Space-time image velocimetry (STIV) technology has achieved good performance in river surface-flow velocity measurement, but the application a field environment is affected by bad weather or lighting conditions, which causes large measurement errors. To improve accuracy and robustness of STIV, we combined STIV with deep learning. Additionally, considering light weight neural network model, adop...

Focusing on text-to-image (T2I) generation, we propose Text and Image Mutual-Translation Adversarial Networks (TIME), a lightweight but effective model that jointly learns T2I generator G an image captioning discriminator D under the Generative Network framework. While previous methods tackle problem as uni-directional task use pre-trained language models to enforce image--text consistency, TIM...

Image segmentation is a common use case of image processing. It enables wide variety activities, from self-driving cars to traffic systems that are capable governing them. Most state the art models like Mask R-CNN and other transformer-based perform well but have very high inference times. Therefore in this paper, novel model architecture proposed can run on consumer grade hardware while giving...