Spatial-Temporal Relation Networks for Multi-Object Tracking
Citations Over TimeTop 1% of 2019 papers
Abstract
Recent progress in multiple object tracking (MOT) has shown that a robust similarity score is a key to the success of trackers. A good similarity score is expected to reflect multiple cues, e.g. appearance, location, and topology, over a long period of time. However, these cues are heterogeneous, making them hard to be combined in a unified network. As a result, existing methods usually encode them in separate networks or require a complex training approach. In this paper, we present a unified framework for similarity measurement based on spatial-temporal relation network which could simultaneously encode various cues and perform reasoning across both spatial and temporal domains. We also study the feature representation of a tracklet-object pair in depth, showing a proper design of the pair features can well empower the trackers. The resulting approach is named spatial-temporal relation networks (STRN). It runs in a feed-forward way and can be trained in an end-to-end manner. The state-of-the-art accuracy was achieved on all of the MOT15$\sim$17 benchmarks using public detection and online settings.
Related Papers
- → Which Eye Tracker Is Right for Your Research? Performance Evaluation of Several Cost Variant Eye Trackers(2016)84 cited
- → Introduction to Eye Tracking(2014)39 cited
- → A comparative study of different eye tracking system algorithms(2019)6 cited
- → Dhrushti-AI: A multi-screen multi-user eye-tracking system to understand the cognitive behavior of humans in process industries(2023)2 cited
- → Framework for Realizing a Free-Target Eye-tracking System(2015)2 cited