Dense Feature Aggregation and Pruning for RGBT Tracking
Explore this paper's citation graph
Summary
This paper presents a novel deep fusion algorithm based on the representations from an end-to-end trained convolutional neural network that achieves clear state-of-the-art against other RGB and RGBT tracking methods.
- Type
- article
- Published
- 2019-07-24
- Cited by
- 218
- References
- 47
- Access
- Open access
- OpenAlex
- https://openalex.org/W2963188742
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:198229527
Keywords
Boosting (machine learning), Convolutional neural network, Complementarity (molecular biology), Pooling, Pattern recognition (psychology)
References
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Learning Multi-domain Convolutional Neural Networks for Visual Tracking
- Learning Spatially Regularized Correlation Filters for Visual Tracking
- Weighted random sampling with a reservoir
- Gradient-based shape descriptors
- Thermo-visual feature fusion for object tracking using multiple spatiogram trackers
- Accurate Scale Estimation for Robust Visual Tracking
- Fusion tracking in color and infrared images using joint sparse representation
- Comparison of Fusion Methods for Thermo-Visual Surveillance Tracking
- Multiple source data fusion via sparse representation for robust visual tracking
- Learning a similarity metric discriminatively, with application to face verification
- SOWP: Spatially Ordered and Weighted Patch Descriptor for Visual Tracking
- Learning Deep Features for Discriminative Localization
- Hedged Deep Tracking
- Learning Collaborative Sparse Representation for Grayscale-Thermal Tracking
- ECO: Efficient Convolution Operators for Tracking
- Grayscale-Thermal Object Tracking via Multitask Laplacian Sparse Representation
- Learning Background-Aware Correlation Filters for Visual Tracking
- End-to-End Representation Learning for Correlation Filter Based Tracking
- Attentional Correlation Filter Network for Adaptive Visual Tracking
Cited by
- Improved Hard Example Mining by Discovering Attribute-based Hard Person Identity
- Deep Adaptive Fusion Network for High Performance RGBT Tracking
- Object Tracking in RGB-T Videos Using Modal-Aware Attention Network and Competitive Learning
- M5L: Multi-Modal Multi-Margin Metric Learning for RGBT Tracking
- Quality-Aware Feature Aggregation Network for Robust RGBT Tracking
- Object fusion tracking based on visible and infrared images: A comprehensive review
- Cross-Modal Pattern-Propagation for RGB-T Tracking
- Jointly Modeling Motion and Appearance Cues for Robust RGB-T Tracking
- Challenge-Aware RGBT Tracking
- S2SiamFC: Self-supervised Fully Convolutional Siamese Network for Visual Tracking
- Methods for Pruning Deep Neural Networks
- RGBT Tracking via Multi-Adapter Network with Hierarchical Divergence Loss
- Duality-Gated Mutual Condition Network for RGBT Tracking
- Multi-modal visual tracking: Review and experimental comparison
- SiamCDA: Complementarity- and Distractor-Aware RGB-T Tracking Based on Siamese Network
- RGBT Tracking via Noise-Robust Cross-Modal Ranking
- Dual Siamese network for RGBT tracking via fusing predicted position maps
- LasHeR: A Large-Scale High-Diversity Benchmark for RGBT Tracking
- Using Artificial Neural Network to Detect Fetal Alcohol Spectrum Disorder in Children
- Robust Multi-Modality Person Re-identification
Related papers
No related papers recorded.