Open AccessProceedings Article
Multi-view multi-class object detection via exemplar compounding
Kai Ma,Jezekiel Ben-Arie +1 more
- pp 3256-3259
Reads0
Chats0
TLDR
VARIS is able to find optimal similarity matching between the input image and pre-stored exemplars while allowing wide geometrical variations which are limited only by topology constraints.Abstract:
To address the multi-view multi-class object detection problem, we propose a method named Vector Array Recognition by Indexing and Sequencing (VARIS). VARIS is able to find optimal similarity matching between the input image and pre-stored exemplars while allowing wide geometrical variations which are limited only by topology constraints. Aggregated similarity is further enhanced by matching the input image with compound exemplars. The exemplar compounding procedure also reduces the number of exemplars necessary for each class. Our experiments show that VARIS with exemplar compounding achieves state-of-the-art performance on PASCAL VOC2007 dataset with a reasonable computational cost.read more
Citations
More filters
Proceedings Article
Multimodality and Dialogue Act Classification in the RoboHelper Project
Lin Chen,Barbara Di Eugenio +1 more
TL;DR: The annotation of a multimodal corpus that includes pointing gestures and haptic actions (force exchanges) is described, and results show that multi-modal features and the dialogue game aid in DA classification.
Journal ArticleDOI
The roles and recognition of Haptic-Ostensive actions in collaborative multimodal human-human dialogues
TL;DR: The last part of the paper presents additional experiments on recognizing H-O actions from the haptic signals measured through the sensory glove, and shows that even though pressure sensors are relatively imprecise and the data provided by the glove is noisy, the classification algorithms can successfully identify actions of interest within subjects.
Proceedings ArticleDOI
Compound exemplar based object detection by incremental random forest
Kai Ma,Jezekiel Ben-Arie +1 more
TL;DR: This paper describes a new hybrid detection method that combines exemplar based approach with discriminative patch selection, and applies a modified random forest for retrieval of input similar local patches of stored exemplars while rejecting background patches.
Proceedings ArticleDOI
Using pressure sensors to identify manipulation actions during human physical interaction
TL;DR: It is shown that pressure sensor data can be used to automatically recognize physical manipulation actions, and may facilitate future studies of multimodal interaction by greatly reducing the time required for manual annotations.
References
More filters
Proceedings ArticleDOI
Histograms of oriented gradients for human detection
Navneet Dalal,Bill Triggs +1 more
TL;DR: It is shown experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection, and the influence of each stage of the computation on performance is studied.
Journal ArticleDOI
Object Detection with Discriminatively Trained Part-Based Models
TL;DR: An object detection system based on mixtures of multiscale deformable part models that is able to represent highly variable object classes and achieves state-of-the-art results in the PASCAL object detection challenges is described.
Proceedings ArticleDOI
Object class recognition by unsupervised scale-invariant learning
TL;DR: The flexible nature of the model is demonstrated by excellent results over a range of datasets including geometrically constrained classes (e.g. faces, cars) and flexible objects (such as animals).
Proceedings ArticleDOI
Poselets: Body part detectors trained using 3D human pose annotations
Lubomir Bourdev,Jitendra Malik +1 more
TL;DR: A new dataset, H3D, is built of annotations of humans in 2D photographs with 3D joint information, inferred using anthropometric constraints, to address the classic problems of detection, segmentation and pose estimation of people in images with a novel definition of a part, a poselet.