Robust 3D perception under corruption has become an essential task for t...
The comprehension of how local interactions arise in global collective
b...
Reinforcement learning is still struggling with solving long-horizon sur...
Deep convolutional neural networks have recently shown promising results...
The Five-hundred-meter Aperture Spherical radio Telescope (FAST) is the
...
Label noise and class imbalance commonly coexist in real-world data. Pre...
We present a novel two-stage fully sparse convolutional 3D object detect...
3D object detection with multi-sensors is essential for an accurate and
...
Automatic diabetic retinopathy (DR) lesions segmentation makes great sen...
Corrupted labels and class imbalance are commonly encountered in practic...
Fine-grained geometry, captured by aggregation of point features in loca...
We consider a new algorithm in light of the min-max Collatz-Wielandt
for...
Most of the existing Siamese-based trackers treat tracking problem as a
...
Offline Siamese networks have achieved very promising tracking performan...
Graph Convolutional Networks (GCNs), which model skeleton data as graphs...
Modeling layout is an important first step for graphic design. Recently,...
The performance of 3D object detection models over point clouds highly
d...
Layout is important for graphic design and scene generation. We propose ...
Face analytics benefits many multimedia applications. It consists of a n...
In this work, we present a simple, highly efficient and modularized Dual...
Detecting small objects is notoriously challenging due to their low
reso...
Most of existing detection pipelines treat object proposals independentl...
Modern deep neural network based object detection methods typically clas...
Video object detection is challenging because objects that are easily
de...