NDLI: Towards coherent natural language description of video streams

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

2015 IEEE International Conference on Computer Vision Workshop (ICCVW)

2013 IEEE International Conference on Computer Vision Workshops

2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops)

WS01: The second IEEE international workshop on mobile vision

WS03: First IEEE workshop on modeling, simulation and visual analysis of large crowds

WS04: 1st IEEE/ISPRS workshop on computer vision for remote sensing of the environment

WS05: OMNIVIS 2011: IEEE workshop on omni-directional vision, camera networks and non-classical cameras

WS06: 6th IEEE workshop on human computer interaction: Real-time vision aspects of natural user interfaces

WS07: Third workshop on GPUs for computer vision

WS08: Workshop on 3D representation and recognition (3dRR-11)

WS09: SIG-11: Second international workshop on stochastic image grammars

WS10: ICCV2011 workshop “live dense reconstruction with moving cameras”

WS11: 3rd IEEE workshop on color and photometry in computer vision

WS12: 2nd international workshop on SOCIALLY INTELLIGENT SURVEILLANCE and MONITORING, SISM 2011

WS13: 2nd IEEE workshop on analysis and retrieval of tracked events and motion in imagery streams

WS14: Challenges and opportunities in robot perception

WS15: 1st IEEE workshop on consumer depth cameras for computer vision

WS16a: Human interaction in computer vision

WS16b: 1st IEEE workshop on performance evaluation on recognition of human actions and pose estimation methods

WS17: 1st IEEE workshop in information theory in computer vision and pattern recognition

WS18: VECTaR 2011: Workshop program

WS20: 4DMOD workshop on “dynamic shape capture and analysis”

WS22: The eleventh IEEE international workshop on visual surveillance

WS23: Computer vision in vehicle technology: From earth to mars (CVVT2011)

WS24: Benchmarking facial image analysis technologies

Stabilizing cell phone video using inertial measurement sensors

High-quality video denoising for motion-based exposure control

Structure and motion estimation from rolling shutter video

Augmented faces

Compressing Feature Sets with Digital Search Trees

Face authentication using graph-based low-rank representation of facial local structures for mobile vision applications

Automatic text detection for mobile augmented reality translation

Epipolar geometry estimation for wide-baseline omnidirectional street view images

Towards robust and efficient text sign reading from a mobile phone

Good features to track: A view geometric approach

Visual localization for mobile surveillance

FaceSimile: A mobile application for face image search based on interactive shape manipulation

A fast and accurate cascade subspace face/eye detector on mobile devices

Wi-Fi and keygraphs for localization with cell phones

A mobile structured light system for food volume estimation

Visual localization by linear combination of image descriptors

“Dancing icons” detection

MCMC-based tracking and identification of leaders in groups

Everybody needs somebody: Modeling social and grouping behavior on a linear programming multiple people tracker

Virtual Tawaf: A case study in simulating the behavior of dense, heterogeneous crowds

Optimizing interaction force for global anomaly detection in crowded scenes

Analyzing pedestrian behavior in crowds for automatic detection of congestions

Integrating pedestrian simulation, tracking and event detection for crowd analysis

T-junction: Experiments, trajectory collection, and analysis

Calibrating dynamic pedestrian route choice with an Extended Range Telepresence System

Lane formation in a microscopic model and the corresponding partial differential equation

Robust outliers detection in image point matching

Multi-view manhole detection, recognition, and 3D localisation

A hierarchical conditional random field model for labeling and classifying images of man-made scenes

Graph matching in 3D space for structural seismic damage assessment

3D roof details by 3D aerial vision

Computer vision for the remote sensing of atmospheric visibility

Text detection and recognition in urban scenes

Classification of multitemporal remote sensing data of different resolution using Conditional Random Fields

Incremental import vector machines for large area land cover classification

Monitoring changes of 3D building elements from unordered photo collections

Classification and reconstruction of surfaces from point clouds of man-made objects

Non-sequential structure from motion

Self-localization of mobile robot equipped with omnidirectional camera using image matching and 3D-2D edge matching

Indoor SLAM using a range-augmented omnidirectional vision

Calibration of radially symmetric distortion based on linearity in the calibrated image

3D environment measurement using binocular stereo and motion stereo by mobile robot with omnidirectional stereo camera

Underwater sensing with omni-directional stereo camera

An insect-inspired omnidirectional vision system including UV-sensitivity and polarisation

Matching cylindrical panorama sequences using planar reprojections

Tracking moving objects with a catadioptric sensor using particle filter

A spherical representation for efficient visual loop closing

Adapting a real-time monocular visual SLAM from conventional to omnidirectional cameras

Optimum alignment of panoramic images for stereoscopic navigation in image-based telepresence systems

Scene structure recovery from a single omnidirectional image

Multiple Hypothesis Tracking in camera networks

Structure from Motion using full spherical panoramic cameras

Real-time sign language letter and word recognition from depth data

Real-time upper body tracking with online initialization using a range sensor

Volumetric 3D graphics on commodity displays using active gaze tracking

Using segmented 3D point clouds for accurate likelihood approximation in human pose tracking

Robust validation of Visual Focus of Attention using adaptive fusion of head and eye gaze patterns

Measuring and reducing observational latency when recognizing actions

Monocular omnidirectional head motion capture in the visible light spectrum

Developer-centred interface design for computer vision

Freehand 3D scanning in a mobile environment using video

Real time feature point tracking with automatic model selection

Demonstrations and live evaluation for the gesture recognition challenge

MoPaCo: High telepresence video communication system using motion parallax with monocular camera

Mid-air interactive display using modulated display light

On building an accurate stereo matching system on graphics hardware

Long term video segmentation through pixel level spectral clustering on GPUs

Learning a dictionary of deformable patches using GPUs

Rapid weak-perspective Structure from Motion with missing data

Accelerating multi-scale flows for LDDKBM diffeomorphic registration

GPU & CPU cooperative accelerated pedestrian and vehicle detection

Real-time semi-global matching disparity estimation on the GPU

Variational Depth from Defocus in real-time

Real-time GPU-based face detection in HD video sequences

A GPU-assisted personal video organizing system

Automatic alignment of paintings and photographs depicting a 3D scene

A hypothesize-and-bound algorithm for simultaneous object classification, pose estimation and 3D reconstruction from a single 2D image

A compositional approach to learning part-based models of objects

Revisiting 3D geometric models for accurate object shape and pose

Projectable classifiers for multi-view object class recognition

CAD-model recognition and 6DOF pose estimation using 3D cues

Holistic 3D reconstruction of urban structures from low-rank textures

Indoor scene segmentation using a structured light sensor

Scale-space representation of scalar functions on 2D manifolds

Scale and rotation invariant color features for weakly-supervised object Learning in 3D space

Trainable 3D recognition using stereo matching

Modeling symmetries for stochastic structural recognition

Human parsing using stochastic and-or grammars and rich appearances

Unsupervised learning of stochastic AND-OR templates for object modeling

An ontology for generating descriptions about natural outdoor scenes

Towards coherent natural language description of video streams

Interactive learning of human activities using active video composition

PEL-CNF: Probabilistic event logic conjunctive normal form for video interpretation

The evolution of stochastic grammars for representation and recognition of activities in videos

Sum-product networks: A new deep architecture

Object detection grammars

Information theoretic methods for learning generative models for relational structures

Learning and the language of thought

Stochastic models for semantic parsing, multi-faceted topic discovery, and causal event inference: Perspectives from natural language processing

Efficient edge-preserving stereo matching

An asymmetric real-time dense visual localisation and mapping system

Real-time global prediction for temporally stable stereo

Online 3D reconstruction using convex optimization

Recursive Live Dense Reconstruction: Some comments on established and imaginable new approaches

GEA optimization for live structureless motion estimation

Real-time visual odometry from dense RGB-D images

Surface reconstruction for RGB-D data using real-time depth propagation

Real-time structure and motion recovery from two views of a multiplanar scene

Live 3D shape reconstruction, recognition and registration

Perceptually motivated automatic sharpness enhancement using hierarchy of non-local means

Color correction using rotation matrix for HDR rendering in iCAM06

Deblurring shaken and partially saturated images

Photometric stereo with auto-radiometric calibration

A new approach of photometric stereo from linear image representation under close lighting

Estimating the unknown poses of a reference plane for specular shape recovery

Color constancy and non-uniform illumination: Can existing algorithms work?

Illuminant color estimation for real-world mixed-illuminant scenes

General $ࡁ^{p}$ constrained approach for colour constancy

Illumination estimation from shadow borders

A theory of color barcodes

Accuracy of the spider model in decomposing layered surfaces

Inverse rendering in SUV space with a linear texture model

Who knows who - Inverting the Social Force Model for finding groups

Do they like me? Using video cues to predict desires during speed-dates

Human pose estimation using structural support vector machines

An efficient IP approach to constrained multiple face tracking and recognition

A joint estimation of head and body orientation cues in surveillance video

Differentiating spontaneous from posed facial expressions within a generic facial expression recognition framework

On improving the robustness of differential optical flow

High-level situation recognition using Fuzzy Metric Temporal Logic, case studies in surveillance and smart environments

Automatic analysis of composite activities in video sequences using Key Action Discovery and hierarchical graphical models

Automatic crowd density and motion analysis in airborne image sequences based on a probabilistic framework

On the effect of temporal information on monocular 3d human pose estimation

Reading the signs: A video based sign dictionary

People appearance tracing in video by spectral graph transduction

Spatiotemporally localized new event detection in crowds

Detecting individual in crowd with moving feature's structure consistency

Video scene classification based on natural language description

Video summarization guiding evaluative rectification for industrial activity recognition

Learning temporal signatures for Lip Reading

Efficient object detection and segmentation with a cascaded Hough Forest ISM

Real-time multi-person tracking with detector assisted structure propagation

Semantic structure from motion with object and point interactions

Evaluation of stereo algorithms for 3D object recognition

Visual grasp affordances from appearance-based cues

Robot localization using 3D-models and an off-board monocular camera

High resolution visual terrain classification for outdoor robots

Driving me around the bend: Learning to drive from visual gist

Topological localization using optical flow descriptors

Unsupervised discovery of object classes in 3D outdoor scenarios

Visual control of a multi-robot coupled system: Application to collision avoidance in human-robot interaction

Deformable part models revisited: A performance evaluation for object category pose estimation

Visual estimation of pointed targets for robot guidance via fusion of face pose and hand orientation

More accurate pinhole camera calibration with imperfect planar target

Detecting and tracking people using an RGB-D camera via multiple detector fusion

Real-time plane extraction from depth images with the Randomized Hough Transform

Visual object classification by robots, using on-line, self-supervised learning

A novel stereoscopic cue for figure-ground segregation of semi-transparent objects

The capturing of turbulent gas flows using multiple Kinects

Spelling it out: Real-time ASL fingerspelling recognition

Consolidation of multiple depth maps

Humanising GrabCut: Learning to segment humans using the Kinect

Fast and accurate environment modeling using three-dimensional occupancy grids

A brute force approach to depth camera odometry

RGBD-HuDaAct: A color-depth video database for human daily activity recognition

Real-time RGB-D mapping and 3-D modeling on the GPU using the random ball cover data structure

A category-level 3-D object dataset: Putting the Kinect to work

Multi-modal surface registration for markerless initial patient setup in radiation therapy using microsoft's Kinect sensor

Featureweighting in dynamic timewarping for gesture recognition in depth data

Going into depth: Evaluating 2D and 3D cues for object classification on a new, large-scale object dataset

Putting the pieces together: Connected Poselets for human pose estimation

Learning shape models for monocular human pose estimation from the Microsoft Xbox Kinect

I spy with my little eye: Learning optimal filters for cross-modal stereo under projected patterns

A cluster-based strategy for active learning of RGB-D object detectors

Real-time preprocessing for dense 3-D range imaging on the GPU: Defect interpolation, bilateral temporal averaging and guided filtering

Real time hand pose estimation using depth sensors

Towards robust cross-user hand tracking and shape recognition

Cultural factors in the regression of non-verbal communication perception

Scene specific people detection by simple human interaction

Interactive object segmentation for mono and stereo applications: Geodesic prior induced graph cut energy minimization

UMPM benchmark: A multi-person dataset with synchronized video and motion capture data for evaluation of articulated human motion and interaction

Expressive Maps for 3D Facial Expression Recognition

Automatic user interaction correction via Multi-label Graph cuts

Probabilistic subspace-based learning of shape dynamics modes for multi-view action recognition

Modeling vs. learning approaches for monocular 3D human pose estimation

A discriminative prototype selection approach for graph embedding in human action recognition

Action recognition by learning discriminative key poses

Temporal key poses for human action recognition

Human action silhouette recognition based on tensor analysis using synthetic silhouette data

Iteratively merging information from a pair of flash/no-flash images using nonlinear diffusion

Efficient variational inference in large-scale Bayesian compressed sensing

STARS: A new ensemble partitioning approach

A multi-affine model for tensor decomposition

Search pruning in video surveillance systems: Efficiency-reliability tradeoff

Computing importance of 2D contour parts by reconstructability

Probabilistic shape-based segmentation using level sets

A invertible dimension reduction of curves on a manifold

Supervised feature quantization with entropy optimization

Evaluating image segments by applying the description length to sets of superpixels

Bayesian online learning on Riemannian manifolds using a dual model with applications to video object tracking

Exploring the representation capabilities of the HOG descriptor

Information theoretic preattentive saliency: A closed-form solution

An information theoretic approach to gender feature selection

An information geometry approach to shape density Minimum Description Length model selection

Tensor-based total bregman divergences between graphs

Towards a theory of compositional learning and encoding of objects

Inferring social roles in long timespan video sequence

Video event detection based on over-segmented STV regions

A generative framework to investigate the underlying patterns in human activities

Human Focused Video Description

Fine-grained categorization of fish motion patterns in underwater videos

Structure context of local features in realistic human action recognition

Individuals, groups, and crowds: Modelling complex, multi-object behaviour in phase space

A hybrid framework for event detection using multi-modal features

YouTubeEvent: On large-scale video event classification

Combining sparse and dense descriptors with temporal semantic structures for robust human action recognition

Detection of activities and events without explicit categorization

Correcting cuboid corruption for action recognition in complex environment

Transductive transfer learning for action recognition in tennis games

Recognizing manipulation actions in arts and crafts shows using domain-specific visual and textual cues

Incorporating temporal context in Bag-of-Words models

Event-driven feature analysis in a 4D spatiotemporal representation for ambient assisted living

Joint reconstruction of 3D shape and non-rigid motion in a region-growing framework

FEM models to code non-rigid EKF monocular SLAM

4D facial expression recognition

Multiview projectors/cameras system for 3D reconstruction of dynamic scenes

3D dynamics analysis in Teichmüller space

3D reconstruction of bat flight kinematics from sparse multiple views

The wave kernel signature: A quantum mechanical approach to shape analysis

Motion capture from dynamic orthographic cameras

Facial expression recognition with temporal modeling of shapes

A pixel-based approach to template-based monocular 3D reconstruction of deformable surfaces

Fast volumetric visual hull computation

The eleventh IEEE international workshop on visual surveillance

Robust object tracking with boosted discriminative model via graph embedding

Detection-based multi-human tracking using a CRF model

Tensor-based covariance matrices for object tracking

Multi-camera multi-object tracking by robust hough-based homography projections

Camera auto-calibration using pedestrians and zebra-crossings

Approximate techniques in solving optimal camera placement problems

Appearance-based head pose estimation with scene-specific adaptation

Multiple person re-identification using part based spatio-temporal color appearance model

A discriminative key pose sequence model for recognizing human interactions

Transferring activities: Updating human behavior analysis

Spatially adaptive illumination modeling for background subtraction

Multi-scale multi-feature codebook-based background subtraction

Automatic surveillance video matting using a shape prior

Self-adaptive Gaussian mixture model for urban traffic monitoring system

Efficient pedestrian detection with group lasso

Relational HOG feature with wild-card for object detection

Person detection in surveillance environment with HoGG: Gabor filters and Histogram of Oriented Gradient

Improving object localization using macrofeature layout selection

Eigenshape kernel based mean shift for human tracking

Multi-view people surveillance using 3D information

Branch and bound global optima search for tracking a single object in a network of non-overlapping cameras

Efficient framework for extended visual object tracking

An analytical formulation of global occlusion reasoning for multi-target tracking

Tracking visual and infrared objects using joint Riemannian manifold appearance and affine shape modeling

Globally optimal target tracking in real time using max-flow network

Robust object tracking via online learning of adaptive appearance manifold

Flexible tracklet association for complex scenarios using a Markov Logic Network

Re-identification of pedestrians with variable occlusion and scale

Human gait characteristics from unconstrained walks and viewpoints

Full-motion recovery from multiple video cameras applied to face tracking and recognition

An X-T slice based method for action recognition

A group sparsity-driven approach to 3-D action recognition

Unsupervised workflow discovery in industrial environments

Self-calibrating 3D context for retrieving people with luggage

Video-based traffic queue length estimation

Multi-cue learning and visualization of unusual events

Slice matching for accurate spatio-temporal alignment

A surveillance video analysis and storage scheme for scalable synopsis browsing

Operator attention based video surveillance

Semantic video event search for surveillance video

Reversible video stream anonymization for video surveillance systems based on pixels relocation and watermarking

A real-time multi-cue framework for determining optical flow confidence

Automatic real-time FACS-coder to anonymise drivers in eye tracker videos

SPARTAN system: Towards a low-cost and high-performance vision architecture for space exploratory rovers

Constrained UAV mission planning: A comparison of approaches

Stixels estimation without depth map computation

Monocular Camera Trajectory Optimization using LiDAR data

Stereo estimation of depth along virtual cut planes

A framework for global vehicle localization using stereo images and satellite and road maps

A confidence measure for assessing optical flow accuracy in the absence of ground truth

Direct Iterative Closest Point for real-time visual odometry

Contrast restoration of road images taken in foggy weather

Showing vehicles at blind corners from mixed-dimensional multi-view geometry

Learning multi-lane trajectories using vehicle-based vision

Unsupervised sub-categorization for object detection: Finding cars from a driving vehicle

Illumination-free gaze estimation method for first-person vision wearable device

Facial action unit detection using kernel partial least squares

3D Twins and Expression Challenge

Static facial expression analysis in tough conditions: Data, evaluation protocol and benchmark

UMB-DB: A database of partially occluded 3D faces

A face biometric benchmarking review and characterisation

High-resolution comprehensive 3-D dynamic database for facial articulation analysis

Manifold based Sparse Representation for robust expression recognition without neutral subtraction

Annotated Facial Landmarks in the Wild: A large-scale, real-world database for facial landmark localization

Single- and cross- database benchmarks for gender classification under unconstrained settings

Evaluation of face recognition system in heterogeneous environments (visible vs NIR)

High quality facial expression recognition in video streams using shape related information only

VADANA: A dense dataset for facial image analysis

Face detection using SURF cascade

Criteria and metrics for thresholded AU detection

Object representation based on gabor wave vector binning: An application to human head pose detection

2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops

Tenth IEEE International Conference on Computer Vision Workshops (ICCVW'05)

Towards coherent natural language description of video streams

Content Provider	IEEE Xplore Digital Library
Author	Khan, M.U.G. Lei Zhang Gotoh, Y.
Copyright Year	2011
Description	Author affiliation: Harbin Engineering University, China (Lei Zhang) \|\| University of Sheffield, United Kingdom (Khan, M.U.G.; Gotoh, Y.)
Abstract	This contribution addresses the approach to creating smooth and coherent description of video streams. Firstly conventional image processing techniques are applied to extract high level features from individual video frames. Natural language description of the frame contents is produced based on high level features. In order to extend the approach to description of video streams, we introduce units of features and overview how units can be used to present coherent, smooth and well phrased descriptions by incorporating spatial and temporal information. The approach is evaluated by calculating overlap similarity score between human authored and machine generated descriptions.
Starting Page	664
Ending Page	671
File Size	2225645
Page Count	8
File Format	PDF
ISBN	9781467300629
e-ISBN	9781467300636
DOI	10.1109/ICCVW.2011.6130306
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2011-11-06
Publisher Place	Spain
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Legged locomotion Visualization Image color analysis Natural languages Video sequences Humans Streaming media
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