HyperAIHyperAI

Command Palette

Search for a command to run...

Console

Visual Object Tracking On Lasot

Metrics

AUC

Results

Performance results of various models on this benchmark

Paper Title
MCITrack-L38476.6Exploring Enhanced Contextual Information for Video-Level Object Tracking
LoRAT-g-37876.2Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance
MCITrack-B22475.3Exploring Enhanced Contextual Information for Video-Level Object Tracking
DAM4SAM75.1A Distractor-Aware Memory for Visual Object Tracking with SAM2
LoRAT-L-37875.1Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance
RTracker-L74.7RTracker: Recoverable Tracking via PN Tree Structured Memory
SAMURAI-L74.2SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory
ODTrack-L74.0ODTrack: Online Dense Temporal Token Learning for Visual Tracking
ARTrackV2-L73.6ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe
PiVOT-L73.4Improving Visual Object Tracking through Visual Prompting
MixViT-L(ConvMAE)73.3MixFormer: End-to-End Tracking with Iterative Mixed Attention
ODTrack-B73.2ODTrack: Online Dense Temporal Token Learning for Visual Tracking
ARTrack-L73.1Autoregressive Visual Tracking
HIPTrack72.7HIPTrack: Visual Tracking with Historical Prompts
SeqTrack-L38472.5Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking
UNINEXT-L72.4Universal Instance Perception as Object Discovery and Retrieval
NeighborTrack-OSTrack72.2NeighborTrack: Improving Single Object Tracking by Bipartite Matching with Neighbor Tracklets
UNINEXT-H72.2Universal Instance Perception as Object Discovery and Retrieval
MITS72.0Integrating Boxes and Masks: A Multi-Object Framework for Unified Visual Tracking and Segmentation
DropTrack71.8DropMAE: Learning Representations via Masked Autoencoders with Spatial-Attention Dropout for Temporal Matching Tasks
0 of 43 row(s) selected.