Spatial-Temporal Video Super-Resolution (ST-VSR) aims to generate high-quality videos with higher resolution (HR) and higher frame rate (HFR). Quite intuitively, pioneering two …
Convolutional neural network (CNN) and Transformer have achieved great success in multimedia applications. However, little effort has been made to effectively and efficiently …
F Li, L Zhang, Z Liu, J Lei, Z Li - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
CNN's limited receptive field restricts its ability to capture long-range spatial-temporal dependencies, leading to unsatisfactory performance in video super-resolution. To tackle …
Video captioning aims to generate natural language sentences that describe the given video accurately. Existing methods obtain favorable generation by exploring richer visual …
Generating a long-term high-spatiotemporal resolution global PM 2.5 dataset is of great significance for environmental management to mitigate the air pollution concerns worldwide …
Existing space-time video super-resolution (ST-VSR) methods fail to achieve high-quality reconstruction since they fail to fully explore the spatial-temporal correlations, long-range …
Y Qiu, D Chen, H Yao, Y Xu… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Abstract Although Magnetic Resonance Imaging (MRI) is very helpful for brain tumor segmentation and discovery, it often lacks some modalities in clinical practice. As a result …
Deep learning has opened up new possibilities for light field super-resolution (SR), but existing methods trained on synthetic datasets with simple degradations (eg, bicubic …
Most video frame interpolation (VFI) algorithms infer the intermediate frame with the help of adjacent frames through the cascaded motion estimation and content refinement. However …