Zobrazeno 1 - 10
of 142
pro vyhledávání: '"de Salvo, Barbara"'
Autor:
Zhang, Sai Qian, Li, Ziyun, Guo, Chuan, Mahloujifar, Saeed, Dangwal, Deeksha, Suh, Edward, De Salvo, Barbara, Liu, Chiao
Inverting visual representations within deep neural networks (DNNs) presents a challenging and important problem in the field of security and privacy for deep learning. The main goal is to invert the features of an unidentified target image generated
Externí odkaz:
http://arxiv.org/abs/2412.10448
Autor:
Hsieh, He-Yen, Li, Ziyun, Zhang, Sai Qian, Ting, Wei-Te Mark, Chang, Kao-Den, De Salvo, Barbara, Liu, Chiao, Kung, H. T.
We present GazeGen, a user interaction system that generates visual content (images and videos) for locations indicated by the user's eye gaze. GazeGen allows intuitive manipulation of visual content by targeting regions of interest with gaze. Using
Externí odkaz:
http://arxiv.org/abs/2411.04335
Autor:
Parmar, Vivek, Bane, Dwijay, Sarwar, Syed Shakib, Stangherlin, Kleber, De Salvo, Barbara, Suri, Manan
With the emergence of the Metaverse and focus on wearable devices in the recent years gesture based human-computer interaction has gained significance. To enable gesture recognition for VR/AR headsets and glasses several datasets focusing on egocentr
Externí odkaz:
http://arxiv.org/abs/2410.19486
Autor:
Augustin, Maximilian, Sarwar, Syed Shakib, Elhoushi, Mostafa, Zhang, Sai Qian, Li, Yuecheng, De Salvo, Barbara
Following their success in natural language processing (NLP), there has been a shift towards transformer models in computer vision. While transformers perform well and offer promising multi-tasking performance, due to their high compute requirements,
Externí odkaz:
http://arxiv.org/abs/2410.17661
Autor:
Zhao, Yiwei, Li, Ziyun, Khwa, Win-San, Sun, Xiaoyu, Zhang, Sai Qian, Sarwar, Syed Shakib, Stangherlin, Kleber Hugo, Lu, Yi-Lun, Gomez, Jorge Tomas, Seo, Jae-Sun, Gibbons, Phillip B., De Salvo, Barbara, Liu, Chiao
Low-Latency and Low-Power Edge AI is essential for Virtual Reality and Augmented Reality applications. Recent advances show that hybrid models, combining convolution layers (CNN) and transformers (ViT), often achieve superior accuracy/performance tra
Externí odkaz:
http://arxiv.org/abs/2410.08326
Autor:
Prasad, Arpan Suravi, Scherer, Moritz, Conti, Francesco, Rossi, Davide, Di Mauro, Alfio, Eggimann, Manuel, Gómez, Jorge Tómas, Li, Ziyun, Sarwar, Syed Shakib, Wang, Zhao, De Salvo, Barbara, Benini, Luca
Extended reality (XR) applications are Machine Learning (ML)-intensive, featuring deep neural networks (DNNs) with millions of weights, tightly latency-bound (10-20 ms end-to-end), and power-constrained (low tens of mW average power). While ML perfor
Externí odkaz:
http://arxiv.org/abs/2312.14750
The limited and dynamically varied resources on edge devices motivate us to deploy an optimized deep neural network that can adapt its sub-networks to fit in different resource constraints. However, existing works often build sub-networks through sea
Externí odkaz:
http://arxiv.org/abs/2207.00670
Autor:
Parmar, Vivek, Sarwar, Syed Shakib, Li, Ziyun, Lee, Hsien-Hsin S., De Salvo, Barbara, Suri, Manan
Low-Power Edge-AI capabilities are essential for on-device extended reality (XR) applications to support the vision of Metaverse. In this work, we investigate two representative XR workloads: (i) Hand detection and (ii) Eye segmentation, for hardware
Externí odkaz:
http://arxiv.org/abs/2206.06780
We design deep neural networks (DNNs) and corresponding networks' splittings to distribute DNNs' workload to camera sensors and a centralized aggregator on head mounted devices to meet system performance targets in inference accuracy and latency unde
Externí odkaz:
http://arxiv.org/abs/2204.04705