One-stage object detection is commonly implemented by optimizing two
sub...
Pair-wise loss functions have been extensively studied and shown to
cont...
Recent advances in neuroscience have highlighted the effectiveness of
mu...
Differentiable architecture search (DAS) has made great progress in sear...
Region Proposal Network (RPN) provides strong support for handling the s...
Siamese-based trackers have achieved excellent performance on visual obj...
Fine-grained image categorization is challenging due to the subtle
inter...
Training an object detector on a data-rich domain and applying it to a
d...
In this work, we propose Knowledge Integration Networks (referred as KIN...
Most existing 3D CNNs for video representation learning are clip-based
m...
Mining informative negative instances are of central importance to deep
...
Recent progress has been made on developing a unified framework for join...
Weakly-supervised instance segmentation aims to detect and segment objec...
We propose a Dual-Stream Pyramid Registration Network (referred as
Dual-...
A family of loss functions built on pair-based computation have been pro...
Visual compatibility is critical for fashion analysis, yet is missing in...
Gliomas are the most common primary brain malignancies, with different
d...
We present a novel hierarchical triplet loss (HTL) capable of automatica...
We present a simple yet efficient approach capable of training deep neur...