Search Results - "Vitaladevuni, Shiv"

Wiring Economy and Volume Exclusion Determine Neuronal Placement in the Drosophila Brain by Rivera-Alba, Marta, Vitaladevuni, Shiv N., Mishchenko, Yuriy, Lu, Zhiyuan, Takemura, Shin-ya, Scheffer, Lou, Meinertzhagen, Ian A., Chklovskii, Dmitri B., de Polavieja, Gonzalo G.

“…Wiring economy has successfully explained the individual placement of neurons in simple nervous systems like that of Caenorhabditis elegans [1–3] and the…”
Get full text

A visual motion detection circuit suggested by Drosophila connectomics by Takemura, Shin-ya, Bharioke, Arjun, Lu, Zhiyuan, Nern, Aljoscha, Vitaladevuni, Shiv, Rivlin, Patricia K., Katz, William T., Olbris, Donald J., Plaza, Stephen M., Winston, Philip, Zhao, Ting, Horne, Jane Anne, Fetter, Richard D., Takemura, Satoko, Blazek, Katerina, Chang, Lei-Ann, Ogundeyi, Omotara, Saunders, Mathew A., Shapiro, Victor, Sigmund, Christopher, Rubin, Gerald M., Scheffer, Louis K., Meinertzhagen, Ian A., Chklovskii, Dmitri B.

“…Animal behaviour arises from computations in neuronal circuits, but our understanding of these computations has been frustrated by the lack of detailed…”
Get full text

Semi-automated reconstruction of neural circuits using electron microscopy by Chklovskii, Dmitri B, Vitaladevuni, Shiv, Scheffer, Louis K

“…Reconstructing neuronal circuits at the level of synapses is a central problem in neuroscience, and the focus of the nascent field of connectomics. Previously…”
Get full text

Monophone-Based Background Modeling for Two-Stage On-Device Wake Word Detection by Wu, Minhua, Panchapagesan, Sankaran, Sun, Ming, Gu, Jiacheng, Thomas, Ryan, Prasad Vitaladevuni, Shiv Naga, Hoffmeister, Bjorn, Mandal, Arindam

“…Accurate on-device wake word detection is crucial to products with far-field voice control such as the Amazon Echo. It is quite challenging to build a wake…”
Get full text

Robust EEG emotion classification using segment level decision fusion by Rozgic, Viktor, Vitaladevuni, Shiv N., Prasad, Rohit

“…In this paper we address single-trial binary classification of emotion dimensions (arousal, valence, dominance and liking) using electroencephalogram (EEG)…”
Get full text

Wiring Economy and Volume Exclusion Determine Neuronal Placement in the Drosophila Brain by Rivera-Alba, Marta, Vitaladevuni, Shiv N., Mishchenko, Yuriy, Lu, Zhiyuan, Takemura, Shin-ya, Scheffer, Lou, Meinertzhagen, Ian A., Chklovskii, Dmitri B., de Polavieja, Gonzalo G.

Get full text

Action recognition using ballistic dynamics by Vitaladevuni, S.N., Kellokumpu, V., Davis, L.S.

“…We present a Bayesian framework for action recognition through ballistic dynamics. Psycho-kinesiological studies indicate that ballistic movements form the…”
Get full text

Towards Data-Efficient Modeling for Wake Word Spotting by Gao, Yixin, Mishchenko, Yuriy, Shah, Anish, Matsoukas, Spyros, Vitaladevuni, Shiv

“…Wake word (WW) spotting is challenging in far-field not only because of the interference in signal transmission but also the complexity in acoustic…”
Get full text

Multimodal feature fusion for robust event detection in web videos by Natarajan, P., Shuang Wu, Vitaladevuni, S., Xiaodan Zhuang, Tsakalidis, S., Unsang Park, Prasad, R., Natarajan, P.

“…Combining multiple low-level visual features is a proven and effective strategy for a range of computer vision tasks. However, limited attention has been paid…”
Get full text

Electron Microscopy Reconstruction of Brain Structure Using Sparse Representations Over Learned Dictionaries by Tao Hu, Nunez-Iglesias, Juan, Vitaladevuni, Shiv, Scheffer, Lou, Shan Xu, Bolorizadeh, Mehdi, Hess, Harald, Fetter, Richard, Chklovskii, Dmitri B.

“…A central problem in neuroscience is reconstructing neuronal circuits on the synapse level. Due to a wide range of scales in brain architecture such…”
Get full text

Co-clustering of image segments using convex optimization applied to EM neuronal reconstruction by Vitaladevuni, S N, Basri, R

“…This paper addresses the problem of jointly clustering two segmentations of closely correlated images. We focus in particular on the application of…”
Get full text

Max-pooling loss training of long short-term memory networks for small-footprint keyword spotting by Ming Sun, Raju, Anirudh, Tucker, George, Panchapagesan, Sankaran, Gengshen Fu, Mandal, Arindam, Matsoukas, Spyros, Strom, Nikko, Vitaladevuni, Shiv

“…We propose a max-pooling based loss function for training Long Short-Term Memory (LSTM) networks for small-footprint keyword spotting (KWS), with low CPU,…”
Get full text

A visual motion detection circuit suggested by Drosophila connectomics by Takemura, Shin-ya, Bharioke, Arjun, Lu, Zhiyuan, Nern, Aljoscha, Vitaladevuni, Shiv, Rivlin, Patricia K, Katz, William T, Olbris, Donald J, Plaza, Stephen M, Winston, Philip, Zhao, Ting, Horne, Jane Anne, Fetter, Richard D, Takemura, Satoko, Blazek, Katerina, Chang, Lei-Ann, Ogundeyi, Omotara, Saunders, Mathew A, Shapiro, Victor, Sigmund, Christopher, Rubin, Gerald M, Scheffer, Louis K, Meinertzhagen, Ian A, Chklovskii, Dmitri B

“…Animal behaviour arises from computations in neuronal circuits, but our understanding of these computations has been frustrated by the lack of detailed…”
Get full text

Avisual motion detection circuit suggested by Drosophila connectomics by Takemura, Shin-ya, Bharioke, Arjun, Lu, Zhiyuan, Nern, Aljoscha, Vitaladevuni, Shiv, Rivlin, Patricia K, Katz, William T, Olbris, Donald J, Plaza, Stephen M, Winston, Philip, Zhao, Ting, Horne, Jane Anne, Fetter, Richard D, Takemura, Satoko, Blazek, Katerina, Chang, Lei-Ann, Ogundeyi, Omotara, Saunders, Mathew A, Shapiro, Victor, Sigmund, Christopher, Rubin, Gerald M, Scheffer, Louis K, Meinertzhagen, Ian A, Chklovskii, Dmitri B

“…Animal behaviour arises from computations in neuronal circuits, but our understanding of these computations has been frustrated by the lack of detailed…”
Get full text

Efficient Orthogonal Matching Pursuit using sparse random projections for scene and video classification by Vitaladevuni, S. N., Natarajan, P., Prasad, R., Natarajan, P.

“…Sparse projection has been shown to be highly effective in several domains, including image denoising and scene / object classification. However, practical…”
Get full text

Detecting near-duplicate document images using interest point matching by Vitaladevuni, S., Choi, F., Prasad, R., Natarajan, P.

“…We present an approach to detecting near-duplicate document images using SIFT interest point matching. Given a set of document images, a database is…”
Get full text

Contour-based joint clustering of multiple segmentations by Glasner, D., Vitaladevuni, S. N., Basri, R.

“…We present an unsupervised, shape-based method for joint clustering of multiple image segmentations. Given two or more closely-related images, such as nearby…”
Get full text

Combining multiple kernels for efficient image classification by Siddiquie, B., Vitaladevuni, S.N., Davis, L.S.

“…We investigate the problem of combining multiple feature channels for the purpose of efficient image classification. Discriminative kernel based methods, such…”
Get full text

Low-Bit Quantization and Quantization-Aware Training for Small-Footprint Keyword Spotting by Mishchenko, Yuriy, Goren, Yusuf, Sun, Ming, Beauchene, Chris, Matsoukas, Spyros, Rybakov, Oleg, Vitaladevuni, Shiv Naga Prasad

“…In this paper, we investigate novel quantization approaches to reduce memory and computational footprint of deep neural network (DNN) based keyword spotters…”
Get full text

Towards Data-efficient Modeling for Wake Word Spotting by Gao, Yixin, Mishchenko, Yuriy, Shah, Anish, Matsoukas, Spyros, Vitaladevuni, Shiv

“…Proc. ICASSP 2020 Wake word (WW) spotting is challenging in far-field not only because of the interference in signal transmission but also the complexity in…”
Get full text