Iskalni niz:
išči po
išči po
išči po
išči po
Vrsta gradiva:
Jezik:
Št. zadetkov: 6
Exact Acceleration of Linear Object Detectors
Charles Dubout , Antonio Torralba , Stefan Carlsson
Video in druga učna gradiva
Oznake: computer science;computer vision;object recognition
We describe a general and exact method to considerably speed up linear object detection systems operating in a sliding, multi-scale window fashion, such as the individual part detectors of part-based models. The main bottleneck of many of those systems is the computational cost of the convolutions b ...
Leto: 2012 Vir: videolectures.net
Diagnosing Error in Object Detectors
Derek Hoiem , Antonio Torralba , Stefan Carlsson
Video in druga učna gradiva
Oznake: computer science;computer vision;object recognition
This paper shows how to analyze the influences of object characteristics on detection performance and the frequency and impact of different types of false positives. In particular, we examine effects of occlusion, size, aspect ratio, visibility of parts, viewpoint, localization error, and confusion ...
Leto: 2012 Vir: videolectures.net
Using linking features in learning non-parametric part models
Leonid Karlinsky , Antonio Torralba , Stefan Carlsson
Video in druga učna gradiva
Oznake: computer science;computer vision;object recognition
We present an approach to the detection of parts of highly deformable objects, such as the human body. Instead of using kinematic constraints on relative angles used by most existing approaches for modeling part-to-part relations, we learn and use special observed 'linking' features that support par ...
Leto: 2012 Vir: videolectures.net
Attributes for classifier feedback
Devi Parikh , Antonio Torralba , Stefan Carlsson
Video in druga učna gradiva
Oznake: computer science;computer vision
Traditional active learning allows a (machine) learner to query the (human) teacher for labels on examples it finds confusing. The teacher then provides a label for only that instance. This is quite restrictive. In this paper, we propose a learning paradigm in which the learner communicates its beli ...
Leto: 2012 Vir: videolectures.net
Latent Hough Transform for Object Detection
Nima Razavi , Antonio Torralba , Stefan Carlsson
Video in druga učna gradiva
Oznake: computer science;computer vision;object recognition
Hough transform based methods for object detection work by allowing image features to vote for the location of the object. While this representation allows for parts observed in different training instances to support a single object hypothesis, it also produces false positives by accumulating votes ...
Leto: 2012 Vir: videolectures.net
Constrained Semi-Supervised Learning using Attributes and Comparative Attributes
Abhinav Shrivastava , Antonio Torralba , Stefan Carlsson
Video in druga učna gradiva
Oznake: computer science;computer vision;machine learning;semi-supervised learning
We consider the problem of semi-supervised bootstrap learning for scene categorization. Existing semi-supervised approaches are typically unreliable and face semantic drift because the learning task is under-constrained. This is primarily because they ignore the strong interactions that often exist ...
Leto: 2012 Vir: videolectures.net
Št. zadetkov: 6
Ključne besede:
Leto izdaje:
Repozitorij:
Tipologija:
Jezik: