Histograms of Sparse Codes for Object Detection

By Xiaofeng Ren, Deva Ramanan. 2013

252 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation (2013, background): “However there is a considerable drawback in terms of compute time, with the forward pass of O-Net taking roughly 7 times longer than T-Net.”
Deformable part models are convolutional neural networks (2014, methodology): “At test time, a DPM is run as a sliding-window detector over a feature pyramid, which is traditionally built using HOG features (alternatives have recently been explored in [24, 26]).”
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition (2013, background): “Recent results have shown that moderately deep unsupervised models outperform the state-of-the art gradient histogram features in part-based detection models (Ren & Ramanan, 2013).”
Computational Baby Learning (2014, methodology): “We compare our method with the state-of-the-art baselines, including DPM HSC [20], Regionlets [26], SegDPM [11] and R-CNN [12].”
YOLACT: Real-Time Instance Segmentation (2019, neutral): “Others have designed prototypes for object detection [1, 45, 38].”
End-to-end integration of a Convolutional Network, Deformable Parts Model and non-maximum suppression (2014, neutral): “ 27.2 10.2 34.8 30.2 28.2 46.6 41.7 26.2 10.3 32.8 26.8 39.8 47.0 30.5 HoG-dpm(v5) [5] 33.2 60.3 10.2 16.1 27.3 54.3 58.2 23.0 20.0 24.1 26.7 12.7 58.1 48.2 43.2 12.0 21.1 36.1 46.0 43.5 33.7 HSC-dpm [12] 32.2 58.3 11.5 16.3 30.6 49.9 54.8 23.5 21.5 27.7 34.0 13.7 58.1 51.6 39.9 12.4 23.5 34.4 47.4 ”
Relationship Matters: Relation Guided Knowledge Transfer for Incremental Learning of Object Detectors (2020, background): “There is a continued interest in the vision community on learning object detection models using deep CNNs [10, 9, 11] as they significantly outperform traditional methods [8, 33, 41].”
Articulated pose estimation with tiny synthetic videos (2015, background): “As a result, modern image features are based on normalized edge-orientations ([7], [20]) or gabor-like filter responses ([28], [16]).”
Object Detection With Deep Learning: A Review (2018, background): “3% with more than 30% improvement over the previous best result (DPM HSC [77]) on PASCAL VOC 2012.”
Region-Based Convolutional Networks for Accurate Object Detection and Segmentation (2016, methodology): “To compute an HSC, sparse code activations are solved for at each pixel using a learned dictionary of 100 7 Â 7 pixel (grayscale) atoms.”
30Hz Object Detection with DPM V5 (2014, background): “HOG pyramid [5] and histogram of sparse codes [19]) and evaluate a given template at all scales.”
DeepID-Net: Object Detection with Deformable Part Based Convolutional Neural Networks (2017, methodology): “[78] [79] [80] [81] [75] [6] [1] [1] [48] [49] [51] [46]”
Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks (2014, background): “It is therefore possible that these manually designed pipelines only outperformed earlier CNNs because CNNs are hard to train using small datasets.”
Unsupervised feature learning for 3D scene labeling (2014, methodology): “As was the case in [16], using sparse coding features learned from image data is usually slightly better than using HOG features.”
Modeling Image Patches with a Generic Dictionary of Mini-epitomes (2014, unknown): “The power of learned patch-level features has also been demonstrated recently in [5, 9, 24].”
Filtered channel features for pedestrian detection (2015, background): “Etc.) Other features include bag-of-words over colour, HOG, or LBP features [4]; learning sparse dictionary encoders [32]; and training features via a convolutional neural network [34].”
Learning Deep Representation with Large-Scale Attributes (2015, background): “Many existing works are included for comparison [12, 30, 40, 38, 10, 11, 14, 13].”
Sparse Modeling for Image and Vision Processing (2014, methodology): “Similar to Rigamonti et al. [2013], the motivation of Hawe et al.”