tlooto
Sign up
Multimodal Machine Learning ApplicationsAdvanced Image and Video Retrieval TechniquesVisual Attention and Saliency Detection

VIP-CAN: Vision Prompt-based Cross-attention Network for Zero-shot Sketch-based Image Retrieval

Guoliang Zhang, Donglin Zhang, Xiao-Jun Wu

2026.5.1PATTERN RECOGNITION LETTERS

DOI: 10.1016/j.patrec.2026.05.006

Abstract

Abstract is not available.

Citation format

ZHANG, Guoliang; ZHANG, Donglin; WU, Xiao-Jun. VIP-CAN: Vision prompt-based cross-attention network for zero-shot sketch-based image retrieval. PATTERN RECOGNITION LETTERS, 2026, 206: 56–62.