Visual Object Tracking On Lasot Ext

Métriques

AUC

Precision

Résultats

Résultats de performance de divers modèles sur ce benchmark

			Paper Title
SAMURAI-L	61.0	72.2	SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory
DAM4SAM	60.9	-	A Distractor-Aware Memory for Visual Object Tracking with SAM2
LoRAT-L-378	56.6	65.1	Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance
LoRAT-g-378	56.5	64.9	Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance
UNINEXT-H	56.2	63.8	Universal Instance Perception as Object Discovery and Retrieval
MCITrack-L384	55.7	62.9	Exploring Enhanced Contextual Information for Video-Level Object Tracking
RTracker-L	54.9	62.7	RTracker: Recoverable Tracking via PN Tree Structured Memory
MCITrack-B224	54.6	62.1	Exploring Enhanced Contextual Information for Video-Level Object Tracking
ODTrack-L	53.9	-	ODTrack: Online Dense Temporal Token Learning for Visual Tracking
ARTrackV2-L	53.4	60.2	ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe
HIPTrack	53.0	60.6	HIPTrack: Visual Tracking with Historical Prompts
ARTrack-L	52.8	59.7	Autoregressive Visual Tracking
DropTrack	52.7	60.2	DropMAE: Learning Representations via Masked Autoencoders with Spatial-Attention Dropout for Temporal Matching Tasks
ODTrack-B	52.4	-	ODTrack: Online Dense Temporal Token Learning for Visual Tracking
SeqTrack-L384	50.7	57.5	Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking
OSTrack	50.6	57.6	Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework
KeepTrack	48.2	-	Learning Target Candidate Association to Keep Track of What Not to Track
LTMU	41.4	47.3	High-Performance Long-Term Tracking with Meta-Updater

0 of 18 row(s) selected.

Visual Object Tracking On Lasot Ext | SOTA | HyperAI