Visual Tracking with Fully Convolutional Networks

By Lijun Wang, Wanli Ouyang, Xiaogang Wang, Huchuan Lu. IEEE International Conference on Computer Vision, 2015

989 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Global and Planetary Change

View Paper: https://www.semanticscholar.org/paper/bf94906f0d7a8ca9da5f6b86e2a476fde1a34dd0

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

In Global and Planetary Change

Citations in the corpus

Learning to Detect Salient Objects with Image-Level Supervision (2017, background): “Driven by the remarkable success of deep neural networks (DNNs) in many computer vision areas [23, 14, 11, 47, 48], there has been a recent surge of interests in training DNNs using samples with accurate pixel-level annotations for saliency detection [57, 26, 49].”
Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection (2017, background): “Several works on visualizing deep CNNs [36, 49, 30, 43] indicate that convolutional features at different levels describe the object and its surroundings from different views.”
Track and Segment: An Iterative Unsupervised Approach for Video Object Proposals (2016, neutral): “SCM [59] Struck [20] TLD [26] ASLA [25] CXT [12] VTD [30] VTS [31] TGPR [17] RPT [34] [52] [35] Ours”
Unveiling the Power of Deep Tracking (2018, methodology): “We compare our method with the following state-of-the-art methods: CCOT [7], ECO [1], MDNet [13], HDT [20], FCNT [12], SRDCF [18], DeepSRDCF [40], BACF [41], Staple [3], MEEM [4], HCF [8], SAMF [42], DSST [43], MUSTER [25], Struck [44], and ASLA [45].”
Online Multi-object Tracking Using CNN-Based Single Object Tracker with Spatial-Temporal Attention Mechanism (2017, background): “Since deep convolutional neural networks (CNNs) are shown to be effective in many computer vision applications [27, 15, 36, 35, 57, 54], many works [47, 19, 31, 48] have explored the usage of CNNs to learn strong discriminative appearance model in single object tracking and demonstrated state-of-the”
Need for Speed: A Benchmark for Higher Frame Rate Object Tracking (2017, methodology): “7, cheaper trackers on higher frame rate video (e.g. KCF and Staple) have been demonstrated as competitive with many deep trackers on lower frame rate videos (such as HDT and FCNT).”
Discriminative Correlation Filter Tracker with Channel and Spatial Reliability (2016, methodology): “The set is indeed diverse, the top-performing trackers come from various classes e.g., correlation ﬁlter methods (CCOT [13], Staple [2], DDC [25]), deep ConvNets (TCNN [25], SSAT[25, 37], MLDF [25, 40], FastSiamnet [3]) and different detection-Overall based approaches (EBT [47], SRBT [25]).”
Learning Attentions: Residual Attentional Siamese Network for High Performance Online Visual Tracking (2018, methodology): “Recently, deep learning models [8,36,43,49], have become an essential oracle to improve the tracking accuracy, mainly due to their large model capacities and strong feature learning abilities.”
Large Margin Object Tracking with Circulant Feature Maps (2017, methodology): “Recent studies [27, 21, 28, 23, 15] have shown state-of-the-art re-sults on many object tracking benchmarks.”
Video Object Detection with an Aligned Spatial-Temporal Memory (2017, background): “o classiﬁcation [25,45,37,48,4]. These methods tend to model entire video frames instead of pixels, which means the ﬁne-grained details required for localizing objects are often lost. Object tracking [20,30,53, 36,34,43,28], which requires accurate localization, is also closely-related. The key diff”
Attentional Correlation Filter Network for Adaptive Visual Tracking (2017, methodology): “Deep learning based trackers: Recent works based on online deep learning trackers have shown high performance [29, 33, 35, 36].”
FusionSeg: Learning to Combine Motion and Appearance for Fully Automatic Segmentation of Generic Objects in Videos (2017, methodology): “Deep learning with motion Deep learning for combining motion and appearance in videos has proven to be useful in several other computer vision tasks such as video classification [32, 22], action recognition [43, 20], object tracking [25, 52, 29] and even computation of optical flow [8].”
Learning Dynamic Memory Networks for Object Tracking (2018, background): “Along with the success of convolution neural networks in object recognition and detection, an increasing number of trackers [4, 13, 22, 26, 31] have adopted deep learning models for visual object tracking.”
TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild (2018, background): “For instance, Siamese-like architectures [34, 15] need to observe a large number of similar and dissimilar patches of the same object.”
A Survey on Deep Learning Technique for Video Segmentation (2021, methodology): “Inspired by the advance in visual tracking [190], Yoon et al.”
Object Detection in Videos with Tubelet Proposal Networks (2017, background): “…GoogLeNet [27], VGG [25] and ResNet [8], were proposed to improve the learning capability on large-scale computer vision datasets for various computer vision tasks, such as object detection [5, 22, 21, 19], semantic segmentation [18, 2, 15], tracking [29, 1, 30], scene understanding [23, 24] etc .”
Modeling and Propagating CNNs in a Tree Structure for Visual Tracking (2016, methodology): “The proposed algorithm is compared with the eight state-of-the-art trackers including HCT [26], CNN-SVM [14], FCNT [34], SRDCF [7], MUSTer [15], MEEM [38], DSST [5], and Struck [12].”
Computer vision and deep learning techniques for pedestrian detection and tracking: A survey (2018, background): “Recent researches in Artiﬁcial Intelligence (AI) led to the spread of modern techniques of machine learning based in deep structures, as reported in novel and innovative works, [110,111,114,117,118,186–188] .”