Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Saksham Suri

Saksham Suri
Alert button

Teaching Matters: Investigating the Role of Supervision in Vision Transformers


Dec 07, 2022
Matthew Walmer, Saksham Suri, Kamal Gupta, Abhinav Shrivastava

Add code
Alert button

Figure 1 for Teaching Matters: Investigating the Role of Supervision in Vision Transformers
Figure 2 for Teaching Matters: Investigating the Role of Supervision in Vision Transformers
Figure 3 for Teaching Matters: Investigating the Role of Supervision in Vision Transformers
Figure 4 for Teaching Matters: Investigating the Role of Supervision in Vision Transformers
* Website: see https://www.cs.umd.edu/~sakshams/vit_analysis, Code: see https://www.github.com/mwalmer-umd/vit_analysis 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Sparsely Annotated Object Detection: A Region-based Semi-supervised Approach


Jan 12, 2022
Sai Saketh Rambhatla, Saksham Suri, Rama Chellappa, Abhinav Shrivastava

Add code
Alert button

Figure 1 for Sparsely Annotated Object Detection: A Region-based Semi-supervised Approach
Figure 2 for Sparsely Annotated Object Detection: A Region-based Semi-supervised Approach
Figure 3 for Sparsely Annotated Object Detection: A Region-based Semi-supervised Approach
Figure 4 for Sparsely Annotated Object Detection: A Region-based Semi-supervised Approach

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Towards Discovery and Attribution of Open-world GAN Generated Images


May 10, 2021
Sharath Girish, Saksham Suri, Saketh Rambhatla, Abhinav Shrivastava

Add code
Alert button

Figure 1 for Towards Discovery and Attribution of Open-world GAN Generated Images
Figure 2 for Towards Discovery and Attribution of Open-world GAN Generated Images
Figure 3 for Towards Discovery and Attribution of Open-world GAN Generated Images
Figure 4 for Towards Discovery and Attribution of Open-world GAN Generated Images

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Learned Spatial Representations for Few-shot Talking-Head Synthesis


Apr 29, 2021
Moustafa Meshry, Saksham Suri, Larry S. Davis, Abhinav Shrivastava

Add code
Alert button

Figure 1 for Learned Spatial Representations for Few-shot Talking-Head Synthesis
Figure 2 for Learned Spatial Representations for Few-shot Talking-Head Synthesis
Figure 3 for Learned Spatial Representations for Few-shot Talking-Head Synthesis
Figure 4 for Learned Spatial Representations for Few-shot Talking-Head Synthesis
* http://www.cs.umd.edu/~mmeshry/projects/lsr/ 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

On Matching Faces with Alterations due to Plastic Surgery and Disguise


Nov 18, 2018
Saksham Suri, Anush Sankaran, Mayank Vatsa, Richa Singh

Add code
Alert button

Figure 1 for On Matching Faces with Alterations due to Plastic Surgery and Disguise
Figure 2 for On Matching Faces with Alterations due to Plastic Surgery and Disguise
Figure 3 for On Matching Faces with Alterations due to Plastic Surgery and Disguise
Figure 4 for On Matching Faces with Alterations due to Plastic Surgery and Disguise
* The 9th IEEE International Conference on Biometrics: Theory, Applications, and Systems (BTAS 2018) 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

An Interpretable Generative Model for Handwritten Digit Image Synthesis


Nov 11, 2018
Yao Zhu, Saksham Suri, Pranav Kulkarni, Yueru Chen, Jiali Duan, C. -C. Jay Kuo

Add code
Alert button

Figure 1 for An Interpretable Generative Model for Handwritten Digit Image Synthesis
Figure 2 for An Interpretable Generative Model for Handwritten Digit Image Synthesis
Figure 3 for An Interpretable Generative Model for Handwritten Digit Image Synthesis
Figure 4 for An Interpretable Generative Model for Handwritten Digit Image Synthesis

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email