Hierarchical Convolutional Features for Visual Tracking

By Chao Ma, Jia-Bin Huang, Xiaokang Yang, Ming-Hsuan Yang. IEEE International Conference on Computer Vision, 2015

1,713 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/5c8a6874011640981e4103d120957802fa28f004

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

Video Segmentation via Object Flow (2016, methodology): “For the appearance term, we construct the color GMM in the first frame, and an online SVM model with CNN features [20] updated every frame.”
Co-Saliency Detection via a Self-Paced Multiple-Instance Learning Framework (2017, background): “all the convolutional layers in the convolutional neural network (CNN) to establish the hypercolumn feature representation [48], [49], [50] for each superpixel.”
Learning Background-Aware Correlation Filters for Visual Tracking (2017, methodology): “The excellent performance of deep convolutional neural networks (CNNs) on several challenging vision tasks [19, 31, 24, 14] has encouraged more recent works to either exploit CNN deep features within CF framework [26, 9, 11] or design deep architectures [2, 28, 34, 5, 32, 33] for robust visual track”
Multi-task Correlation Particle Filter for Robust Object Tracking (2017, methodology): “Empirical studies using large object tracking benchmark datasets show that these CNN based trackers [25, 29] perform favorably against methods based on hand-crafted features.”
Context-Aware Correlation Filter Tracking (2017, methodology): “To put the tracking performance into perspective, we compare the best performing context-aware CF trackers (SAMFCA and STAPLECA) and their baselines (SAMF [18] and STAPLE [1]) to the most recent state-of-the-art trackers (SOWP [15], HCFT [21], and MEEM [29]), which are not necessarily CF 0 0.”
Attentional Correlation Filter Network for Adaptive Visual Tracking (2017, methodology): “Similarly, for correlation filter based trackers, only some of the convolutional features are useful at a time [6,8,26,30].”
CREST: Convolutional Residual Learning for Visual Tracking (2017, methodology): “We compare our CREST tracker with 29 trackers from the OTB-2013 benchmark [45] and other 21 state-of-the-art trackers including KCF [17], MEEM [48], TGPR [13], DSST [7], RPT [27], MUSTer [20], LCT [31], HCFT [30], FCNT [42], SRDCF [9], CNN-SVM [19], DeepSRDCF [8], DAT [35], Staple [2], SRDCFdecon [1”
LaSOT: A High-quality Large-scale Single Object Tracking Benchmark (2020, methodology): “, HCFT [62], DSTRCF [50], ECO [14], GFSDCF [85], ASRCF [12]) and regularization techniques (e.”
A Twofold Siamese Network for Real-Time Object Tracking (2018, background): “Some trackers [7, 26, 30, 9, 6] integrate deep features into conventional tracking approaches and benefit from the expressive power of CNN features.”
Detect to Track and Track to Detect (2017, methodology): “Recent correlation trackers [1, 25] typically work on high-level ConvNet features and compute the cross correlation between a tracking template and the search image (or a local region around the tracked position from the previous frame).”
Adaptive Decontamination of the Training Set: A Unified Formulation for Discriminative Visual Tracking (2016, methodology): “We perform a comprehensive comparison with 17 recent state-of-the-art trackers: EDFT [7], LSHT [12], DFT [24], ASLA [15], TLD [16], Struck [11], CFLB [8], ACT [6], TGPR [9], KCF [13], DSST [2], SAMF [19], DAT [23], MEEM [29], LCT [22], HCF [21] and SRDCF [5].”
Learning Dynamic Memory Networks for Object Tracking (2018, methodology): “To further show our tracking accuracy, we also compared with another 8 recent state-of-the art trackers that are not real-time speed, including CREST [26], CSR-DCF [19], MCPF [38], SRDCFdecon [9], SINT [29], SRDCF [6], HDT [23], HCF [20] on OTB-2015.”
Probabilistic Regression for Visual Tracking (2020, methodology): “Here, wθ is the convolution kernel and φ(x) are the features extracted from the image x, typically by a CNN with frozen weights [12, 31].”
Fully-Convolutional Siamese Networks for Object Tracking (2016, methodology): “correlation filters) using the network’s internal representation as features [5,6] or perform SGD (stochastic gradient descent) to fine-tune multiple layers of the network [7–9].”
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].”
GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild (2018, methodology): “More recently, several attempts have been made to use deep learning to improve tracking performance [54], [60], [62].”
Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking (2021, background): “Discriminative correlation filter (DCF) tackles the visual tracking by solving the ridge regression in Fourier domain, which exhibits attractive efficiency [20, 35, 34, 15, 37, 53, 11, 8].”
Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking (2016, methodology): “Surprisingly, in the context of tracking, recent DCF-based methods [10,35] have”
Learning Aberrance Repressed Correlation Filters for Real-Time UAV Tracking (2019, methodology): “The results are compared with 20 state-of-the-art trackers with both hand-crafted based trackers and deep-based trackers, i.e., KCF [13], DSST [8], SAMF [18], MUSTER [14], BACF [15], SRDCF [7], STAPLE CA [21], MCCT-H [27], STRCF [16], ECO-HC (with gray-scale) [5], ECO [5], CCOT [9], HCF [19], ADNet ”