Alert button
Picture for Ganesh Venkatesh

Ganesh Venkatesh

Alert button

Temporally Consistent Online Depth Estimation in Dynamic Scenes

Add code
Bookmark button
Alert button
Nov 17, 2021
Zhaoshuo Li, Wei Ye, Dilin Wang, Francis X. Creighton, Russell H. Taylor, Ganesh Venkatesh, Mathias Unberath

Figure 1 for Temporally Consistent Online Depth Estimation in Dynamic Scenes
Figure 2 for Temporally Consistent Online Depth Estimation in Dynamic Scenes
Figure 3 for Temporally Consistent Online Depth Estimation in Dynamic Scenes
Figure 4 for Temporally Consistent Online Depth Estimation in Dynamic Scenes
Viaarxiv icon

Omni-sparsity DNN: Fast Sparsity Optimization for On-Device Streaming E2E ASR via Supernet

Add code
Bookmark button
Alert button
Oct 15, 2021
Haichuan Yang, Yuan Shangguan, Dilin Wang, Meng Li, Pierce Chuang, Xiaohui Zhang, Ganesh Venkatesh, Ozlem Kalinli, Vikas Chandra

Figure 1 for Omni-sparsity DNN: Fast Sparsity Optimization for On-Device Streaming E2E ASR via Supernet
Figure 2 for Omni-sparsity DNN: Fast Sparsity Optimization for On-Device Streaming E2E ASR via Supernet
Figure 3 for Omni-sparsity DNN: Fast Sparsity Optimization for On-Device Streaming E2E ASR via Supernet
Figure 4 for Omni-sparsity DNN: Fast Sparsity Optimization for On-Device Streaming E2E ASR via Supernet
Viaarxiv icon

Collaborative Training of Acoustic Encoders for Speech Recognition

Add code
Bookmark button
Alert button
Jul 13, 2021
Varun Nagaraja, Yangyang Shi, Ganesh Venkatesh, Ozlem Kalinli, Michael L. Seltzer, Vikas Chandra

Figure 1 for Collaborative Training of Acoustic Encoders for Speech Recognition
Figure 2 for Collaborative Training of Acoustic Encoders for Speech Recognition
Figure 3 for Collaborative Training of Acoustic Encoders for Speech Recognition
Viaarxiv icon

Noisy Training Improves E2E ASR for the Edge

Add code
Bookmark button
Alert button
Jul 09, 2021
Dilin Wang, Yuan Shangguan, Haichuan Yang, Pierce Chuang, Jiatong Zhou, Meng Li, Ganesh Venkatesh, Ozlem Kalinli, Vikas Chandra

Figure 1 for Noisy Training Improves E2E ASR for the Edge
Figure 2 for Noisy Training Improves E2E ASR for the Edge
Figure 3 for Noisy Training Improves E2E ASR for the Edge
Figure 4 for Noisy Training Improves E2E ASR for the Edge
Viaarxiv icon

Latency-Aware Neural Architecture Search with Multi-Objective Bayesian Optimization

Add code
Bookmark button
Alert button
Jun 25, 2021
David Eriksson, Pierce I-Jen Chuang, Samuel Daulton, Peng Xia, Akshat Shrivastava, Arun Babu, Shicong Zhao, Ahmed Aly, Ganesh Venkatesh, Maximilian Balandat

Figure 1 for Latency-Aware Neural Architecture Search with Multi-Objective Bayesian Optimization
Figure 2 for Latency-Aware Neural Architecture Search with Multi-Objective Bayesian Optimization
Figure 3 for Latency-Aware Neural Architecture Search with Multi-Objective Bayesian Optimization
Figure 4 for Latency-Aware Neural Architecture Search with Multi-Objective Bayesian Optimization
Viaarxiv icon

Accelerating Sparse Deep Neural Networks

Add code
Bookmark button
Alert button
Apr 16, 2021
Asit Mishra, Jorge Albericio Latorre, Jeff Pool, Darko Stosic, Dusan Stosic, Ganesh Venkatesh, Chong Yu, Paulius Micikevicius

Figure 1 for Accelerating Sparse Deep Neural Networks
Figure 2 for Accelerating Sparse Deep Neural Networks
Figure 3 for Accelerating Sparse Deep Neural Networks
Figure 4 for Accelerating Sparse Deep Neural Networks
Viaarxiv icon

Memory-efficient Speech Recognition on Smart Devices

Add code
Bookmark button
Alert button
Feb 23, 2021
Ganesh Venkatesh, Alagappan Valliappan, Jay Mahadeokar, Yuan Shangguan, Christian Fuegen, Michael L. Seltzer, Vikas Chandra

Figure 1 for Memory-efficient Speech Recognition on Smart Devices
Figure 2 for Memory-efficient Speech Recognition on Smart Devices
Figure 3 for Memory-efficient Speech Recognition on Smart Devices
Figure 4 for Memory-efficient Speech Recognition on Smart Devices
Viaarxiv icon

Learning Dynamic Network Using a Reuse Gate Function in Semi-supervised Video Object Segmentation

Add code
Bookmark button
Alert button
Dec 21, 2020
Hyojin Park, Jayeon Yoo, Seohyeong Jeong, Ganesh Venkatesh, Nojun Kwak

Figure 1 for Learning Dynamic Network Using a Reuse Gate Function in Semi-supervised Video Object Segmentation
Figure 2 for Learning Dynamic Network Using a Reuse Gate Function in Semi-supervised Video Object Segmentation
Figure 3 for Learning Dynamic Network Using a Reuse Gate Function in Semi-supervised Video Object Segmentation
Figure 4 for Learning Dynamic Network Using a Reuse Gate Function in Semi-supervised Video Object Segmentation
Viaarxiv icon

Can Temporal Information Help with Contrastive Self-Supervised Learning?

Add code
Bookmark button
Alert button
Nov 25, 2020
Yutong Bai, Haoqi Fan, Ishan Misra, Ganesh Venkatesh, Yongyi Lu, Yuyin Zhou, Qihang Yu, Vikas Chandra, Alan Yuille

Figure 1 for Can Temporal Information Help with Contrastive Self-Supervised Learning?
Figure 2 for Can Temporal Information Help with Contrastive Self-Supervised Learning?
Figure 3 for Can Temporal Information Help with Contrastive Self-Supervised Learning?
Figure 4 for Can Temporal Information Help with Contrastive Self-Supervised Learning?
Viaarxiv icon

TTVOS: Lightweight Video Object Segmentation with Adaptive Template Attention Module and Temporal Consistency Loss

Add code
Bookmark button
Alert button
Nov 09, 2020
Hyojin Park, Ganesh Venkatesh, Nojun Kwak

Figure 1 for TTVOS: Lightweight Video Object Segmentation with Adaptive Template Attention Module and Temporal Consistency Loss
Figure 2 for TTVOS: Lightweight Video Object Segmentation with Adaptive Template Attention Module and Temporal Consistency Loss
Figure 3 for TTVOS: Lightweight Video Object Segmentation with Adaptive Template Attention Module and Temporal Consistency Loss
Figure 4 for TTVOS: Lightweight Video Object Segmentation with Adaptive Template Attention Module and Temporal Consistency Loss
Viaarxiv icon