Autoregressive Queries for Adaptive Tracking with Spatio-TemporalTransformers

arXiv:2403.10574v1 Announce Type: new
Abstract: The rich spatio-temporal information is crucial to capture the complicated target appearance variations in visual tracking. However, most top-performing tracking algorithms rely on many hand-crafted components for spatio-temporal information aggregation. Consequently, the spatio-temporal information is far away from being fully explored. To alleviate this issue, we propose an adaptive tracker with spatio-temporal transformers (named AQATrack), which adopts simple autoregressive queries to effectively learn spatio-temporal information without many hand-designed components. Firstly, we introduce a set of …

abstract aggregation algorithms arxiv components cs.cv however information issue queries temporal tracking type visual