Rgb T Tracking On Lasher

Métriques

Precision

Success

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	Precision	Success	Paper Title	Repository
STMT	67.4	53.7	Transformer RGBT Tracking with Spatio-Temporal Multimodal Tokens	-
SeqTrackv2-L256	74.1	58.8	Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking
CAFormer	70.0	55.6	Cross-modulated Attention Transformer for RGBT Tracking	-
SDSTrack	66.5	53.1	SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking
MMMP	71.4	56.7	From Two-Stream to One-Stream: Efficient RGB-T Tracking via Mutual Prompt Learning and Knowledge Distillation	-
CAT	45.0	31.4	Challenge-Aware RGBT Tracking	-
OneTracker	67.2	53.8	OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning	-
SeqTrackv2-B256	70.4	55.8	Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking
ProTrack	50.9	42.1	Prompting for Multi-Modal Tracking	-
PromptTrack	76.2	60.7	-	-
SUTrack-L384	76.9	61.9	SUTrack: Towards Simple and Unified Single Object Tracking
SeqTrackv2-L384	76.7	61.0	Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking
MPLT	72.0	57.1	RGB-T Tracking via Multi-Modal Mutual Prompt Learning
TBSI	70.2	56.5	Bridging Search Region Interaction With Template for RGB-T Tracking
MANet++	46.7	31.4	RGBT Tracking via Multi-Adapter Network with Hierarchical Divergence Loss	-
GMMT	70.7	56.6	Generative-based Fusion Mechanism for Multi-Modal Tracking
SeqTrackv2-B384	71.5	56.2	Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking
BAT	70.2	56.3	Bi-directional Adapter for Multi-modal Tracking
Un-Track	66.7	53.6	Single-Model and Any-Modality for Video Object Tracking
MambaVT-M256	72.7	57.5	MambaVT: Spatio-Temporal Contextual Modeling for robust RGB-T Tracking	-

0 of 36 row(s) selected.