Zobrazeno 1 - 10
of 88
pro vyhledávání: '"Jing HAO"'
Publikováno v:
IEEE Transactions on Affective Computing. 13:818-828
Facial Attribute Classification (FAC) has attracted increasing attention in computer vision and pattern recognition. However, state-of-the-art FAC methods perform face detection/alignment and FAC independently. The inherent dependencies between these
Publikováno v:
Neurocomputing. 456:463-468
Few-shot meta-learning has been recently reviving with expectations to mimic humanity's fast adaption to new concepts based on prior knowledge. In this short communication, we give a concise review on recent representative methods in few-shot meta-le
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. 32:4742-4747
In deep face recognition, the commonly used softmax loss and its newly proposed variations are not yet sufficiently effective to handle the class imbalance and softmax saturation issues during the training process while extracting discriminative feat
Publikováno v:
Neurocomputing. 453:465-481
Scene text detection plays a vital role for scene text understanding, but arbitrary-shaped text detection remains a significant challenge. To extract discriminative features, most recent state-of-the-art methods adopt heavy networks, resulting in par
Publikováno v:
Neurocomputing. 447:10-22
Traffic sign detection and recognition in the wild is a challenging task. Existing techniques are often incapable of detecting small or occluded traffic signs because of the scale variation and context loss, which causes semantic gaps between multipl
Publikováno v:
Neurocomputing. 450:362-371
Video action recognition is a vital area of computer vision. By adding temporal dimension into convolution structure, 3D convolution neural network owns the capacity to extract spatio-temporal features from videos. However, due to computing constrain
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 31:2764-2778
In recent years, deep learning-based person re-identification (Re-ID) methods have made significant progress. However, the performance of these methods substantially decreases when dealing with occlusion, which is ubiquitous in realistic scenarios. I
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 31:1332-1341
Human fingerprints are detailed and nearly unique markers of human identity. Such a unique and stable fingerprint is also left on each acquired image. It can reveal how an image was degraded during the image acquisition procedure and thus is closely
Publikováno v:
Neurocomputing. 428:259-267
Automatic speech recognition (ASR) is a crucial technology for man-machine interaction. End-to-end models have been studied recently in deep learning for ASR. However, these models are not suitable for the practical application of ASR due to their la
Publikováno v:
IEEE Signal Processing Letters. 28:658-662
Exploiting both RGB (2D appearance) and Depth (3D geometry) information can improve the performance of semantic segmentation. However, due to the inherent difference between the RGB and Depth information, it remains a challenging problem in how to in