Visual Object Tracking On Trackingnet

Métriques

Accuracy

Normalized Precision

Precision

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	Accuracy	Normalized Precision	Precision	Paper Title	Repository
ARTrack-L	85.6	89.6	86.0	Autoregressive Visual Tracking
SiamFC++	74.5	79.8	68.5	SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation Guidelines
ATOM(Resnet18)+EnergyRegression	-	80.1	69.7	Energy-Based Models for Deep Probabilistic Regression
NeighborTrack-OSTrack	83.79	88.30	-	NeighborTrack: Improving Single Object Tracking by Bipartite Matching with Neighbor Tracklets
GFS-DCF	60.9	71.79	56.57	Joint Group Feature Selection and Discriminative Filter Learning for Robust Visual Object Tracking
SiamBAN-ACM	75.3	81.0	71.2	Learning to Fuse Asymmetric Feature Maps in Siamese Trackers
ODTrack-B	85.1	-	-	ODTrack: Online Dense Temporal Token Learning for Visual Tracking
DiMP-50	74.0	80.1	-	Learning Discriminative Model Prediction for Tracking
UNINEXT-H	85.4	89.0	86.4	Universal Instance Perception as Object Discovery and Retrieval
OSTrack-384	83.9	88.5	83.2	Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework
MixFormer-L	83.9	88.9	83.1	MixFormer: End-to-End Tracking with Iterative Mixed Attention
MixFormerV2-B	83.4	88.1	81.6	-	-
TREG	78.5	83.8	75	Target Transformed Regression for Accurate Tracking
SeqTrack-L384	85.5	89.8	85.8	Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking
ATOM	70.34	77.11	64.84	ATOM: Accurate Tracking by Overlap Maximization
AiATrack	82.7	87.8	80.4	AiATrack: Attention in Attention for Transformer Visual Tracking
LoRAT-g-378	86.0	90.2	86.1	Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance
SLT-TransT	82.8	87.5	81.4	Towards Sequence-Level Training for Visual Tracking
MCITrack-B224	86.3	90.9	86.1	Exploring Enhanced Contextual Information for Video-Level Object Tracking
TATrack-L	85.0	89.3	84.5	Target-Aware Tracking with Long-term Context Attention	-

0 of 37 row(s) selected.