computer-vision-5

Real-Time Visual Tracking

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in real-time-visual-tracking-5

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find real-time-visual-tracking-5 models and implementations

Datasets

Drunkard's Dataset

Subtasks

No subtasks available.

Most implemented papers

Deeper and Wider Siamese Networks for Real-Time Visual Tracking

Houwen Peng, Qiang Wang, Zhipeng Zhang•Sun Jan 06 2019

This paper proposes new residual modules to eliminate the negative impact of padding, and designs new architectures using these modules with controlled receptive field size and network stride that guarantee real-time tracking speed when applied to SiamFC and SiamRPN.

931

Content

0

Paper Graph

Fully Convolutional Online Tracking

Limin Wang, Gangshan Wu, Yutao Cui, Cheng Jiang•Tue Apr 14 2020

This work presents the first fully convolutional online tracking framework (FCOT), with a focus on enabling online learning for both classification and regression branches, and introduces an online regression model generator (RMG) based on the carefully designed anchor-free box regression branch.

57 0

Paper Graph

Fast Online Object Tracking and Segmentation: A Unifying Approach

Philip H. S. Torr, Li Zhang, Luca Bertinetto, Qiang Wang, Weiming Hu•Tue Dec 11 2018

This method improves the offline training procedure of popular fully-convolutional Siamese approaches for object tracking by augmenting their loss with a binary segmentation task, and operates online, producing class-agnostic object segmentation masks and rotated bounding boxes at 55 frames per second.

1295 0

Paper Graph

SRT3D: A Sparse Region-Based 3D Object Tracking Approach for the Real World

Rudolph Triebel, Manuel Stoiber, Martin Pfanne, Klaus H. Strobl, A. Albu-Schaffer•Sun Oct 24 2021

SRT3D is developed, a sparse region-based approach to 3D object tracking that improves on the current state of the art both in terms of runtime and quality, performing particularly well for noisy and cluttered images encountered in the real world.

56 0

Paper Graph

ReconNet: Non-Iterative Reconstruction of Images from Compressively Sensed Random Measurements

Suhas Lohit, K. Kulkarni, P. Turaga, Ronan Kerviche, Amit Ashok•Mon Jan 25 2016

A novel convolutional neural network architecture which takes in CS measurements of an image as input and outputs an intermediate reconstruction which is fed into an off-the-shelf denoiser to obtain the final reconstructed image, ReconNet.

67 0

Paper Graph

Visual Pursuit Control based on Gaussian Processes with Switched Motion Trajectories

Marco Omainska, Junya Yamauchi, M. Fujita•Wed Aug 17 2022

This paper presents an improved Visual Motion Observer with switched Gaussian Process models for an extended class of target motion profiles and proposes a pursuit control law with an online method to estimate the switching behavior of the target by the GP model uncertainty.

0 0

Paper Graph

Real-time visual tracking by deep reinforced decision making

Kyoung Mu Lee, Janghoon Choi, Junseok Kwon•Mon Feb 20 2017

This paper introduces a novel real-time visual tracking algorithm based on a template selection strategy constructed by deep reinforcement learning methods that is generally applicable to other confidence map based tracking algorithms.

55 0

Paper Graph

Real Time Visual Tracking using Spatial-Aware Temporal Aggregation Network

Xianming Liu, Tao Hu, Lichao Huang, Han Shen•Thu Aug 01 2019

This paper proposes a correlation filter based tracking method which aggregates historical features in a spatial-aligned and scale-aware paradigm, named as Spatial-Aware Temporal Aggregation network (SATA), is able to assemble appearances and motion contexts of various scales in a time period, resulting in better performance compared to a single static image.

1 0

Paper Graph

BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Models

Bowen Wen, Kostas E. Bekris•Sat Jul 31 2021

BundleTrack is proposed, a general framework for 6D pose tracking of novel objects, which does not depend upon 3D models, either at the instance or category-level, and leverages the complementary attributes of recent advances in deep learning for segmentation and robust feature extraction, as well as memory-augmented pose graph optimization for spatiotemporal consistency.

151 0

Paper Graph

Adding a benchmark result helps the community track progress.