126 citations
- Huawei Technologies (China)CN21 papers
- Peking UniversityCN10 papers
- Huawei Technologies (Sweden)SE7 papers
- Huawei Technologies (United States)US6 papers
- University College LondonGB5 papers
- University of Hong KongHK5 papers
- Hong Kong University of Science and TechnologyHK3 papers
- Lomonosov Moscow State UniversityRU3 papers
- National Research University Higher School of EconomicsRU3 papers
- Shanghai Jiao Tong UniversityCN3 papers
- Southern University of Science and TechnologyCN3 papers
- Tsinghua UniversityCN3 papers
4 papers · 2 filters
Machine vision-aware quality metrics for compressed image and video assessment
Mikhail Dremin, Konstantin Kozhemyakov, Ivan Molodetskikh +3
A main goal in developing video-compression algorithms is to enhance human-perceived visual quality while maintaining file size. But modern video-analysis efforts such as detection…
Adaptive Parametric Activation: Unifying and Generalising Activation Functions Across Tasks
Konstantinos Panagiotis Alexandridis, Jiankang Deng, Anh Nguyen +1
The activation function plays a crucial role in model optimisation, yet the optimal choice remains unclear. For example, the Sigmoid activation is the de-facto activation in balanc…
Spatio-temporal Prompting Network for Robust Video Feature Extraction
Guanxiong Sun, Chi Wang, Zhaoyu Zhang +3
Frame quality deterioration is one of the main challenges in the field of video understanding. To compensate for the information loss caused by deteriorated frames, recent approach…
Full-Body Motion Reconstruction with Sparse Sensing from Graph Perspective
Feiyu Yao, Zongkai Wu, Li Yi
Estimating 3D full-body pose from sparse sensor data is a pivotal technique employed for the reconstruction of realistic human motions in Augmented Reality and Virtual Reality. How…