We propose an online tracking algorithm that performs the object detecti...
We propose a memory efficient method, named Stochastic Backpropagation (...
In this paper, we present Long Short-term TRansformer (LSTR), a new temp...
Online tracking of multiple objects in videos requires strong capacity o...
We propose to predict the future trajectories of observed agents (e.g.,
...
We propose to detect Deepfake generated by face manipulation based on on...
Understanding the structure of the ice at the Earth's poles is important...
Video anomaly detection (VAD) has been extensively studied. However, res...
Passive visual systems typically fail to recognize objects in the amodal...
We propose StartNet to address Online Detection of Action Start (ODAS) w...
Recognizing abnormal events such as traffic violations and accidents in
...
Most work on temporal action detection is formulated in an offline manne...
Predicting the future location of vehicles is essential for safety-criti...
In a world in which cameras are becoming more and more pervasive, scenes...
Deep learning methods have surpassed the performance of traditional
tech...
A major emerging challenge is how to protect people's privacy as cameras...
Ground-penetrating radar on planes and satellites now makes it practical...