Visual Object Tracking On Lasot

评估指标

AUC

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
MCITrack-L384	76.6	Exploring Enhanced Contextual Information for Video-Level Object Tracking
LoRAT-g-378	76.2	Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance
MCITrack-B224	75.3	Exploring Enhanced Contextual Information for Video-Level Object Tracking
DAM4SAM	75.1	A Distractor-Aware Memory for Visual Object Tracking with SAM2
LoRAT-L-378	75.1	Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance
RTracker-L	74.7	RTracker: Recoverable Tracking via PN Tree Structured Memory
SAMURAI-L	74.2	SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory
ODTrack-L	74.0	ODTrack: Online Dense Temporal Token Learning for Visual Tracking
ARTrackV2-L	73.6	ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe
PiVOT-L	73.4	Improving Visual Object Tracking through Visual Prompting
MixViT-L(ConvMAE)	73.3	MixFormer: End-to-End Tracking with Iterative Mixed Attention
ODTrack-B	73.2	ODTrack: Online Dense Temporal Token Learning for Visual Tracking
ARTrack-L	73.1	Autoregressive Visual Tracking	-
HIPTrack	72.7	HIPTrack: Visual Tracking with Historical Prompts
SeqTrack-L384	72.5	Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking
UNINEXT-L	72.4	Universal Instance Perception as Object Discovery and Retrieval
NeighborTrack-OSTrack	72.2	NeighborTrack: Improving Single Object Tracking by Bipartite Matching with Neighbor Tracklets
UNINEXT-H	72.2	Universal Instance Perception as Object Discovery and Retrieval
MITS	72.0	Integrating Boxes and Masks: A Multi-Object Framework for Unified Visual Tracking and Segmentation
DropTrack	71.8	DropMAE: Learning Representations via Masked Autoencoders with Spatial-Attention Dropout for Temporal Matching Tasks

0 of 43 row(s) selected.