Fine-grained open-set recognition (FineOSR) aims to recognize images
bel...
Neural pathways as model explanations consist of a sparse set of neurons...
Hand trajectory forecasting from egocentric views is crucial for enablin...
The compositional zero-shot learning (CZSL) task aims to recognize unsee...
The popular VQ-VAE models reconstruct images through learning a discrete...
Online action detection is the task of predicting the action as soon as ...
We present a novel dynamic recommendation model that focuses on users wh...
This paper concerns the problem of multi-object tracking based on the
mi...
Temporal Action Localization (TAL) has experienced remarkable success un...
Deep learning models have been shown to be vulnerable to adversarial att...
Action prediction aims to infer the forthcoming human action with
partia...
In many applications, it is essential to understand why a machine learni...
Traffic accident anticipation aims to accurately and promptly predict th...
In a real-world scenario, human actions are typically out of the distrib...
Widely deployed deep neural network (DNN) models have been proven to be
...
In this paper, we propose a novel approach to predict group activities g...
Traffic accident anticipation aims to predict accidents from dashcam vid...
Monocular 3D object detection aims to detect objects in a 3D physical wo...
The accuracy of OCR is usually affected by the quality of the input docu...
Image deblurring is a fundamental and challenging low-level vision probl...
Convolutional neural network has recently achieved great success for ima...
Derived from rapid advances in computer vision and machine learning, vid...
A very deep convolutional neural network (CNN) has recently achieved gre...