Toward Category-Level Object Recognition

Joseph L. Mundy (auth.), Jean Ponce, Martial Hebert, Cordelia Schmid, Andrew Zisserman (eds.)9783540687948, 3540687947

Although research in computer vision for recognizing 3D objects in photographs dates back to the 1960s, progress was relatively slow until the turn of the millennium, and only now do we see the emergence of effective techniques for recognizing object categories with different appearances under large variations in the observation conditions. Tremendous progress has been achieved in the past five years, thanks largely to the integration of new data representations, such as invariant semi-local features, developed in the computer vision community with the effective models of data distribution and classification procedures developed in the statistical machine-learning community.

This volume is a post-event proceedings volume and contains selected papers based on presentations given, and vivid discussions held, during two workshops held in Taormina in 2003 and 2004. The main goals of these two workshops were to promote the creation of an international object recognition community, with common datasets and evaluation procedures, to map the state of the art and identify the main open problems and opportunities for synergistic research, and to articulate the industrial and societal needs and opportunities for object recognition research worldwide.

The 30 thoroughly revised papers presented are organized in the following topical sections: recognition of specific objects, recognition of object categories, recognition of object categories with geometric relations, and joint recognition and segmentation.

Table of contents :
Front Matter….Pages –
Front Matter….Pages 1-1
Object Recognition in the Geometric Era: A Retrospective….Pages 3-28
Dataset Issues in Object Recognition….Pages 29-48
Industry and Object Recognition: Applications, Applied Research and Challenges….Pages 49-64
Front Matter….Pages 65-65
What and Where: 3D Object Recognition with Accurate Pose….Pages 67-82
Object Recognition Using Local Affine Frames on Maximally Stable Extremal Regions….Pages 83-104
3D Object Modeling and Recognition from Photographs and Image Sequences….Pages 105-126
Video Google: Efficient Visual Search of Videos….Pages 127-144
Simultaneous Object Recognition and Segmentation by Image Exploration….Pages 145-169
Front Matter….Pages 171-171
Comparison of Generative and Discriminative Techniques for Object Detection and Classification….Pages 173-195
Synergistic Face Detection and Pose Estimation with Energy-Based Models….Pages 196-206
Generic Visual Categorization Using Weak Geometry….Pages 207-224
Components for Object Detection and Identification….Pages 225-237
Cross Modal Disambiguation….Pages 238-257
Translating Images to Words for Recognizing Objects in Large Image and Video Collections….Pages 258-276
A Semi-supervised Learning Approach to Object Recognition with Spatial Integration of Local Features and Segmentation Cues….Pages 277-300
Towards the Optimal Training of Cascades of Boosted Ensembles….Pages 301-320
Visual Classification by a Hierarchy of Extended Fragments….Pages 321-344
Shared Features for Multiclass Object Detection….Pages 345-361
Generative Models for Labeling Multi-object Configurations in Images….Pages 362-381
Object Detection and Localization Using Local and Global Features….Pages 382-400
Front Matter….Pages 171-171
The Trace Model for Object Detection and Tracking….Pages 401-420
Front Matter….Pages 421-421
A Discriminative Framework for Texture and Object Recognition Using Local Image Features….Pages 423-442
A Sparse Object Category Model for Efficient Learning and Complete Recognition….Pages 443-461
Object Recognition by Combining Appearance and Geometry….Pages 462-482
Shape Matching and Object Recognition….Pages 483-507
An Implicit Shape Model for Combined Object Categorization and Segmentation….Pages 508-524
Statistical Models of Shape and Texture for Face Recognition….Pages 525-542
Front Matter….Pages 543-543
Image Parsing: Unifying Segmentation, Detection, and Recognition….Pages 545-576
Sequential Learning of Layered Models from Video….Pages 577-595
An Object Category Specific mrf for Segmentation….Pages 596-616
Back Matter….Pages –