GTC ON-DEMAND

 
SEARCH SESSIONS
SEARCH SESSIONS

Search All
 
Refine Results:
 
Year(s)

SOCIAL MEDIA

EMAIL SUBSCRIPTION

 
 

GTC ON-DEMAND

Presentation
Media
Abstract:
We'll discuss problems in face recognition such as face identification, verification, and attribute detection, and review the field's key technical components. This session will cover neural network design options, training strategies, and the physical meanings of the variant cost functions, as well as advanced issues involved in deploying face-recognition technologies, including scalability, lighting, training data, cross-domain learning and data augmentation strategies. In addiition, we'll discuss challenges involved in adapting face recognition from 2D to 3D signals and deploying face recognition in tangible products.
We'll discuss problems in face recognition such as face identification, verification, and attribute detection, and review the field's key technical components. This session will cover neural network design options, training strategies, and the physical meanings of the variant cost functions, as well as advanced issues involved in deploying face-recognition technologies, including scalability, lighting, training data, cross-domain learning and data augmentation strategies. In addiition, we'll discuss challenges involved in adapting face recognition from 2D to 3D signals and deploying face recognition in tangible products.  Back
 
Topics:
Computer Vision, AI & Deep Learning Research, AI Application, Deployment & Inference
Type:
Talk
Event:
GTC Silicon Valley
Year:
2019
Session ID:
S9566
Streaming:
Share:
 
Abstract:
We saw the huge success of the deep learning paradigm and the superhuman capability in numerous benchmarks in image, video, audio, or text. However, it poses huge challenges as adopting the methods in industrial applications (mainly due to the lack of quality tracking data) as the neural networks consume enormous parameters and require relatively huge quality training data. We'll aim for investigating the "data augmentation" strategies increasing quality training data for robust inference across different learning problems mainly in image, video, 3D, and IoT data streams. We'll first quantify the importance of training data for deep neural networks then review numerous strategies, such as crawling from the web, utilizing generative models, 3D computer graphics, augmented reality, engagement in social media, gaming, etc. We'll compare the effectiveness among the diverse strategies. As generally taking the data from other domains, we also need to deal with the cross-domain learning problem. We'll provide detailed insights from our recent work published in top conferences (e.g., CVPR, ICCV, AAAI, etc.) and those cases in industrial applications.
We saw the huge success of the deep learning paradigm and the superhuman capability in numerous benchmarks in image, video, audio, or text. However, it poses huge challenges as adopting the methods in industrial applications (mainly due to the lack of quality tracking data) as the neural networks consume enormous parameters and require relatively huge quality training data. We'll aim for investigating the "data augmentation" strategies increasing quality training data for robust inference across different learning problems mainly in image, video, 3D, and IoT data streams. We'll first quantify the importance of training data for deep neural networks then review numerous strategies, such as crawling from the web, utilizing generative models, 3D computer graphics, augmented reality, engagement in social media, gaming, etc. We'll compare the effectiveness among the diverse strategies. As generally taking the data from other domains, we also need to deal with the cross-domain learning problem. We'll provide detailed insights from our recent work published in top conferences (e.g., CVPR, ICCV, AAAI, etc.) and those cases in industrial applications.  Back
 
Topics:
AI & Deep Learning Research, Advanced AI Learning Techniques
Type:
Talk
Event:
GTC Silicon Valley
Year:
2018
Session ID:
S8391
Streaming:
Download:
Share:
 
Abstract:
We'll demonstrate how to design the end-to-end neural networks for leveraging large-scale multimodal data streams for ranking (recommendation), mining human behaviors/interests, and machine comprehension jointly from different modalities such as images, videos, audios, and 3D models. We'll present effective neural networks for considering both sequential (temporal) and spatial (convolutional) variations and numerous strategies for cross-modal learning. We'll show how to tackle the cross-domain problems (for example, images vs. 3D models, audio vs. text), how to leverage freely available web data for training in a semi-supervised or unsupervised manner. We'll describe breakthroughs in 3D model retrieval, human activities understanding from social media, listening comprehension test, and more.
We'll demonstrate how to design the end-to-end neural networks for leveraging large-scale multimodal data streams for ranking (recommendation), mining human behaviors/interests, and machine comprehension jointly from different modalities such as images, videos, audios, and 3D models. We'll present effective neural networks for considering both sequential (temporal) and spatial (convolutional) variations and numerous strategies for cross-modal learning. We'll show how to tackle the cross-domain problems (for example, images vs. 3D models, audio vs. text), how to leverage freely available web data for training in a semi-supervised or unsupervised manner. We'll describe breakthroughs in 3D model retrieval, human activities understanding from social media, listening comprehension test, and more.  Back
 
Topics:
Artificial Intelligence and Deep Learning, Signal and Audio Processing
Type:
Talk
Event:
GTC Silicon Valley
Year:
2017
Session ID:
S7355
Download:
Share:
 
 
Previous
  • Amazon Web Services
  • IBM
  • Cisco
  • Dell EMC
  • Hewlett Packard Enterprise
  • Inspur
  • Lenovo
  • SenseTime
  • Supermicro Computers
  • Synnex
  • Autodesk
  • HP
  • Linear Technology
  • MSI Computer Corp.
  • OPTIS
  • PNY
  • SK Hynix
  • vmware
  • Abaco Systems
  • Acceleware Ltd.
  • ASUSTeK COMPUTER INC
  • Cray Inc.
  • Exxact Corporation
  • Flanders - Belgium
  • Google Cloud
  • HTC VIVE
  • Liqid
  • MapD
  • Penguin Computing
  • SAP
  • Sugon
  • Twitter
Next