Saltar al contenido principal
Volver al leaderboard

llm

ReferTrack: Referring Then Tracking for Embodied Visual Tracking

📄 Paper Trending (47⬆️): Embodied visual tracking (EVT) requires a mobile agent to continuously follow a specific target described in natural language using only onboard vision. While recent vision-language-action (VLA) policies unify target identification and trajectory planning, their chain-of-thought (CoT) reasoning ofte...

Fuente: HuggingFace_Papers

Qué hace

📄 Paper Trending (47⬆️): Embodied visual tracking (EVT) requires a mobile agent to continuously follow a specific target described in natural language using only onboard vision. While recent vision-language-action (VLA) policies unify target identification and trajectory planning, their chain-of-thought (CoT) reasoning ofte...

Para quién es

No disponible

Precio

No disponible

Puntos fuertes

  • No disponible

Límites

  • No disponible

¿Quieres integrarlo en tu negocio? Reserva una llamada gratuita

Reservar
ReferTrack: Referring Then Tracking for Embodied Visual Tracking | ToolAI - StudioCentOS