Parallel spatio-temporal attention-based TCN for multivariate time series prediction

J Fan, K Zhang, Y Huang, Y Zhu, B Chen - Neural Computing and …, 2023 - Springer
As industrial systems become more complex and monitoring sensors for everything from
surveillance to our health become more ubiquitous, multivariate time series prediction is …

Asformer: Transformer for action segmentation

F Yi, H Wen, T Jiang - arXiv preprint arXiv:2110.08568, 2021 - arxiv.org
Algorithms for the action segmentation task typically use temporal models to predict what
action is occurring at each frame for a minute-long daily activity. Recent studies have shown …

Ms-tct: Multi-scale temporal convtransformer for action detection

R Dai, S Das, K Kahatapitiya… - Proceedings of the …, 2022 - openaccess.thecvf.com
Action detection is an essential and challenging task, especially for densely labelled
datasets of untrimmed videos. The temporal relation is complex in those datasets, including …

Learning an augmented rgb representation with cross-modal knowledge distillation for action detection

R Dai, S Das, F Bremond - Proceedings of the IEEE/CVF …, 2021 - openaccess.thecvf.com
In video understanding, most cross-modal knowledge distillation (KD) methods are tailored
for classification tasks, focusing on the discriminative representation of the trimmed videos …

Pdan: Pyramid dilated attention network for action detection

R Dai, S Das, L Minciullo, L Garattoni… - Proceedings of the …, 2021 - openaccess.thecvf.com
Handling long and complex temporal information is an important factor for action detection
tasks. This challenge is further aggravated by densely distributed actions in untrimmed …

Two birds with one stone: Knowledge-embedded temporal convolutional transformer for depression detection and emotion recognition

W Zheng, L Yan, FY Wang - IEEE Transactions on Affective …, 2023 - ieeexplore.ieee.org
Depression is a critical problem in modern society that affects an estimated 350 million
people worldwide, causing feelings of sadness and a lack of interest and pleasure …

Pay attention to doctor–patient dialogues: Multi-modal knowledge graph attention image-text embedding for COVID-19 diagnosis

W Zheng, L Yan, C Gou, ZC Zhang, JJ Zhang, M Hu… - Information …, 2021 - Elsevier
The sudden increase in coronavirus disease 2019 (COVID-19) cases puts high pressure on
healthcare services worldwide. At this stage, fast, accurate, and early clinical assessment of …

Self-attention transfer networks for speech emotion recognition

Z Zhao, K Wang, Z Bao, Z Zhang, N Cummins… - Virtual Reality & …, 2021 - Elsevier
Background A crucial element of human–machine interaction, the automatic detection of
emotional states from human speech has long been regarded as a challenging task for …

Opitrack: a wearable-based clinical opioid use tracker with temporal convolutional attention networks

BT Gullapalli, S Carreiro, BP Chapman… - Proceedings of the …, 2021 - dl.acm.org
Opioid use disorder is a medical condition with major social and economic consequences.
While ubiquitous physiological sensing technologies have been widely adopted and …

Ctrn: Class-temporal relational network for action detection

R Dai, S Das, F Bremond - arXiv preprint arXiv:2110.13473, 2021 - arxiv.org
Action detection is an essential and challenging task, especially for densely labelled
datasets of untrimmed videos. There are many real-world challenges in those datasets, such …