Temporal segment networks: Towards good practices for deep action recognition

L Wang, Y **ong, Z Wang, Y Qiao, D Lin… - European conference on …, 2016 - Springer
Deep convolutional networks have achieved great success for visual recognition in still
images. However, for action recognition in videos, the advantage over traditional methods is …

Prompting visual-language models for efficient video understanding

C Ju, T Han, K Zheng, Y Zhang, W **e - European Conference on …, 2022 - Springer
Image-based visual-language (I-VL) pre-training has shown great success for learning joint
visual-textual representations from large-scale web data, revealing remarkable ability for …

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

Y Fu, T **ang, YG Jiang, X Xue… - IEEE Signal …, 2018 - ieeexplore.ieee.org
With the recent renaissance of deep convolutional neural networks (CNNs), encouraging
breakthroughs have been achieved on the supervised recognition tasks, where each class …

Transfer learning and its extensive appositeness in human activity recognition: A survey

A Ray, MH Kolekar - Expert Systems with Applications, 2024 - Elsevier
In this competitive world, the supervision and monitoring of human resources are primary
and necessary tasks to drive context-aware applications. Advancement in sensor and …

Graph convolutional networks for temporal action localization

R Zeng, W Huang, M Tan, Y Rong… - Proceedings of the …, 2019 - openaccess.thecvf.com
Most state-of-the-art action localization systems process each action proposal individually,
without explicitly exploiting their relations during learning. However, the relations between …

A survey of zero-shot learning: Settings, methods, and applications

W Wang, VW Zheng, H Yu, C Miao - ACM Transactions on Intelligent …, 2019 - dl.acm.org
Most machine-learning methods focus on classifying instances whose classes have already
been seen in training. In practice, many applications require classifying instances whose …

An empirical study and analysis of generalized zero-shot learning for object recognition in the wild

WL Chao, S Changpinyo, B Gong, F Sha - Computer Vision–ECCV 2016 …, 2016 - Springer
We investigate the problem of generalized zero-shot learning (GZSL). GZSL relaxes the
unrealistic assumption in conventional zero-shot learning (ZSL) that test data belong only to …

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 …

Human mesh recovery from monocular images via a skeleton-disentangled representation

Y Sun, Y Ye, W Liu, W Gao, Y Fu… - Proceedings of the …, 2019 - openaccess.thecvf.com
We describe an end-to-end method for recovering 3D human body mesh from single images
and monocular videos. Different from the existing methods try to obtain all the complex 3D …

Tore: Token reduction for efficient human mesh recovery with transformer

Z Dou, Q Wu, C Lin, Z Cao, Q Wu… - Proceedings of the …, 2023 - openaccess.thecvf.com
In this paper, we introduce a set of simple yet effective TOken REduction (TORE) strategies
for Transformer-based Human Mesh Recovery from monocular images. Current SOTA …