Robust Superpixel Tracking

By Fan Yang, Huchuan Lu, Ming-Hsuan Yang. IEEE Transactions on Image Processing, 2014

318 citations recorded by the source corpus.

How researchers see this paper

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

Visual Tracking with Fully Convolutional Networks (2015, unknown): “In discriminative models, tracking is cast as a foreground and background separation problem [24, 37, 34].”
Transferring Rich Feature Hierarchies for Robust Visual Tracking (2015, methodology): “Note that this approach shares the same spirit as that in [34] which is also based on a conﬁdence map.”
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 [43].”
Superpixels: An evaluation of the state-of-the-art (2016, methodology): “…algorithms around 2009, they have been applied to many important problems in computer 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…”
Multi-Target Multi-Camera Tracking by Tracklet-to-Target Assignment (2020, background): “For the ﬁrst step, the generation of local tracklets within a single camera is referred to as the single camera multi-target tracking task [18], [44]–[47], which has been intensively studied in computer vision and pattern recognition communities [3], [48]–[50].”