Object detection by labeling superpixels

By Junjie Yan, Yinan Yu, Xiangyu Zhu, Zhen Lei, S. Li. 2015

109 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

Citations in the corpus

Learning Non-maximum Suppression (2017, methodology): “[37, 5] combine detections with semantic labelling, while [36] rephrase detection as a labelling problem.”
CRAFT Objects from Images (2016, methodology): “[24, 36] find that using the CNN to shrink the proposals generated by grouping style proposals leads to performance gain.”
DenseBox: Unifying Landmark Localization with End to End Object Detection (2015, background): “However, most state-of-the-art object detection approaches [26, 20, 8, 14, 41] rely on R-CNN, which divides detection into two steps: salient object proposal generation and region proposal classiﬁcation.”
Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes (2016, methodology): “Early approaches constrained their output to a bottom-up segmentation followed by a CNN based region classification [54].”
Factors in Finetuning Deep Model for Object Detection with Long-Tail Distribution (2016, methodology): “2 We also include the recent approach in [43].”
Chained Cascade Network for Object Detection (2017, result): “We compare our framework with several other state-of-art approaches [11, 33, 14, 20, 36, 13, 41].”
Ship Rotated Bounding Box Space for Ship Extraction From High-Resolution Optical Satellite Images With Complex Backgrounds (2016, methodology): “Here, we compare four labeling ways for ship detection, including labeling pixels [2], [3], [5], superpixels [13], bounding boxes [6]–[10], and rotated bounding boxes [11], [12].”
Pooling Methods in Deep Neural Networks, a Review (2020, background): “…efficiency, super-pixel has become a midlevel image representation and is widely used in computer vision algorithms such as object detection [29, 30], semantic segmentation [31-34], saliency estimation [35-38], optical flow estimation [39, 40], depth estimation [41, 42], and object tracking…”
Quantization Mimic: Towards Very Tiny CNN for Object Detection (2018, background): “The target of object detection [5,6,7,8,9,10] is to locate and classify the objects in images.”
T-CNN: Tubelets With Convolutional Neural Networks for Object Detection From Videos (2016, background): “State-of-the-art methods for detecting objects of general classes are mainly based on deep CNNs [1], [3], [4], [5], [8], [10], [11], [12], [13], [14], [15], [16], [17].”
Face Alignment in Full Pose Range: A 3D Total Solution (2015, unknown): “CNN has been proved of excellent capability to extract useful information from images with large variations in object detection [48] and image classification [40].”
Multi-scale Patch Aggregation (MPA) for Simultaneous Detection and Segmentation (2016, background): “This concept was extensively explored in mid-level representation work [1, 7, 36] and found useful to extract and organize structural information.”
DeepID-Net: Object Detection with Deformable Part Based Convolutional Neural Networks (2017, methodology): “Because of the power on learning feature representation, deep models have been widely used for object recognition, detection and other vision tasks [1], [6], [7], [19], [20], [21], [29], [30], [31], [32], [33], [34], [35], [36], [37], [38], [38], [39], [40], [41], [42], [43], [44], [45], [46], [47],”
Superpixels: An evaluation of the state-of-the-art (2016, background): “…vision: tracking [10, 11], stereo and occlusion [12, 13], 3D-reconstruction [14], saliency [15], object detection [16, 17], depth recovery [18] and depth estimation [19], indoor scene understanding [20], scene ﬂow [21], and as basis for convolutional neural networks [22] to name just a few.”
A Convnet for Non-maximum Suppression (2015, background): “Yao et al. (2012) and Dai et al. (2015) refine detections by linking them with semantic labelling; while Yan et al. (2015) side-steps NMS all-together by defining the detection task directly as a labelling problem.”
Learning Chained Deep Features and Classifiers for Cascade in Object Detection (2017, result): “We compare our framework with several other state-of-art approaches [13, 28, 15, 18, 32, 14, 35].”