SOTAVerified

Visual Object Tracking

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

Papers

Showing 110 of 341 papers

TitleStatusHype
UMDATrack: Unified Multi-Domain Adaptive Tracking Under Adverse Weather ConditionsCode1
Mamba-FETrack V2: Revisiting State Space Model for Frame-Event based Visual Object TrackingCode1
R1-Track: Direct Application of MLLMs to Visual Object Tracking via Reinforcement LearningCode2
Fully Spiking Neural Networks for Unified Frame-Event Object Tracking0
Progressive Scaling Visual Object Tracking0
Adapting SAM 2 for Visual Object Tracking: 1st Place Solution for MMVPR Challenge Multi-Modal Tracking0
Towards Low-Latency Event Stream-based Visual Object Tracking: A Slow-Fast ApproachCode0
CGTrack: Cascade Gating Network with Hierarchical Feature Aggregation for UAV TrackingCode0
Adversarial Attack for RGB-Event based Visual Object TrackingCode0
SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual TrackingCode1
Show:102550
← PrevPage 1 of 35Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1LoRAT-g-378AUC0.74Unverified
2NeighborTrack-OSTrackAUC0.73Unverified
3LoRAT-L-378AUC0.73Unverified
4SPMTrack-BAUC0.72Unverified
5ARTrackV2-LAUC0.72Unverified
6ARTrack-LAUC0.71Unverified
7OSTrack -384AUC0.71Unverified
8AiATrackAUC0.71Unverified
9HIPTrackAUC0.71Unverified
10MixFormerAUC0.7Unverified