DMV: Visual Object Tracking Via Part-level Dense Memory And Voting-based Retrieval

Abstract

We propose a novel memory-based tracker via part-level dense memory and voting-based retrieval, called DMV. Since deep learning techniques have been introduced to the tracking field, Siamese trackers have attracted many researchers due to the balance between speed and accuracy. However, most of them are based on a single template matching, which limits the performance as it restricts the accessible in-formation to the initial target features. In this paper, we relieve this limitation by maintaining an external memory that saves the tracking record. Part-level retrieval from the memory also liberates the information from the template and allows our tracker to better handle the challenges such as appearance changes and occlusions. By updating the memory during tracking, the representative power for the target object can be enhanced without online learning. We also propose a novel voting mechanism for the memory reading to filter out unreliable information in the memory. We comprehensivel

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keynam2020dmv

Related papers

• MFST: Multi-features Siamese Tracker (2021)0.95
• Deep Similarity Metric Learning For Real-time Pedestrian Tracking (2018)0.00
• Smiletrack: Similarity Learning For Occlusion-aware Multiple Object Tracking (2022)17.36
• HM4: Hidden Markov Model With Memory Management For Visual Place Recognition (2020)5.24
• Mmf-track: Multi-modal Multi-level Fusion For 3D Single Object Tracking (2023)7.16
• Quasi-dense Similarity Learning For Multiple Object Tracking (2020)19.58
• Qdtrack: Quasi-dense Similarity Learning For Appearance-only Multiple Object Tracking (2022)15.75
• Multiple Convolutional Features In Siamese Networks For Object Tracking (2021)7.73