Zobrazeno 1 - 10
of 333
pro vyhledávání: '"Liu, Shih-Chii"'
Event cameras are advantageous for tasks that require vision sensors with low-latency and sparse output responses. However, the development of deep network algorithms using event cameras has been slow because of the lack of large labelled event camer
Externí odkaz:
http://arxiv.org/abs/2406.03439
Autor:
Chen, Qinyu, Kim, Kwantae, Gao, Chang, Zhou, Sheng, Jang, Taekwang, Delbruck, Tobi, Liu, Shih-Chii
This paper introduces, to the best of the authors' knowledge, the first fine-grained temporal sparsity-aware keyword spotting (KWS) IC leveraging temporal similarities between neighboring feature vectors extracted from input frames and network hidden
Externí odkaz:
http://arxiv.org/abs/2405.03905
Autor:
Wang, Zuowen, Gao, Chang, Wu, Zongwei, Conde, Marcos V., Timofte, Radu, Liu, Shih-Chii, Chen, Qinyu, Zha, Zheng-jun, Zhai, Wei, Han, Han, Liao, Bohao, Wu, Yuliang, Wan, Zengyu, Wang, Zhong, Cao, Yang, Tan, Ganchao, Chen, Jinze, Pei, Yan Ru, Brüers, Sasskia, Crouzet, Sébastien, McLelland, Douglas, Coenen, Oliver, Zhang, Baoheng, Gao, Yizhao, Li, Jingyuan, So, Hayden Kwok-Hay, Bich, Philippe, Boretti, Chiara, Prono, Luciano, Lică, Mircea, Dinucu-Jianu, David, Grîu, Cătălin, Lin, Xiaopeng, Ren, Hongwei, Cheng, Bojun, Zhang, Xinan, Vial, Valentin, Yezzi, Anthony, Tsai, James
This survey reviews the AIS 2024 Event-Based Eye Tracking (EET) Challenge. The task of the challenge focuses on processing eye movement recorded with event cameras and predicting the pupil center of the eye. The challenge emphasizes efficient eye tra
Externí odkaz:
http://arxiv.org/abs/2404.11770
Epilepsy is a common disease of the nervous system. Timely prediction of seizures and intervention treatment can significantly reduce the accidental injury of patients and protect the life and health of patients. This paper presents a neuromorphic Sp
Externí odkaz:
http://arxiv.org/abs/2402.09424
Autor:
Chen, Xi, Gao, Chang, Wang, Zuowen, Cheng, Longbiao, Zhou, Sheng, Liu, Shih-Chii, Delbruck, Tobi
Recurrent Neural Networks (RNNs) are useful in temporal sequence tasks. However, training RNNs involves dense matrix multiplications which require hardware that can support a large number of arithmetic operations and memory accesses. Implementing onl
Externí odkaz:
http://arxiv.org/abs/2312.09391
Publikováno v:
2023 IEEE Biomedical Circuits and Systems Conference (BioCAS)
This paper presents a sparse Change-Based Convolutional Long Short-Term Memory (CB-ConvLSTM) model for event-based eye tracking, key for next-generation wearable healthcare technology such as AR/VR headsets. We leverage the benefits of retina-inspire
Externí odkaz:
http://arxiv.org/abs/2308.11771
Autor:
Ott, Joachim, Liu, Shih-Chii
This work proposes a model for continual learning on tasks involving temporal sequences, specifically, human motions. It improves on a recently proposed brain-inspired replay model (BI-R) by building a biologically-inspired conditional temporal varia
Externí odkaz:
http://arxiv.org/abs/2211.05231
Autor:
Kim, Kwantae, Gao, Chang, Graça, Rui, Kiselev, Ilya, Yoo, Hoi-Jun, Delbruck, Tobi, Liu, Shih-Chii
This article presents the first keyword spotting (KWS) IC which uses a ring-oscillator-based time-domain processing technique for its analog feature extractor (FEx). Its extensive usage of time-encoding schemes allows the analog audio signal to be pr
Externí odkaz:
http://arxiv.org/abs/2208.00693
Autor:
Kim, Kwantae, Liu, Shih-Chii
Edge audio devices can reduce data bandwidth requirements by pre-processing input speech on the device before transmission to the cloud. As edge devices are required to ensure always-on operation, their stringent power constraints pose several design
Externí odkaz:
http://arxiv.org/abs/2206.02639
Reducing energy consumption is a critical point for neural network models running on edge devices. In this regard, reducing the number of multiply-accumulate (MAC) operations of Deep Neural Networks (DNNs) running on edge hardware accelerators will r
Externí odkaz:
http://arxiv.org/abs/2204.01460