Video Object Tracking On Nv Vot211

评估指标

AUC

Precision

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	41.50	54.20	Exploring Enhanced Contextual Information for Video-Level Object Tracking
ProContEXT	40.10	54.50	ProContEXT: Exploring Progressive Context Transformer for Tracking
ODTrack	39.60	55.80	ODTrack: Online Dense Temporal Token Learning for Visual Tracking
KeepTrack	39.59	55.50	Learning Target Candidate Association to Keep Track of What Not to Track
TATrack-L	39.29	53.94	Target-Aware Tracking with Long-term Context Attention
ToMP-50	39.25	53.01	Transforming Model Prediction for Tracking
Mixformer(ConvMAE)	39.23	54.20	MixFormer: End-to-End Tracking with Iterative Mixed Attention
AiATrack	38.91	53.47	AiATrack: Attention in Attention for Transformer Visual Tracking
OSTrack-384	38.59	53.06	Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework
Neighbor- Track(OSTrack)	38.32	52.54	NeighborTrack: Improving Single Object Tracking by Bipartite Matching with Neighbor Tracklets
STARK	38.26	51.37	Learning Spatio-Temporal Transformer for Visual Tracking
SLT-TransT	37.22	51.70	Towards Sequence-Level Training for Visual Tracking
STMTrack	36.84	50.34	STMTrack: Template-free Visual Tracking with Space-time Memory Networks
TransT	36.79	51.97	Transformer Tracking
TrDiMP	36.66	50.68	Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking
RTS	36.20	53.68	Robust Visual Tracking by Segmentation
KYS	36.02	48.13	Know Your Surroundings: Exploiting Scene Information for Object Tracking
ARTrack-L	35.92	51.64	Autoregressive Visual Tracking	-
DiMP-50	35.89	48.68	Learning Discriminative Model Prediction for Tracking
SiamBAN-ACM	35.80	48.31	Learning to Fuse Asymmetric Feature Maps in Siamese Trackers

0 of 44 row(s) selected.