Zhong-Hao Wang

YOLO-TVP: Real-time open-vocabulary object detection with Semantic-Target Soft Cross-Entropy and text-visual prompts

With scratch-trained detector weights and frozen vision-language encoders used only for prompt-side priors, YOLO-TVP achieves competitive prompt-conditioned detection while preserving real-time efficiency, verifying its advances in semantic alignment and prompt-adaptive detection.