[图书][B] Newsmakers: Artificial intelligence and the future of journalism
F Marconi - 2020 - degruyter.com
The Newsmaker has been assigned to cover a debate between two politicians. In looking for
a new angle that provides a different way for her readers to understand the event, the …
a new angle that provides a different way for her readers to understand the event, the …
Deep 360 pilot: Learning a deep agent for piloting through 360 sports videos
Watching a 360° sports video requires a viewer to continuously select a viewing angle,
either through a sequence of mouse clicks or head movements. To relieve the viewer from …
either through a sequence of mouse clicks or head movements. To relieve the viewer from …
Interpreting deep learning-based networking systems
While many deep learning (DL)-based networking systems have demonstrated superior
performance, the underlying Deep Neural Networks (DNNs) remain blackboxes and stay …
performance, the underlying Deep Neural Networks (DNNs) remain blackboxes and stay …
Transition forests: Learning discriminative temporal transitions for action recognition and detection
G Garcia-Hernando, TK Kim - Proceedings of the IEEE …, 2017 - openaccess.thecvf.com
A human action can be seen as transitions between one's body poses over time, where the
transition depicts a temporal relation between two poses. Recognizing actions thus involves …
transition depicts a temporal relation between two poses. Recognizing actions thus involves …
[PDF][PDF] Classification of puck possession events in ice hockey
Group activity recognition in sports is often challenging due to the complex dynamics and
interaction among the players. In this paper, we propose a recurrent neural network to …
interaction among the players. In this paper, we propose a recurrent neural network to …
What can we learn from autonomous level-5 motorsport?
Whether BMW, VW or Google: Almost all leading automobile and technology companies are
researching and developing the multi-stage autonomy of vehicles, which enables a …
researching and developing the multi-stage autonomy of vehicles, which enables a …
Multi-task learning for joint re-identification, team affiliation, and role classification for sports visual tracking
AM Mansourian, V Somers… - Proceedings of the 6th …, 2023 - dl.acm.org
Effective tracking and re-identification of players is essential for analyzing soccer videos.
But, it is a challenging task due to the non-linear motion of players, the similarity in …
But, it is a challenging task due to the non-linear motion of players, the similarity in …
Learning to capture a film-look video with a camera drone
The development of intelligent drones has simplified aerial filming and provided smarter
assistant tools for users to capture a film-look footage. Existing methods of autonomous …
assistant tools for users to capture a film-look footage. Existing methods of autonomous …
Predicting head pose from speech with a conditional variational autoencoder
Natural movement plays a significant role in realistic speech animation. Numerous studies
have demonstrated the contribution visual cues make to the degree we, as human …
have demonstrated the contribution visual cues make to the degree we, as human …
A two-point method for PTZ camera calibration in sports
Calibrating narrow field of view soccer cameras is challenging because there are very few
field markings in the image. Unlike previous solutions, we propose a two-point method …
field markings in the image. Unlike previous solutions, we propose a two-point method …