Transferring Rich Feature Hierarchies for Robust Visual Tracking
arXiv:1501.04587
Abstract
Convolutional neural network (CNN) models have demonstrated great success in various computer vision tasks including image classification and object detection. However, some equally important tasks such as visual tracking remain relatively unexplored. We believe that a major hurdle that hinders the application of CNN to visual tracking is the lack of properly labeled training data. While existing applications that liberate the power of CNN often need an enormous amount of training data in the order of millions, visual tracking applications typically have only one labeled example in the first frame of each video. We address this research issue here by pre-training a CNN offline and then transferring the rich feature hierarchies learned to online tracking. The CNN is also fine-tuned during online tracking to adapt to the appearance of the tracked target specified in the first video frame. To fit the characteristics of object tracking, we first pre-train the CNN to recognize what is an object, and then propose to generate a probability map instead of producing a simple class label. Using two challenging open benchmarks for performance evaluation, our proposed tracker has demonstrated substantial improvement over other state-of-the-art trackers.
References in corpus (2)
Cited by in corpus (38)
- Empirical Evaluation of Rectified Activations in Convolutional Network
- Discriminative Correlation Filter with Channel and Spatial Reliability
- Learning feed-forward one-shot learners
- Distilled Siamese Networks for Visual Tracking
- BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
- Siamese Instance Search for Tracking
- Deep Reinforcement Learning for Visual Object Tracking in Videos
- Learning Multi-Domain Convolutional Neural Networks for Visual Tracking
- Understanding and Diagnosing Visual Tracking Systems
- Tracking Randomly Moving Objects on Edge Box Proposals
- Beyond Local Search: Tracking Objects Everywhere with Instance-Specific Proposals
- TRAT: Tracking by Attention Using Spatio-Temporal Features
- Fully-Convolutional Siamese Networks for Object Tracking
- Recurrent Convolutional Neural Network Regression for Continuous Pain Intensity Estimation in Video
- Multiple People Tracking Using Hierarchical Deep Tracklet Re-identification
- SPM-Tracker: Series-Parallel Matching for Real-Time Visual Object Tracking
- Deep Learning of Appearance Models for Online Object Tracking
- Multi-level CNN for lung nodule classification with Gaussian Process assisted hyperparameter optimization
- Recurrent Filter Learning for Visual Tracking
- Online Object Tracking, Learning and Parsing with And-Or Graphs
- Factors in Finetuning Deep Model for object detection
- Densely Connected Recurrent Residual (Dense R2UNet) Convolutional Neural Network for Segmentation of Lung CT Images
- Deep Lesion Tracker: Monitoring Lesions in 4D Longitudinal Imaging Studies
- Towards a Principled Integration of Multi-Camera Re-Identification and Tracking through Optimal Bayes Filters
- High Performance Visual Object Tracking with Unified Convolutional Networks
- Keyfilter-Aware Real-Time UAV Object Tracking
- Feature Selection Convolutional Neural Networks for Visual Tracking
- Fast Dynamic Convolutional Neural Networks for Visual Tracking
- Tracking using Numerous Anchor points
- Pixel-wise object tracking
- End-to-End Multi-Object Tracking with Global Response Map
- Continuity-Discrimination Convolutional Neural Network for Visual Object Tracking
- Shallow Cue Guided Deep Visual Tracking via Mixed Models
- CAN: Composite Appearance Network for Person Tracking and How to Model Errors in a Tracking System
- Attention-Mechanism-based Tracking Method for Intelligent Internet of Vehicles
- Leveraging Tacit Information Embedded in CNN Layers for Visual Tracking
- Spherical U-Net on Cortical Surfaces: Methods and Applications
- A Universal Update-pacing Framework For Visual Tracking