Zobrazeno 1 - 10 of 163 pro vyhledávání: '"Rao, Raghuveer M"'
1
Report
AMD: Automatic Multi-step Distillation of Large-scale Vision Models
Autor: Han, Cheng, Wang, Qifan, Dianat, Sohail A., Rabbani, Majid, Rao, Raghuveer M., Fang, Yi, Guan, Qiang, Huang, Lifu, Liu, Dongfang
Transformer-based architectures have become the de-facto standard models for diverse vision tasks owing to their superior performance. As the size of the models continues to scale up, model distillation becomes extremely important in various real app
Externí odkaz: http://arxiv.org/abs/2407.04208
Zobrazit plný text záznamu
2
Report
Prototypical Transformer as Unified Motion Learners
Autor: Han, Cheng, Lu, Yawen, Sun, Guohao, Liang, James C., Cao, Zhiwen, Wang, Qifan, Guan, Qiang, Dianat, Sohail A., Rao, Raghuveer M., Geng, Tong, Tao, Zhiqiang, Liu, Dongfang
In this work, we introduce the Prototypical Transformer (ProtoFormer), a general and unified framework that approaches various motion tasks from a prototype perspective. ProtoFormer seamlessly integrates prototype learning with Transformer by thought
Externí odkaz: http://arxiv.org/abs/2406.01559
Zobrazit plný text záznamu
4
Report
Human Action Attribute Learning From Video Data Using Low-Rank Representations
Autor: Wu, Tong, Gurram, Prudhvi, Rao, Raghuveer M., Bajwa, Waheed U.
Representation of human actions as a sequence of human body movements or action attributes enables the development of models for human activity recognition and summarization. We present an extension of the low-rank representation (LRR) model, termed
Externí odkaz: http://arxiv.org/abs/1612.07857
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje