Person re-identification (Re-ID) via gait features within 3D skeleton sequences is a newly-emerging topic with several advantages. Existing solutions either rely on hand-crafted descriptors or supe…
Designing effective architectures is one of the key factors behind the success of deep neural networks. Existing deep architectures are either manually designed or automatically searched by some Ne…
This paper focuses on the challenging task of learning 3D object surface reconstructions from RGB images. Existing methods achieve varying degrees of success by using different surface representati…
Temporal action localization, which requires a machine to recognize the location as well as the category of action instances in videos, has long been researched in computer vision. The main challen…
This paper tackles the problem of training a deep convolutional neural network of both low-bitwidth weights and activations. Optimizing a low-precision network is very challenging due to the non-di…
We study network pruning which aims to remove redundant channels/kernels and hence speed up the inference of deep networks. Existing pruning methods either train from scratch with sparsity constrai…
This paper proposes an electronic-photonic converged adaptive-tuning-step (ATS) pipelined time-division-multiplexing (PTDM) scheme to achieve fast wavelength locking of multiple micro-ring resonato…
The click feature of an image, defined as the user click frequency vector of the image on a predefined word vocabulary, is known to effectively reduce the semantic gap for fine-grained image recogn…
High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-of-the-art framework…
In this article, we experimentally demonstrate the combined benefit of artificial neural network-based nonlinearity compensation and probabilistic shaping for the first time. We demonstrate that th…