Recently, the sparse vector code (SVC) is emerging as a promising soluti...
In most existing grant-free (GF) studies, the two key tasks, namely acti...
Object detection is a basic computer vision task to loccalize and catego...
In this paper, a novel transceiver architecture is proposed to simultane...
We introduce a robust, real-time, high-resolution human video matting me...
Post-training quantization methods use a set of calibration data to comp...
Video inpainting aims to fill spatio-temporal "corrupted" regions with
p...
Vision transformers (ViTs) have been successfully applied in image
class...
Current neural architecture search (NAS) algorithms still require expert...
Video instance segmentation is a complex task in which we need to detect...
Model quantization helps to reduce model size and latency of deep neural...
Non-Local (NL) blocks have been widely studied in various vision tasks.
...
Quantization reduces computation costs of neural networks but suffers fr...
Deep neural networks with adaptive configurations have gained increasing...
Designing of search space is a critical problem for neural architecture
...
Human body part parsing refers to the task of predicting the semantic
se...
In this paper we present a new computer vision task, named video instanc...
We present a novel problem setting in zero-shot learning, zero-shot obje...
Dense video captioning is an extremely challenging task since accurate a...
We present a simple and general method to train a single neural network
...
Learning long-term spatial-temporal features are critical for many video...
Learning long-term spatial-temporal features are critical for many video...
Video object segmentation targets at segmenting a specific object throug...
Dense captioning is a newly emerging computer vision topic for understan...
Updated on 24/09/2015: This update provides preliminary experiment resul...