Video outpainting aims to adequately complete missing areas at the edges...
Aerial-aquatic vehicles are capable to move in the two most dominant flu...
Along with the widespread use of face recognition systems, their
vulnera...
In this work, we present a new computer vision task named video object o...
In this paper, we propose a Graph Inception Diffusion Networks(GIDN) mod...
Motion transfer aims to transfer the motion of a driving video to a sour...
Image animation aims to animate a source image by using motion learned f...
Anomaly identification is highly dependent on the relationship between t...
Skeleton-based action recognition has drawn a lot of attention for its
c...
Transformer-based methods have recently achieved great advancement on 2D...
Recently, transformers have shown great potential in image classificatio...
Temporal action detection (TAD) aims to locate and recognize the actions...
Semi-supervised object detection (SSOD) aims to facilitate the training ...
Given a source image and a driving video depicting the same object type,...
The goal of video highlight detection is to select the most attractive
s...
Real-time semantic segmentation, which aims to achieve high segmentation...
Creative image animations are attractive in e-commerce applications, whe...
In crowd counting, due to the problem of laborious labelling, it is perc...
The goal of few-shot learning is to learn a model that can recognize nov...
Renewable energy such as solar power is critical to fight the ever more
...
While deep learning has achieved remarkable results on various applicati...