TF-SMOT composes pretrained vision-language models into a training-free pipeline that reaches state-of-the-art tracking and improved summary quality on the BenSMOT benchmark.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Proposes a control-theoretic pipeline using Gauss-Markov and instrumental-variable estimators to reconstruct and forecast latent time-varying parameters from noisy gradients in strongly convex online optimization, along with a bound on expected tracking error.
citing papers explorer
-
Training-Free Semantic Multi-Object Tracking with Vision-Language Models
TF-SMOT composes pretrained vision-language models into a training-free pipeline that reaches state-of-the-art tracking and improved summary quality on the BenSMOT benchmark.
-
Online Optimization with Unknown Time-Varying Parameters from Noisy Gradient Measurements
Proposes a control-theoretic pipeline using Gauss-Markov and instrumental-variable estimators to reconstruct and forecast latent time-varying parameters from noisy gradients in strongly convex online optimization, along with a bound on expected tracking error.