List your company

Pedestrian crossing intention prediction on VR-based egocentric video dataset (test)

78.9AccuracyVLP
48.84456.64764.4572.253Jun 8, 2026

Evaluation results

MethodLinks
VLPGroup=Fine-tuned, Prompt=Standard, Time (s)=0.0072026.0678.978.7
Qwen3-VL-2BGroup=Fine-tuned, Prompt=Standard, Time (s)=0.122026.0677.777.3
CLIP+TransformerGroup=Baselines, Prompt=—2026.0672.772.4
Qwen2.5-VL-7BGroup=Zero-shot, Prompt=Standard, Time (s)=0.33, Quantization=8-bit2026.0663.257.9
Qwen2.5-VL-7BGroup=Zero-shot, Prompt=Visual prompt, Time (s)=0.33, Quantization=8-bit2026.0660.552.6
Intern3VL-8BGroup=Zero-shot, Prompt=Standard, Time (s)=1.35, Quantization=8-bit2026.0659.447.5
Qwen2.5-VL-7BGroup=Zero-shot, Prompt=CoT (multi), Time (s)=3.78, Quantization=8-bit2026.0659.437.1
Qwen3-VL-2BGroup=Zero-shot, Prompt=Standard, Time (s)=0.122026.0659.358
Intern3VL-2BGroup=Zero-shot, Prompt=Standard, Time (s)=0.722026.0658.644.6
Qwen3-VL-8BGroup=Zero-shot, Prompt=Standard, Time (s)=0.32, Quantization=8-bit2026.0657.955.9
Qwen2.5-VL-7BGroup=Zero-shot, Prompt=CoT (simple), Time (s)=2.32, Quantization=8-bit2026.0656.854.3
MajorityGroup=Baselines, Prompt=—2026.0656.736.2
VLPGroup=Zero-shot, Prompt=Standard, Time (s)=0.012026.0656.737.8
RandomGroup=Baselines, Prompt=—2026.065049.7