SOTAVerified

Object Tracking

Object tracking is the task of taking an initial set of object detections, creating a unique ID for each of the initial detections, and then tracking each of the objects as they move around frames in a video, maintaining the ID assignment. State-of-the-art methods involve fusing data from RGB and event-based cameras to produce more reliable object tracking. CNN-based models using only RGB images as input are also effective. The most popular benchmark is OTB. There are several evaluation metrics specific to object tracking, including HOTA, MOTA, IDF1, and Track-mAP.

( Image credit: Towards-Realtime-MOT )

Papers

Showing 15511600 of 1966 papers

TitleStatusHype
CDTB: A Color and Depth Visual Object Tracking Dataset and Benchmark0
Performance Evaluation Methodology for Long-Term Visual Object Tracking0
Unsupervised Learning of Object Structure and Dynamics from Videos0
How To Train Your Deep Multi-Object TrackerCode0
CVPR19 Tracking and Detection Challenge: How crowded can it get?0
Learning Deep Multi-Level Similarity for Thermal Infrared Object TrackingCode0
Active inference body perception and action for humanoid robots0
Detection and Tracking of Multiple Mice Using Part Proposal Networks0
Learning Rotation Adaptive Correlation Filters in Robust Visual Object Tracking0
Creative Flow+ DatasetCode0
Eliminating Exposure Bias and Metric Mismatch in Multiple Object Tracking0
Automated Ground Truth Estimation of Vulnerable Road Users in Automotive Radar Data Using GNSS0
Fooling Detection Alone is Not Enough: First Adversarial Attack against Multiple Object TrackingCode1
WPU-Net: Boundary Learning by Using Weighted Propagation in Convolution NetworkCode1
Tracking in Urban Traffic Scenes from Background Subtraction and Object Detection0
Intra-frame Object Tracking by DeblattingCode0
LightTrack: A Generic Framework for Online Top-Down Human Pose TrackingCode0
FANTrack: 3D Multi-Object Tracking with Feature Association NetworkCode0
Frame-wise Motion and Appearance for Real-time Multiple Object Tracking0
DHER: Hindsight Experience Replay for Dynamic GoalsCode0
Mixture of Pre-processing Experts Model for Noise Robust Deep Learning on Resource Constrained Platforms0
EM-Fusion: Dynamic Object-Level SLAM with Probabilistic Data AssociationCode0
A Large Scale Urban Surveillance Video Dataset for Multiple-Object Tracking and Behavior Analysis0
Spatial-Temporal Relation Networks for Multi-Object Tracking0
Physical Adversarial Textures that Fool Visual Object Tracking0
Deep Learning Based Automatic Video Annotation Tool for Self-Driving Car0
Video Object Segmentation and Tracking: A Survey0
Learning Discriminative Model Prediction for TrackingCode0
FAMNet: Joint Learning of Feature, Affinity and Multi-dimensional Assignment for Online Multiple Object Tracking0
SPM-Tracker: Series-Parallel Matching for Real-Time Visual Object Tracking0
Super accurate low latency object detection on a surveillance UAVCode0
On evaluating CNN representations for low resource medical image classification0
INFER: INtermediate representations for FuturE pRedictionCode0
Efficient Bird Eye View Proposals for 3D Siamese Tracking0
Multi-person Articulated Tracking with Spatial and Temporal Embeddings0
Inserting Videos into Videos0
Detection and Tracking of Small Objects in Sparse 3D Laser Range Data0
Tracking without bells and whistlesCode1
Generating superpixels using deep image representations0
Leveraging Shape Completion for 3D Siamese TrackingCode0
Distributed Variational Bayesian Algorithms for Extended Object Tracking0
Unsupervised learning-based long-term superpixel tracking0
Online Multi-Object Tracking with Instance-Aware Tracker and Dynamic Model Refreshment0
MOTS: Multi-Object Tracking and Segmentation0
Object tracking in video signals using Compressive Sensing0
SiamVGG: Visual Tracking using Deeper Siamese NetworksCode0
TrackNet: Simultaneous Object Detection and Tracking and Its Application in Traffic Video Analysis0
Real-time Prediction of Automotive Collision Risk from Monocular Video0
Confidence Trigger Detection: Accelerating Real-time Tracking-by-detection Systems0
Online Multi-Object Tracking with Dual Matching Attention NetworksCode0
Show:102550
← PrevPage 32 of 40Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1HR-CEUTrack-LargeSuccess Rate65Unverified
2HR-CEUTrack-BaseSuccess Rate63.2Unverified
3CEUTrack-LargeSuccess Rate62.8Unverified
4CEUTrack-BaseSuccess Rate62Unverified
5SiamR-CNNSuccess Rate60.9Unverified
6TransTSuccess Rate60.5Unverified
7SuperDiMPSuccess Rate60.2Unverified
8TrDiMPSuccess Rate60.1Unverified
9KeepTrackSuccess Rate59.6Unverified
10AiATrackSuccess Rate59Unverified
#ModelMetricClaimedVerifiedStatus
1HR-MonTrack-BaseSuccess Rate68.5Unverified
2HR-MonTrack-TinySuccess Rate66.3Unverified
3Multi-modalSuccess Rate63.4Unverified
4PrDiMPSuccess Rate59Unverified
5DiMPSuccess Rate57.1Unverified
6MonTrackSuccess Rate54.9Unverified
7ATOMSuccess Rate46.5Unverified
8KYSSuccess Rate26.6Unverified
#ModelMetricClaimedVerifiedStatus
1OmniTrackHOTA23.45Unverified
2DeepSORTHOTA21.16Unverified
3OC-SORTHOTA20.83Unverified
4ByteTrackHOTA20.66Unverified
5TrackFormerHOTA19.62Unverified
6HybridSORTHOTA16.64Unverified
7DiffMOTHOTA16.4Unverified
8Bot-SORTHOTA15.77Unverified
#ModelMetricClaimedVerifiedStatus
1DiMP50Success Rate67.33Unverified
2PrDiMP50Success Rate67Unverified
3PrDiMP18Success Rate65.9Unverified
4DiMP18Success Rate64.6Unverified
5AtomSuccess Rate63.8Unverified
#ModelMetricClaimedVerifiedStatus
1finalHumans0.14Unverified
2night_furyHumans0.05Unverified
3Yolo based methodHumans0.02Unverified
4finalHumans0Unverified
#ModelMetricClaimedVerifiedStatus
1M2-Trackmean precision83.4Unverified
2BATmean precision75.2Unverified
#ModelMetricClaimedVerifiedStatus
1UMMT3DMOTA95Unverified
2MMPTRACK3DMOTA94.8Unverified
#ModelMetricClaimedVerifiedStatus
1Siam-FCAverage IOU0.66Unverified
#ModelMetricClaimedVerifiedStatus
1RT-MDNetPrecision Plot0.63Unverified