Current state-of-the-art deep learning based face recognition (FR) model...
We propose a dense tensor accelerator called VectorMesh, a scalable,
mem...
In the interactive segmentation, users initially click on the target obj...
Person re-identification (re-ID) has received great success with the
sup...
Video-based person re-identification (Re-ID) aims at matching the video
...
Lossy image compression is often limited by the simplicity of the chosen...
Vehicle re-identification (re-ID) matches images of the same vehicle acr...
We investigate pruning and quantization for deep neural networks. Our go...
Person re-identification (re-ID) requires one to match images of the sam...
We propose GrateTile, an efficient, hardwarefriendly data storage scheme...
Vehicle re-identification (re-ID) focuses on matching images of the same...
Computationally intensive deep neural networks (DNNs) are well-suited to...
Digital media is ubiquitous and produced in ever-growing quantities. Thi...
Video-based person re-identification (Re-ID) aims at matching video sequ...
Most recent studies on deep learning based speech enhancement (SE) focus...
Reverberation, which is generally caused by sound reflections from walls...
Reverberation, which is generally caused by sound reflections from walls...
Deep Convolutional Neural Networks (CNN) have won a significant place in...
Photo composition is an important factor affecting the aesthetics in
pho...