Tetris decomposes stationary videos into tile polyominoes and applies classifier plus ILP pruning to cut detector calls, staying within 5% accuracy loss while delivering up to 17.4x throughput gains over priors.
Simple online and realtime tracking with a deep association metric,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
SMAC introduces a spatial-modal fusion backbone and adaptive collapse network for multimodal MOT, reporting 63.31 HOTA and 79.21 MOTA on UniRTL RNT modality.
citing papers explorer
-
Tetris: Tile-level Sampling for Efficient and High-Fidelity Video Object Tracking
Tetris decomposes stationary videos into tile polyominoes and applies classifier plus ILP pruning to cut detector calls, staying within 5% accuracy loss while delivering up to 17.4x throughput gains over priors.
-
SMAC: Spatial-Modal Joint Modeling and Adaptive Representation Collapse for Multimodal Object Tracking
SMAC introduces a spatial-modal fusion backbone and adaptive collapse network for multimodal MOT, reporting 63.31 HOTA and 79.21 MOTA on UniRTL RNT modality.