Crowdsourcing More Effective Initializations for Single-Target Trackers Through Automatic Re-querying
| Autor: | Stephan J. Lemmer, Jason J. Corso, Jean Y. Song |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Computer science
business.industry BitTorrent tracker 05 social sciences Initialization 020207 software engineering 02 engineering and technology Crowdsourcing Object (computer science) Machine learning computer.software_genre Bounding overwatch Minimum bounding box Video tracking 0202 electrical engineering electronic engineering information engineering Redundancy (engineering) 0501 psychology and cognitive sciences Artificial intelligence business computer 050107 human factors |
| Zdroj: | CHI |
| DOI: | 10.1145/3411764.3445181 |
| Popis: | In single-target video object tracking, an initial bounding box is drawn around a target object and propagated through a video. When this bounding box is provided by a careful human expert, it is expected to yield strong overall tracking performance that can be mimicked at scale by novice crowd workers with the help of advanced quality control methods. However, we show through an investigation of 900 crowdsourced initializations that such quality control strategies are inadequate for this task in two major ways: first, the high level of redundancy in these methods (e.g., averaging multiple responses to reduce error) is unnecessary, as 23% of crowdsourced initializations perform just as well as the gold-standard initialization. Second, even nearly perfect initializations can lead to degraded long-term performance due to the complexity of object tracking. Considering these findings, we evaluate novel approaches for automatically selecting bounding boxes to re-query, and introduce Smart Replacement, an efficient method that decides whether to use the crowdsourced replacement initialization. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|