CapGaze
홈페이지 · 논문 1편
Consists of eye movements and verbal descriptions recorded synchronously over images. Source: [Human Attention in Image Captioning: Dataset and Analysis](/paper/a-synchronized-multi-modal-attention-caption)
홈페이지 · 논문 1편
Consists of eye movements and verbal descriptions recorded synchronously over images. Source: [Human Attention in Image Captioning: Dataset and Analysis](/paper/a-synchronized-multi-modal-attention-caption)