STRIDE-QA: Visual Question Answering Dataset for Spatiotemporal Reasoning in Urban Driving Scenes

Documenti analoghi

• Read or Ignore? A Unified Benchmark for Typographic-Attack Robustness and Text Recognition in Vision-Language Models
  di: Waseda, Futa, et al.
  Pubblicazione: (2025)
• ACT-Bench: Towards Action Controllable World Models for Autonomous Driving
  di: Arai, Hidehisa, et al.
  Pubblicazione: (2024)
• Text-Printed Image: Bridging the Image-Text Modality Gap for Text-centric Training of Large Vision-Language Models
  di: Yamabe, Shojiro, et al.
  Pubblicazione: (2025)
• NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenario
  di: Qian, Tianwen, et al.
  Pubblicazione: (2023)
• One-D-Piece: Image Tokenizer Meets Quality-Controllable Compression
  di: Miwa, Keita, et al.
  Pubblicazione: (2025)