OA-VAT improves visual active tracking by combining instance-level prototype discrimination with occlusion-aware diffusion planning, reporting gains over prior SOTA on simulated and real drone benchmarks.
Lasot: A high-quality benchmark for large-scale single ob- ject tracking
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
STORM is an end-to-end MLLM for referring multi-object tracking that uses task-composition learning to leverage sub-task data and introduces the STORM-Bench dataset, achieving SOTA results.
citing papers explorer
-
Instance-level Visual Active Tracking with Occlusion-Aware Planning
OA-VAT improves visual active tracking by combining instance-level prototype discrimination with occlusion-aware diffusion planning, reporting gains over prior SOTA on simulated and real drone benchmarks.
-
STORM: End-to-End Referring Multi-Object Tracking in Videos
STORM is an end-to-end MLLM for referring multi-object tracking that uses task-composition learning to leverage sub-task data and introduces the STORM-Bench dataset, achieving SOTA results.