image sets

Scale-invariant line descriptors for wide baseline matching

Multiple foreground recognition and cosegmentation: An object-oriented CRF model with robust higher-order potentials

Improving streaming video segmentation with early and mid-level visual processing

Hierarchical representation of videos with spatio-temporal fibers

Efficient dense subspace clustering

Viewpoint-independent book spine segmentation

Multi-leaf alignment from fluorescence plant images

Age group classification via structured fusion of uncertainty-driven shape features and selected surface features

Integrating visual words as bunch of n-grams for effective biomedical image classification

A CRF approach to fitting a generalized hand skeleton model

Discovering discriminative cell attributes for HEp-2 specimen image classification

Automatic 3D change detection for glaucoma diagnosis

Linear Local Distance coding for classification of HEp-2 staining patterns

Video segmentation and feature co-occurrences for activity classification

Offline learning of prototypical negatives for efficient online Exemplar SVM

GMM improves the reject option in hierarchical classification for fish recognition

Brownian descriptor: A rich meta-feature for appearance matching

Selection of universal features for image classification

Learning local image descriptors using binary decision trees

Data-driven exemplar model selection

Attribute-based vehicle recognition using viewpoint-aware multiple instance SVMs

Segmentation and matching: Towards a robust object detection system

Furniture-geek: Understanding fine-grained furniture attributes from freely associated text and tags

Local inter-session variability modelling for object classification

Random projections on manifolds of Symmetric Positive Definite matrices for image classification

Elastic reflection symmetry based shape descriptors

Car make and model recognition using 3D curve alignment

Unsupervised domain adaptation using parallel transport on Grassmann manifold

Towards cautious collective inference for object verification

Joint hierarchical learning for efficient multi-class object detection

Im2depth: Scalable exemplar based depth transfer

Accelerating arrays of linear classifiers using approximate range queries

Selectively guiding visual concept discovery

Feature combination with Multi-Kernel Learning for fine-grained visual classification

Learning mid-level features from object hierarchy for image classification

COLOR CHILD: A robust and computationally efficient Color Image Local Descriptor

Transfer learning via attributes for improved on-the-fly classification

A spatial-color layout feature for representing galaxy images

Exemplar codes for facial attributes and tattoo recognition

Generalized feature learning and indexing for object localization and recognition

Beyond PASCAL: A benchmark for 3D object detection in the wild

Gradient based efficient feature selection

Physical querying with multi-modal sensing

Interactively test driving an object detector: Estimating performance on unlabeled data

Recognizing locations with Google Glass: A case study

Real-time video decolorization using bilateral filtering

Color and flow based superpixels for 3D geometry respecting meshing

Real-time 3D page tracking and book status recognition for high-speed book digitization based on adaptive capturing

System for semi-automated surveying of street-lighting poles from street-level panoramic images

Optical filter selection for automatic visual inspection

Vision for road inspection

Automatic identification of window regions on indoor point clouds using LiDAR and cameras

Recognition of 3D package shapes for single camera metrology

3D pose estimation of bats in the wild

Model-based anthropometry: Predicting measurements from 3D human scans in multiple poses

NRSfM using local rigidity

GPU-accelerated and efficient multi-view triangulation for scene reconstruction

Fast dense 3D reconstruction using an adaptive multiscale discrete-continuous variational method

Volumetric reconstruction applied to perceptual studies of size and weight

Online algorithms for factorization-based structure from motion

3D Metric Rectification using Angle Regularity

Fine-grained object recognition with Gnostic Fields

Point pattern matching based on line graph spectral context and descriptor embedding

Depth-based patch scaling for content-aware stereo image completion

Detecting 3D geometric boundaries of indoor scenes under varying lighting

Car make and model recognition using 3D curve alignment

Accelerating arrays of linear-supp

2013 IEEE Workshop on Applications of Computer Vision (WACV)

2012 IEEE Workshop on the Applications of Computer Vision (WACV)

2011 IEEE Workshop on Applications of Computer Vision (WACV)

2009 Workshop on Applications of Computer Vision (WACV)

2008 IEEE Workshop on Applications of Computer Vision

2007 IEEE Workshop on Applications of Computer Vision (WACV '07)

2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION'05) - Volume 1

Sixth IEEE Workshop on Applications of Computer Vision, 2002. (WACV 2002). Proceedings.

Proceedings Fifth IEEE Workshop on Applications of Computer Vision

Proceedings Fourth IEEE Workshop on Applications of Computer Vision. WACV'98 (Cat. No.98EX201)

Proceedings Third IEEE Workshop on Applications of Computer Vision. WACV'96

Proceedings of 1994 IEEE Workshop on Applications of Computer Vision

[1992] Proceedings IEEE Workshop on Applications of Computer Vision

Improving multiview face detection with multi-task deep convolutional neural networks

Content Provider	IEEE Xplore Digital Library
Author	Cha Zhang Zhengyou Zhang
Copyright Year	2014
Description	Author affiliation: Microsoft Res., Redmond, WA, USA (Cha Zhang; Zhengyou Zhang)
Abstract	Multiview face detection is a challenging problem due to dramatic appearance changes under various pose, illumination and expression conditions. In this paper, we present a multi-task deep learning scheme to enhance the detection performance. More specifically, we build a deep convolutional neural network that can simultaneously learn the face/nonface decision, the face pose estimation problem, and the facial landmark localization problem. We show that such a multi-task learning scheme can further improve the classifier's accuracy. On the challenging FDDB data set, our detector achieves over 3% improvement in detection rate at the same false positive rate compared with other state-of-the-art methods.
Sponsorship	IEEE Comput. Soc.
Starting Page	1036
Ending Page	1041
File Size	4840242
Page Count	6
File Format	PDF
ISBN	9781479949854
DOI	10.1109/WACV.2014.6835990
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2014-03-24
Publisher Place	USA
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Face Detectors Face detection Neural networks Feature extraction Training Estimation
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