Inception Institute of Artificial Intelligence, Ltd.

Deng-Ping Fan

Ling Shao

Mingchen Zhuge

Yuchao Dai

Xin Yu

Yiran Zhong

Jing Zhang

Nick Barnes

A saliency detection explicitly models complementary information between appearance, or color, and depth information in images. A mutual-information minimization is used as a regularizer to reduce the redundancy between appearance features from RGB and geometric features from depth in the latent space. Then the latent features of each of the appearance and geometric modalities are fused to achieve multi-modal feature fusion for saliency detection.

Complementary learning for multi-modal saliency detection

A transformer based vision-linguistic (VL) model and training technique uses a number of different image patches covering the same portion of an image, along with a text description of the image to train the model. The model and pre-training techniques may be used in domain specific training of the model. The model can be used for fine-grained image-text tasks in the fashion domain.

Domain specific pre-training of cross modality transformer model

Growing community of inventors

Abu Dhabi, United Arab Emirates

Deng-Ping Fan