TrackingNet

Overview edit

Variants: TrackingNet

Associated Benchmarks

This dataset is used in 2 benchmarks:

• Visual Tracking - Metrics: ACCURACY, Normalized Precision
• Visual Object Tracking - Metrics: Accuracy, Normalized Precision, Precision, Success Rate, AUC

Recent Benchmark Submissions

Research Papers

Recent papers with results on this dataset:

• SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Tracking (2025) -
• Exploring Enhanced Contextual Information for Video-Level Object Tracking (2024) -
• SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory (2024) -
• Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance (2024) -
• ODTrack: Online Dense Temporal Token Learning for Visual Tracking (2024) -
• ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe (2023) -
• HIPTrack: Visual Tracking with Historical Prompts (2023) -
• Integrating Boxes and Masks: A Multi-Object Framework for Unified Visual Tracking and Segmentation (2023) -
• Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking (2023) -
• DropMAE: Masked Autoencoders with Spatial-Attention Dropout for Tracking Tasks (2023) -
• Universal Instance Perception as Object Discovery and Retrieval (2023) -
• Target-Aware Tracking with Long-term Context Attention (2023) -
• MixFormer: End-to-End Tracking with Iterative Mixed Attention (2023) -
• NeighborTrack: Improving Single Object Tracking by Bipartite Matching with Neighbor Tracklets (2022) -
• Towards Sequence-Level Training for Visual Tracking (2022) -
• AiATrack: Attention in Attention for Transformer Visual Tracking (2022) -
• Towards Grand Unification of Object Tracking (2022) -
• Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework (2022) -
• MixFormer: End-to-End Tracking with Iterative Mixed Attention (2022) -
• SwinTrack: A Simple and Strong Baseline for Transformer Tracking (2021) -