Signals 4 · free daily AI digest

Cross-Domain Tracker Adaptation Without Target-Domain Labels via Vision-Language Agents

Paper recorded by Signals 4 on 2026-09-04 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-04 on arXiv · recorded by Signals 4 on 2026-09-07

Category: cs.CV · 计算机视觉 · first seen 2026-09-07

Abstract

We present a system that uses a Vision-Language Model (VLM) as a diagnostic agent for adapting a detect-to-track pipeline to a new target domain without access to target-domain labels. Rather than optimizing against annotated metrics, the VLM directly inspects rendered tracking outputs, identifies visual failure modes, and recommends parameter updates through an iterative tuning loop. We first dem

Read on arXiv →

#139 most recent of 237 cs.CV papers we have recorded · ↑ newer: Few-Shot Video Recognition via Hierarchical Metric Learning · ↓ older: Measured Sliders: Learning Continuous Controls from Differentiable Ima
Cite this page: Cross-Domain Tracker Adaptation Without Target-Domain Labels via Vision-Language Agents: the #139 most recent of 237 cs.CV papers we have recorded (as of 2026-09-04). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/cross-domain-tracker-adaptation-without-target-domain-labels-via-vision-language.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CV papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions