research
∙
11/01/2021
AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsampling
Pooling layers are essential building blocks of Convolutional Neural Net...
share
research
∙
05/11/2021
Incremental Few-Shot Instance Segmentation
Few-shot instance segmentation methods are promising when labeled traini...
research
∙
11/08/2020
Right on Time: Multi-Temporal Convolutions for Human Action Recognition in Videos
The variations in the temporal performance of human actions observed in ...
research
∙
06/15/2020
Learn to cycle: Time-consistent feature discovery for action recognition
Temporal motion has been one of the essential components for effectively...
research
∙
02/07/2020
Learning Class Regularized Features for Action Recognition
Training Deep Convolutional Neural Networks (CNNs) is based on the notio...
research
∙
09/30/2019
Spatio-Temporal FAST 3D Convolutions for Human Action Recognition
Effective processing of video input is essential for the recognition of ...
research
∙
09/18/2019
Class Feature Pyramids for Video Explanation
Deep convolutional networks are widely used in video action recognition....
research
∙
09/15/2019
Multitask Learning to Improve Egocentric Action Recognition
In this work we employ multitask learning to capitalize on the structure...
research
∙
06/19/2019
Light Field Saliency Detection with Deep Convolutional Networks
CNN-based methods have been proven to work well for saliency detection o...
research
∙
05/02/2019
Egocentric Hand Track and Object-based Human Action Recognition
Egocentric vision is an emerging field of computer vision that is charac...
research
∙
02/04/2019
Saliency Tubes: Visual Explanations for Spatio-Temporal Convolutions
Deep learning approaches have been established as the main methodology f...
research
∙
11/05/2018
A personal model of trumpery: Deception detection in a real-world high-stakes setting
Language use reveals information about who we are and how we feel1-3. On...
research
∙
07/31/2018