HieDG discretizes geometric cues with a hierarchical residual codebook and integrates the resulting tokens into query-based trackers to boost identity consistency on animal and generic MOT benchmarks.
In: Proceedings of the IEEE International Conference on Advanced Video and Signal Based Surveillance
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
HieDG: A Hierarchical Discrete Geometry-Guided Framework for Multi-Animal Tracking
HieDG discretizes geometric cues with a hierarchical residual codebook and integrates the resulting tokens into query-based trackers to boost identity consistency on animal and generic MOT benchmarks.