BMVC 2010 - PDF Preprint Papers

BMVC 2010

Teaser Browsing | Click Here

Title Browsing | Click Here

Wall of Fame | Most Viewed BMVC-2010 Paper

click to vote

BMVC
2010

110views Computer Vision» more BMVC 2010»

Embedding Visual Words into Concept Space for Action and Scene Recognition

1 years 3 months ago

Download bmvc10.dcs.aber.ac.uk

In this paper we propose a novel approach to introducing semantic relations into the bag-of-words framework. We use the latent semantic models, such as LSA and pLSA, in order to d...

Behrouz Khadem, Elahe Farahzadeh, Deepu Rajan, And...

claim paper

Read More »

Disclaimer and Copyright Notice

Sciweavers respects the rights of all copyright holders and in this regard, authors are only allowed to share a link to their preprint paper on their own website. Every contribution is associated with a desciptive image. It is the sole responsibility of the authors to ensure that their posted image is not copyright infringing. This service is compliant with IEEE copyright.

Id	Views	Title	Status
1	110	Embedding Visual Words into Concept Space for Action and Scene Recognition	claim
2	106	Histogram of Oriented Cameras - A New Descriptor for Visual SLAM in Dynamic Environments	claim
3	105	Learning Directional Local Pairwise Bases with Sparse Coding	claim
4	104	A Wavelet Based Local Descriptor for Human Action Recognition	claim
5	104	The Fastest Pedestrian Detector in the West	claim
6	98	Generalized Descriptor Compression for Storage and Matching	claim
7	97	Manifold Learning for ToF-based Human Body Tracking and Activity Recognition	claim
8	97	Discriminative Topics Modelling for Action Feature Selection and Recognition	claim
9	93	Clustered Pose and Nonlinear Appearance Models for Human Pose Estimation	claim
10	91	Skeleton Extraction via Anisotropic Heat Flow	claim
11	88	Generalized RBF feature maps for Efficient Detection	claim
12	88	Vision-Based Behavior Prediction in Urban Traffic Environments by Scene Categorization	claim
13	85	Background subtraction adapted to PTZ cameras by keypoint density estimation	claim
14	85	Live Feature Clustering in Video Using Appearance and 3D Geometry	claim
15	85	Recognizing human actions in still images: a study of bag-of-features and part-based representations	claim
16	85	Person Re-Identification by Support Vector Ranking	claim
17	84	Weakly Supervised Object Recognition and Localization with Invariant High Order Features	claim
18	84	Manifold Learning for Multi-Modal Image Registration	claim
19	83	Histogram of Body Poses and Spectral Regression Discriminant Analysis for Human Action Categorization	claim
20	80	Insect Species Recognition using Sparse Representation	claim
21	80	SLP: A Zero-Contact Non-Invasive Method for Pulmonary Function Testing	claim
22	80	Graph-based Analysis of Textured Images for Hierarchical Segmentation	claim
23	79	Robust 3D Face Recognition by Using Shape Filtering	claim
24	79	On-line Adaption of Class-specific Codebooks for Instance Tracking	claim
25	78	Implicit Shape Kernel for Discriminative Learning of the Hough Transform Detector	claim
26	77	Active 3D Segmentation through Fixation of Previously Unseen Objects	claim
27	76	Feature Sets and Dimensionality Reduction for Visual Object Detection	claim
28	75	Joint Optimisation for Object Class Segmentation and Dense Stereo Reconstruction	claim
29	74	Unifying Planar and Point Mapping in Monocular SLAM	claim
30	74	Robust Camera Calibration using Inaccurate Targets	claim
31	73	Pose and Expression-Invariant 3D Face Recognition using Elastic Radial Curves	claim
32	72	Segmentation using Deformable Spatial Priors with Application to Clothing	claim
33	72	Detection of Curves with Unknown Endpoints using Minimal Path Techniques	claim
34	71	Motion Coherent Tracking with Multi-label MRF optimization	claim
35	71	Cross View Gait Recognition Using Correlation Strength	claim
36	70	Back to the Future: Learning Shape Models from 3D CAD Data	claim
37	70	Recognition from Appearance Subspaces across Image Sets of Variable Scale	claim
38	70	A 2D+t Feature-preserving Non-local Means Filter for Image Denoising and Improved Detection of Small and Weak Particles	claim
39	70	Pairwise Macropixel Comparison Can Work at Least as Well as Advanced Holistic Algorithms for Face Recognition	claim
40	69	Large-scale Dictionary Learning For Local Coordinate Coding	claim
41	68	Stratified Generalized Procrustes Analysis	claim
42	68	Skin Color Weighted Disparity Competition for Hand Segmentation from Stereo Camera	claim
43	68	Using Context to Create Semantic 3D Models of Indoor Environments	claim
44	68	Image Topic Discovery with Saliency Detection	claim
45	67	Calibration of Non-Overlapping Cameras---Application to Vision-Based Robotics	claim
46	67	Sparse Sparse Bundle Adjustment	claim
47	67	Background Modelling on Tensor Field for Foreground Segmentation	claim
48	67	Object Recognition using 3D SIFT in Complex CT Volumes	claim
49	66	Accounting for the Relative Importance of Objects in Image Retrieval	claim
50	66	Improving object classification using semantic attributes	claim
51	65	Toward Robust Action Retrieval in Video	claim
52	65	Improved Anatomical Landmark Localization in Medical Images Using Dense Matching of Graphical Models	claim
53	65	Saliency Segmentation based on Learning and Graph Cut Refinement	claim
54	65	"How old are you?" : Age Estimation with Tensors of Binary Gaussian Receptive Maps	claim
55	64	Image-based walkthroughs from incremental and partial scene reconstructions	claim
56	64	Electoral College and Direct Popular Vote for Multi-Candidate Election	claim
57	63	Three-step image rectification	claim
58	63	Automatic Facial Expression Recognition using Bags of Motion Words	claim
59	63	Multi-View Planning for Simultaneous Coverage and Accuracy Optimisation	claim
60	62	FAST: Fast Adaptive Silhouette Area based Template Matching	claim
61	62	Evaluation of dimensionality reduction methods for image auto-annotation	claim
62	61	Iterative Hyperplane Merging: A Framework for Manifold Learning	claim
63	61	Improving bag-of-features action recognition with non-local cues	claim
64	60	Manifold Alignment via Corresponding Projections	claim
65	60	Toward robust estimation of specular flow	claim
66	59	Automatic annotation of unique locations from video and text	claim
67	59	A principled approach to remove false alarms by modelling the context of a face detector	claim
68	58	Diffusion-based Regularisation Strategies for Variational Level Set Segmentation	claim
69	58	Deterministic Sample Consensus with Multiple Match Hypotheses	claim
70	58	TV-Based Multi-Label Image Segmentation with Label Cost Prior	claim
71	58	Trans Media Relevance Feedback for Image Autoannotation	claim
72	58	Label propagation in complex video sequences using semi-supervised learning	claim
73	58	StyP-Boost: A Bilinear Boosting Algorithm for Learning Style-Parameterized Classifiers	claim
74	57	Robust Texture Recognition Using Credal Classifiers	claim
75	57	Multi-class Boosting for Early Classification of Sequences	claim
76	57	Accurate and Efficient Face Recognition from Video	claim
77	56	High Five: Recognising human interactions in TV shows	claim
78	56	Joint Modeling of Algorithm Behavior and Image Quality for Algorithm Performance Prediction	claim
79	56	Localized fusion of Shape and Appearance features for 3D Human Pose Estimation	claim
80	56	Incremental Model Selection for Detection and Tracking of Planar Surfaces	claim
81	55	Isotropic Granularity-tunable gradients partition (IGGP) descriptors for human detection	claim
82	55	Additive Update Predictors in Active Appearance Models	claim
83	55	Real-time Action Recognition by Spatiotemporal Semantic and Structural Forests	claim
84	54	Inferring Image Transformation and Structure from Motion-Blurred Images	claim
85	54	Moving Camera Registration for Multiple Camera Setups in Dynamic Scenes	claim
86	54	A Novel Framework for Tracking In-vitro Cells in Time-lapse Phase Contrast Data	claim
87	54	Towards On-Line Intensity-Based Surface Recovery from Monocular Images	claim
88	53	A general boosting-based framework for active object recognition	claim
89	53	Classifying Textile Designs using Region Graphs	claim
90	52	Object Detection with Geometrical Context Feedback Loop	claim
91	52	Epipolar Constraints for Multiscale Matching	claim
92	48	Local Gaussian Processes for Pose Recognition from Noisy Inputs	claim
93	47	Probabilistic Latent Sequential Motifs: Discovering Temporal Activity Patterns in Video Scenes	claim
94	47	Person Identification using Shadow Analysis	claim
95	46	Patch-Cuts: A Graph-Based Image Segmentation Method Using Patch Features and Spatial Relations	claim
96	45	Weighted Local Bundle Adjustment and Application to Odometry and Visual SLAM Fusion	claim
97	43	Multiscale Keypoint Analysis based on Complex Wavelets	claim
98	40	Reducing mismatching under time-pressure by reasoning about visibility and occlusion	claim
99	38	Making a Shallow Network Deep: Growing a Tree from Decision Regions of a Boosting Classifier	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers