Gebruikersprofielen voor Yadong Mu
Yadong MuPeking University Geverifieerd e-mailadres voor pku.edu.cn Geciteerd door 9956 |
Deep high-resolution representation learning for visual recognition
High-resolution representations are essential for position-sensitive vision problems, such as
human pose estimation, semantic segmentation, and object detection. Existing state-of-the-…
human pose estimation, semantic segmentation, and object detection. Existing state-of-the-…
High-resolution representations for labeling pixels and regions
High-resolution representation learning plays an essential role in many vision problems, eg,
pose estimation and semantic segmentation. The high-resolution network (HRNet)~\cite{…
pose estimation and semantic segmentation. The high-resolution network (HRNet)~\cite{…
Fast fourier convolution
Vanilla convolutions in modern deep networks are known to operate locally and at fixed scale
(eg, the widely-adopted 3* 3 kernels in image-oriented tasks). This causes low efficacy in …
(eg, the widely-adopted 3* 3 kernels in image-oriented tasks). This causes low efficacy in …
Discriminative local binary patterns for human detection in personal album
In recent years, local pattern based object detection and recognition have attracted increasing
interest in computer vision research community. However, to our best knowledge no …
interest in computer vision research community. However, to our best knowledge no …
Recurrent attentive zooming for joint crowd counting and precise localization
Crowd counting is a new frontier in computer vision with far-reaching applications particularly
in social safety management. A majority of existing works adopt a methodology that first …
in social safety management. A majority of existing works adopt a methodology that first …
Weakly-supervised action localization by generative attention modeling
Weakly-supervised temporal action localization is a problem of learning an action localization
model with only video-level action labeling available. The general framework largely relies …
model with only video-level action labeling available. The general framework largely relies …
Weakly-supervised hashing in kernel space
The explosive growth of the vision data motivates the recent studies on efficient data indexing
methods such as locality-sensitive hashing (LSH). Most existing approaches perform …
methods such as locality-sensitive hashing (LSH). Most existing approaches perform …
Informative dropout for robust representation learning: A shape-bias perspective
Convolutional Neural Networks (CNNs) are known to rely more on local texture rather than
global shape when making decisions. Recent work also indicates a close relationship …
global shape when making decisions. Recent work also indicates a close relationship …
Attention-based multi-context guiding for few-shot semantic segmentation
Few-shot learning is a nascent research topic, motivated by the fact that traditional deep
learning methods require tremendous amounts of data. The scarcity of annotated data becomes …
learning methods require tremendous amounts of data. The scarcity of annotated data becomes …
Deep steering: Learning end-to-end driving model from spatial and temporal visual cues
In recent years, autonomous driving algorithms using low-cost vehicle-mounted cameras
have attracted increasing endeavors from both academia and industry. There are multiple …
have attracted increasing endeavors from both academia and industry. There are multiple …