This paper describes a discriminatively trained, multiscale, deformable part model for object detection. Our system achieves a two-fold improvement in average. This paper describes a discriminatively trained, multi- scale, deformable part model for object detection. Our sys- tem achieves a two-fold. “A discriminatively trained, multiscale, deformable part model.” Computer Vision and Pattern Recognition, CVPR IEEE Conference on. IEEE,
|Published (Last):||3 December 2007|
|PDF File Size:||2.67 Mb|
|ePub File Size:||8.10 Mb|
|Price:||Free* [*Free Regsitration Required]|
Skip to search form Skip to main content. Felzenszwalb and David A.
A discriminatively trained, multiscale, deformable part model
FelzenszwalbDavid A. This paper describes a discriminatively trained, multiscale, deformable part model for object detection. Our system achieves a two-fold improvement in average precision over the best performance in the PASCAL person detection challenge.
It also outperforms the best results in the challenge in ten out of twenty categories. The system relies heavily discrkminatively deformable parts. This paper has highly influenced other papers.
This paper has 2, citations.
A Discriminatively Trained, Multiscale, Deformable Part Model | BibSonomy
From This Paper Topics from this paper. Topics Discussed in This Paper. Discriminative model Data mining Object detection.
Pascal Information retrieval Semantics computer science. Semiconductor industry Latent Dirichlet allocation Conditional random field. Citations Publications citing this paper.
A discriminatively trained, multiscale, deformable part model – Semantic Scholar
Showing of 1, extracted citations. CorsoKhurshid A. Face detection based on deep convolutional neural networks exploiting incremental facial part learning Danai TriantafyllidouAnastasios Tefas 23rd International Conference on Pattern….
Fast moving pedestrian detection based on motion segmentation and new motion features Shanshan ZhangDominik A. KleinChristian BauckhageArmin B. Cremers Multimedia Tools and Applications Citation Statistics 2, Citations 0 ’10 ’13 ’16 ‘ Semantic Scholar estimates that this publication has 2, citations based on the available data. See our Aprt for additional information.