Visual Object Tracking

150 papers with code • 21 benchmarks • 26 datasets

Visual Object Tracking is an important research topic in computer vision, image understanding and pattern recognition. Given the initial state (centre location and scale) of a target in the first frame of a video sequence, the aim of Visual Object Tracking is to automatically obtain the states of the object in the subsequent video frames.

Source: Learning Adaptive Discriminative Correlation Filters via Temporal Consistency Preserving Spatial Feature Selection for Robust Visual Object Tracking

Libraries

Use these libraries to find Visual Object Tracking models and implementations

Most implemented papers

SSD: Single Shot MultiBox Detector

weiliu89/caffe 8 Dec 2015

Experimental results on the PASCAL VOC, MS COCO, and ILSVRC datasets confirm that SSD has comparable accuracy to methods that utilize an additional object proposal step and is much faster, while providing a unified framework for both training and inference.

SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks

STVIR/pysot CVPR 2019

Moreover, we propose a new model architecture to perform depth-wise and layer-wise aggregations, which not only further improves the accuracy but also reduces the model size.

One-Shot Video Object Segmentation

kmaninis/OSVOS-PyTorch CVPR 2017

This paper tackles the task of semi-supervised video object segmentation, i. e., the separation of an object from the background in a video, given the mask of the first frame.

SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation Guidelines

MegviiDetection/video_analyst 14 Nov 2019

Following these guidelines, we design our Fully Convolutional Siamese tracker++ (SiamFC++) by introducing both classification and target state estimation branch(G1), classification score without ambiguity(G2), tracking without prior knowledge(G3), and estimation quality score(G4).

ECO: Efficient Convolution Operators for Tracking

martin-danelljan/ECO CVPR 2017

Moreover, our fast variant, using hand-crafted features, operates at 60 Hz on a single CPU, while obtaining 65. 0% AUC on OTB-2015.

High Performance Visual Tracking With Siamese Region Proposal Network

foolwood/DaSiamRPN CVPR 2018

Visual object tracking has been a fundamental topic in recent years and many deep learning based trackers have achieved state-of-the-art performance on multiple benchmarks.

Deeper and Wider Siamese Networks for Real-Time Visual Tracking

researchmm/SiamDW CVPR 2019

Siamese networks have drawn great attention in visual tracking because of their balanced accuracy and speed.

Rethinking Self-supervised Correspondence Learning: A Video Frame-level Similarity Perspective

xvjiarui/VFS ICCV 2021

To learn generalizable representation for correspondence in large-scale, a variety of self-supervised pretext tasks are proposed to explicitly perform object-level or patch-level similarity learning.

Discriminative Correlation Filter with Channel and Spatial Reliability

alanlukezic/csr-dcf CVPR 2017

Short-term tracking is an open and challenging problem for which discriminative correlation filters (DCF) have shown excellent performance.

YouTube-VOS: Sequence-to-Sequence Video Object Segmentation

BehradToghi/ECCV_Youtube_VOS ECCV 2018

End-to-end sequential learning to explore spatial-temporal features for video segmentation is largely limited by the scale of available video segmentation datasets, i. e., even the largest video segmentation dataset only contains 90 short video clips.