Transfer learning enhanced vision-based human activity recognition: a decade-long analysis

A Ray, MH Kolekar, R Balasubramanian… - International Journal of …, 2023 - Elsevier
The discovery of several machine learning and deep learning techniques has paved the
way to extend the reach of humans in various real-world applications. Classical machine …

Recent advances in zero-shot recognition: Toward data-efficient understanding of visual content

Y Fu, T ** network
K Gong, X Liang, Y Li, Y Chen… - Proceedings of the …, 2018 - openaccess.thecvf.com
Instance-level human parsing towards real-world human analysis scenarios is still under-
explored due to the absence of sufficient data resources and technical difficulty in parsing …

Look into person: Joint body parsing & pose estimation network and a new benchmark

X Liang, K Gong, X Shen, L Lin - IEEE transactions on pattern …, 2018 - ieeexplore.ieee.org
Human parsing and pose estimation have recently received considerable interest due to
their substantial application potentials. However, the existing datasets have limited numbers …

Look into person: Self-supervised structure-sensitive learning and a new benchmark for human parsing

K Gong, X Liang, D Zhang… - Proceedings of the …, 2017 - openaccess.thecvf.com
Human parsing has recently attracted a lot of research interests due to its huge application
potentials. However existing datasets have limited number of images and annotations, and …

Elaborative rehearsal for zero-shot action recognition

S Chen, D Huang - Proceedings of the IEEE/CVF …, 2021 - openaccess.thecvf.com
The growing number of action classes has posed a new challenge for video understanding,
making Zero-Shot Action Recognition (ZSAR) a thriving direction. The ZSAR task aims to …

Semantic object parsing with graph lstm

X Liang, X Shen, J Feng, L Lin, S Yan - … 11–14, 2016, Proceedings, Part I …, 2016 - Springer
By taking the semantic object parsing task as an exemplar application scenario, we propose
the Graph Long Short-Term Memory (Graph LSTM) network, which is the generalization of …

I know the relationships: Zero-shot action recognition via two-stream graph convolutional networks and knowledge graphs

J Gao, T Zhang, C Xu - Proceedings of the AAAI conference on artificial …, 2019 - aaai.org
Recently, with the ever-growing action categories, zero-shot action recognition (ZSAR) has
been achieved by automatically mining the underlying concepts (eg, actions, attributes) in …

Two-stream 3-d convnet fusion for action recognition in videos with arbitrary size and length

X Wang, L Gao, P Wang, X Sun… - IEEE Transactions on …, 2017 - ieeexplore.ieee.org
3-D convolutional neural networks (3-D-convNets) have been very recently proposed for
action recognition in videos, and promising results are achieved. However, existing 3-D …

Rethinking zero-shot video classification: End-to-end training for realistic applications

B Brattoli, J Tighe, F Zhdanov… - Proceedings of the …, 2020 - openaccess.thecvf.com
Trained on large datasets, deep learning (DL) can accurately classify videos into hundreds
of diverse classes. However, video data is expensive to annotate. Zero-shot learning (ZSL) …