paper-with-me

홈 › Papers

Multi-Target Tracking with Transferable Convolutional Neural Networks

2022-10-27 · Damian Owerko, Charilaos I. Kanatsoulis, Jennifer Bondarchuk, Donald J. Bucci Jr, Alejandro Ribeiro

Multi-target tracking (MTT) is a classical signal processing task, where the goal is to estimate the states of an unknown number of moving targets from noisy sensor measurements. In this paper, we revisit MTT from a deep learning perspective and propose a convolutional neural network (CNN) architecture to tackle it. We represent the target states and sensor measurements as images and recast the problem as an image-to-image prediction task. Then we train a fully convolutional model at small tracking areas and transfer it to much larger areas with numerous targets and sensors. This transfer learning approach enables MTT at a large scale and is also theoretically supported by our novel analysis that bounds the generalization error. In practice, the proposed transferable CNN architecture outperforms random finite set filters on the MTT task with 10 targets and transfers without re-training to a larger MTT task with 250 targets with a 29% performance improvement.

📄 PDF Abstract BibTeX arXiv:2210.15539

Code (1)

damowerko/mtt 공식 구현 pytorch

Tasks

Transfer Learning

Similar Papers 제목 키워드 기반

Schema Encoding for Transferable Dialogue State Tracking

2022-10-05 · COLING 2022 10 · Hyunmin Jeon, Gary Geunbae Lee

Dialogue state tracking (DST) is an essential sub-task for task-oriented dialogue systems. Recent work has focused on deep neural models for DST. However, the neural models require a large dataset for training. Furthermo…

Dialogue State TrackingTask-Oriented Dialogue Systems

Schema Encoding for Transferable Dialogue State Tracking

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Dialogue state tracking (DST) is an essential sub-task for task-oriented dialogue systems.Recent work has focused on deep neural models for DST.However, the neural models require a large dataset for training.Furthermore,…

Dialogue State Tracking

BranchOut: Regularization for Online Ensemble Tracking With Convolutional Neural Networks

2017-07-01 · CVPR 2017 7 · Bohyung Han, Jack Sim, Hartwig Adam

We propose an extremely simple but effective regularization technique of convolutional neural networks (CNNs), referred to as BranchOut, for online ensemble tracking. Our algorithm employs a CNN for target representatio…

DiversityVisual Tracking

Deep Convolutional Neural Networks for Thermal Infrared Object Tracking

2017-10-15 · Knowledge-Based Systems 2017 10 · QiaoLiu, Xiaohuan Lu, Zhenyu He, Chunkai Zhang 외

Unlike the visual object tracking, thermal infrared object tracking can track a target object in total darkness. Therefore, it has broad applications, such as in rescue and video surveillance at night. However, there are…

ObjectObject TrackingThermal Infrared Object TrackingVisual Object Tracking+1

Hierarchical Convolutional Features for Visual Tracking

2015-12-01 · ICCV 2015 12 · Chao Ma, Jia-Bin Huang, Xiaokang Yang, Ming-Hsuan Yang

Visual object tracking is challenging as target objects often undergo significant appearance changes caused by deformation, abrupt motion, background clutter and occlusion. In this paper, we exploit features extracted fr…

Object RecognitionObject TrackingVisual Object TrackingVisual Tracking