Leveraging Tacit Information Embedded in CNN Layers for Visual Tracking
arXiv:2010.01204
Abstract
Different layers in CNNs provide not only different levels of abstraction for describing the objects in the input but also encode various implicit information about them. The activation patterns of different features contain valuable information about the stream of incoming images: spatial relations, temporal patterns, and co-occurrence of spatial and spatiotemporal (ST) features. The studies in visual tracking literature, so far, utilized only one of the CNN layers, a pre-fixed combination of them, or an ensemble of trackers built upon individual layers. In this study, we employ an adaptive combination of several CNN layers in a single DCF tracker to address variations of the target appearances and propose the use of style statistics on both spatial and temporal properties of the target, directly extracted from CNN layers for visual tracking. Experiments demonstrate that using the additional implicit data of CNNs significantly improves the performance of the tracker. Results demonstrate the effectiveness of using style similarity and activation consistency regularization in improving its localization and scale accuracy.
ACCV 2020 Camera Ready Extended Version
References in corpus (9)
- Two-Stream Convolutional Networks for Action Recognition in Videos
- Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking
- Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network
- Modeling and Propagating CNNs in a Tree Structure for Visual Tracking
- Transferring Rich Feature Hierarchies for Robust Visual Tracking
- Learning Background-Aware Correlation Filters for Visual Tracking
- Deep convolutional filter banks for texture recognition and segmentation
- What have we learned from deep representations for action recognition?
- Object Detection, Tracking, and Motion Segmentation for Object-level Video Segmentation