Learning the Fusion of Video Data Streams

2003 ◽  
pp. 61-79 ◽  
Author(s):  
J. Renno ◽  
P. Remagnino ◽  
G. A. Jones
Keyword(s):  
Data Streams ◽  
Video Data

Cognitively Motivated Novelty Detection in Video Data Streams

2007 ◽  
pp. 209-233
Author(s):  
James M. Kang ◽  
Muhammad Aurangzeb Ahmad ◽  
Ankur Teredesai ◽  
Roger Gaborski
Keyword(s):  
Data Streams ◽  
Novelty Detection ◽  
Video Data

scholarly journals Learning neural decoders without labels using multiple data streams

2021 ◽  
Author(s):  
Steven M. Peterson ◽  
Rajesh P. N. Rao ◽  
Bingni W. Brunton
Keyword(s):  
Real World ◽  
Data Streams ◽  
Video Data ◽  
Neural Decoding ◽  
Computer Interfaces ◽  
Multiple Data ◽  
Real World Applications ◽  
Recorded Data ◽  
Robust Adaptive ◽  
Decoding Accuracy

AbstractRecent advances in neural decoding have accelerated the development of brain-computer interfaces aimed at assisting users with everyday tasks such as speaking, walking, and manipulating objects. However, current approaches for training neural decoders commonly require large quantities of labeled data, which can be laborious or infeasible to obtain in real-world settings. One intriguing alternative uses self-supervised models that share self-generated pseudo-labels between two data streams; such models have shown exceptional performance on unlabeled audio and video data, but it remains unclear how well they extend to neural decoding. Here, we learn neural decoders without labels by leveraging multiple simultaneously recorded data streams, including neural, kinematic, and physiological signals. Specifically, we apply cross-modal, self-supervised deep clustering to decode movements from brain recordings; these decoders are compared to supervised and unimodal, self-supervised models. We find that sharing pseudo-labels between two data streams during training substantially increases decoding performance compared to unimodal, self-supervised models, with accuracies approaching those of supervised decoders trained on labeled data. Next, we develop decoders trained on three modalities that match or slightly exceed the performance of supervised models, achieving state-of-the-art neural decoding accuracy. Cross-modal decoding is a flexible, promising approach for robust, adaptive neural decoding in real-world applications without any labels.

An adaptive QoS control method in the multichannel communication of the MPEG video data streams

2003 ◽  
Vol 86 (10) ◽  
pp. 66-78
Author(s):  
Kentaro Ogawa ◽  
Katsunori Yamaoka ◽  
Yoshinori Sakai
Keyword(s):  
Data Streams ◽  
Control Method ◽  
Video Data ◽  
Qos Control ◽  
Adaptive Qos

SpaceFibre based on-board networks for real-time video data streams: SpaceFibre, long paper

2016 ◽  
Author(s):  
Alexey Khakhulin ◽  
Igor Orlovsky ◽  
Yuriy Sheynin ◽  
Ilya Korobkov ◽  
Valentin Olenev ◽  
...  
Keyword(s):  
Real Time ◽  
Data Streams ◽  
Video Data ◽  
Board Networks

Design of multichannel communication system of the MPEG video data streams using adaptive QoS control

2004 ◽  
Vol 87 (10) ◽  
pp. 81-92
Author(s):  
Kentaro Ogawa ◽  
Aki Kobayashi ◽  
Katsunori Yamaoka ◽  
Yoshinori Sakai
Keyword(s):  
Data Streams ◽  
Communication System ◽  
Video Data ◽  
Qos Control ◽  
Adaptive Qos
Sign in / Sign up

Export Citation Format

Share Document