This study presents a novel multimodal fusion model for three-dimensiona...
We introduce PointOdyssey, a large-scale synthetic dataset, and data
gen...
Regular object detection methods output rectangle bounding boxes, which ...
Compressed videos often exhibit visually annoying artifacts, known as
Pe...
Adversarial reprogramming allows stealing computational resources by
rep...
The convergence of policy gradient algorithms in reinforcement learning
...
We propose a novel method to reliably estimate the pose of a camera give...
Predicting human motion is critical for assistive robots and AR/VR
appli...
Recurrent Neural Networks (RNN) are ubiquitous computing systems for
seq...
The three-dimensional (3D) geological models are the typical and key dat...
Adversarial reprogramming allows repurposing a machine-learning model to...
We propose DeepMultiCap, a novel method for multi-person performance cap...
We prove three decomposition results for sparse positive (semi-)definite...
We present a novel Balanced Incremental Model Agnostic Meta Learning sys...
Point clouds have been widely adopted in 3D semantic scene understanding...
Random Recurrent Neural Networks (RRNN) are the simplest recurrent netwo...
Pedestrian detection is an essential task in autonomous driving research...
With the great achievement of artificial intelligence, vehicle technolog...
Most existing deep reinforcement learning (DRL) frameworks consider eith...
Starcraft II (SCII) is widely considered as the most challenging Real Ti...