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 11511200 of 1966 papers

TitleStatusHype
Discussion among Different Methods of Updating Model Filter in Object Tracking0
Distillation of Diffusion Features for Semantic Correspondence0
Distractor-aware Event-based Tracking0
Distributed Expectation Propagation for Multi-Object Tracking over Sensor Networks0
Distributed Extended Object Tracking Information Filter Over Sensor Networks0
Distributed Extended Object Tracking Using Coupled Velocity Model from WLS Perspective0
Distributed Variational Bayesian Algorithms for Extended Object Tracking0
Divert More Attention to Vision-Language Tracking0
Divert More Attention to Vision-Language Object Tracking0
DL-SLOT: Dynamic Lidar SLAM and Object Tracking Based On Graph Optimization0
DMV: Visual Object Tracking via Part-level Dense Memory and Voting-based Retrieval0
Does Video Compression Impact Tracking Accuracy?0
Domain Adaptive SiamRPN++ for Object Tracking in the Wild0
DOT: Dynamic Object Tracking for Visual SLAM0
DreamTrack: Dreaming the Future for Multimodal Visual Object Tracking0
DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving0
DroBoost: An Intelligent Score and Model Boosting Method for Drone Detection0
DropTrack -- automatic droplet tracking using deep learning for microfluidic applications0
DSRRTracker: Dynamic Search Region Refinement for Attention-based Siamese Multi-Object Tracking0
DTLLM-VLT: Diverse Text Generation for Visual Language Tracking Based on LLM0
DTVLT: A Multi-modal Diverse Text Benchmark for Visual Language Tracking Based on LLM0
Dual approach for object tracking based on optical flow and swarm intelligence0
Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction0
Dynamic Resource-aware Corner Detection for Bio-inspired Vision Sensors0
Dynamic Template Selection Through Change Detection for Adaptive Siamese Tracking0
DynaSLAM II: Tightly-Coupled Multi-Object Tracking and SLAM0
EANet: Enhanced Attribute-based RGBT Tracker Network0
Easy-Poly: A Easy Polyhedral Framework For 3D Multi-Object Tracking0
EBBIOT: A Low-complexity Tracking Algorithm for Surveillance in IoVT Using Stationary Neuromorphic Vision Sensors0
EdgeServe: A Streaming System for Decentralized Model Serving0
Effective Fusion of Deep Multitasking Representations for Robust Visual Tracking0
Effective Object Tracking in Unstructured Crowd Scenes0
Efficient Adversarial Attacks for Visual Object Tracking0
Efficient and Consistent Adversarial Bipartite Matching0
Efficient Convolutional Neural Network Training with Direct Feedback Alignment0
Efficient Data Association and Uncertainty Quantification for Multi-Object Tracking0
Efficient data-driven encoding of scene motion using Eccentricity0
Efficient Discriminative Nonorthogonal Binary Subspace with its Application to Visual Tracking0
Efficient Joint Detection and Multiple Object Tracking with Spatially Aware Transformer0
Efficiently Tracking Homogeneous Regions in Multichannel Images0
Efficient Multi-Object Tracking on Edge Devices via Reconstruction-Based Channel Pruning0
Efficient Image Denoising by Low-Rank Singular Vector Approximations of Geodesics' Gramian Matrix0
Efficient resource management in UAVs for Visual Assistance0
Efficient Single-Image Depth Estimation on Mobile Devices, Mobile AI & AIM 2022 Challenge: Report0
Efficient Bird Eye View Proposals for 3D Siamese Tracking0
Efficient Training for Visual Tracking with Deformable Transformer0
Efficient universal shuffle attack for visual object tracking0
Egocentric Height Estimation0
Eliminating Exposure Bias and Loss-Evaluation Mismatch in Multiple Object Tracking0
Eliminating Exposure Bias and Metric Mismatch in Multiple Object Tracking0
Show:102550
← PrevPage 24 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