#### Filter Results:

- Full text PDF available (7)

#### Publication Year

2013

2017

- This year (2)
- Last 5 years (9)
- Last 10 years (9)

#### Publication Type

#### Co-author

#### Journals and Conferences

#### Data Set Used

#### Key Phrases

Learn More

- Mahyar Najibi, Mohammad Rastegari, Larry S. Davis
- 2016 IEEE Conference on Computer Vision and…
- 2016

We introduce G-CNN, an object detection technique based on CNNs which works without proposal algorithms. G-CNN starts with a multi-scale grid of fixed bounding boxes. We train a regressor to move and scale elements of the grid towards objects iteratively. G-CNN models the problem of object detection as finding a path from a fixed grid to boxes tightly… (More)

- Mahyar Najibi, Pouya Samangouei, Rama Chellappa, Larry S. Davis
- ArXiv
- 2017

We introduce the Single Stage Headless (SSH) face detector. Unlike two stage proposal-classification detectors, SSH detects faces in a single stage directly from the early convolutional layers in a classification network. SSH is headless. That is, it is able to achieve state-of-the-art results while removing the “head” of its underlying classification… (More)

- Amirreza Shaban, Hamid R. Rabiee, Mahyar Najibi
- ArXiv
- 2013

- Mahyar Najibi, Fan Yang, Qiaosong Wang, Robinson Piramuthu
- ArXiv
- 2017

In this work, we propose an efficient and effective approach for unconstrained salient object detection in images using deep convolutional neural networks. Instead of generating thousands of candidate bounding boxes and refining them, our network directly learns to generate the saliency map containing the exact number of salient objects. During training, we… (More)

Data coding as a building block of several image processing algorithms has been received great attention recently. Indeed, the importance of the locality assumption in coding approaches is studied in numerous works and several methods are proposed based on this concept. We probe this assumption and claim that taking the similarity between a data point and a… (More)

- Amirreza Shaban, Hamid R. Rabiee, Mahyar Najibi, Safoora Yousefi
- IEEE Transactions on Image Processing
- 2015

Feature coding has received great attention in recent years as a building block of many image processing algorithms. In particular, the importance of the locality assumption in coding approaches has been studied in many previous works. We review this assumption and claim that using the similarity of data points to a more global set of anchor points does not… (More)

- Bahadir Ozdemir, Mahyar Najibi, Larry S. Davis
- ArXiv
- 2016

We propose an incremental strategy for learning hash functions with kernels for largescale image search. Our method is based on a two-stage classification framework that treats binary codes as intermediate variables between the feature space and the semantic space. In the first stage of classification, binary codes are considered as class labels by a set of… (More)

- Bahadir Ozdemir, Mahyar Najibi, Larry S. Davis
- BMVC
- 2016

where w ∈ Rd denotes the weight vector to be learned, 2‖w‖ 2 is a quadratic regularization term, C > 0 is a fixed regularization constant and R : Rd → R is a non-negative convex risk function e.g. hinge loss on training data, R(w) = ∑i=1 max(0,1− yiwxi). The cutting plane method approximates the convex function F(w) by a piecewise linear function Ft(w) with… (More)

- Mahyar Najibi, Mohammad Rastegari, Larry S. Davis
- ArXiv
- 2015

The growing amount of data available in modern-day datasets makes the need to efficiently search and retrieve information. To make large-scale search feasible, Distance Estimation and Subset Indexing are the main approaches. Although binary coding has been popular for implementing both techniques, n-ary coding (known as Product Quantization) is also very… (More)

- ‹
- 1
- ›