Srikrishna Karanam

papers

684

total citations

papers (12)

Towards Visually Explaining Variational Autoencoders

CVPR 2020arXiv

255

citations

Hierarchical Kinematic Human Mesh Recovery

ECCV 2020arXiv

115

citations

Spatio-Temporal Representation Factorization for Video-Based Person Re-Identification

ICCV 2021arXiv

citations

A-STAR: Test-time Attention Segregation and Retention for Text-to-image Synthesis

ICCV 2023arXiv

citations

PseudoClick: Interactive Image Segmentation with Click Imitation

ECCV 2022arXiv

citations

A Peek Into the Reasoning of Neural Networks: Interpreting With Structural Visual Concepts

CVPR 2021arXiv

citations

TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction

CVPR 2025arXiv

citations

SMPL-A: Modeling Person-Specific Deformable Anatomy

CVPR 2022

citations

Ensemble Attention Distillation for Privacy-Preserving Federated Learning

ICCV 2021

citations

Srikrishna Karanam

papers (12)

Towards Visually Explaining Variational Autoencoders

Hierarchical Kinematic Human Mesh Recovery

Spatio-Temporal Representation Factorization for Video-Based Person Re-Identification

A-STAR: Test-time Attention Segregation and Retention for Text-to-image Synthesis

PseudoClick: Interactive Image Segmentation with Click Imitation

A Peek Into the Reasoning of Neural Networks: Interpreting With Structural Visual Concepts

CoPL: Contextual Prompt Learning for Vision-Language Understanding

Self-supervised Human Mesh Recovery with Cross-Representation Alignment

Composing Parts for Expressive Object Generation

TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction

SMPL-A: Modeling Person-Specific Deformable Anatomy

Ensemble Attention Distillation for Privacy-Preserving Federated Learning

papers (12)

Towards Visually Explaining Variational Autoencoders

Hierarchical Kinematic Human Mesh Recovery

Spatio-Temporal Representation Factorization for Video-Based Person Re-Identification

A-STAR: Test-time Attention Segregation and Retention for Text-to-image Synthesis

PseudoClick: Interactive Image Segmentation with Click Imitation

A Peek Into the Reasoning of Neural Networks: Interpreting With Structural Visual Concepts

CoPL: Contextual Prompt Learning for Vision-Language Understanding

Self-supervised Human Mesh Recovery with Cross-Representation Alignment

Composing Parts for Expressive Object Generation

TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction

SMPL-A: Modeling Person-Specific Deformable Anatomy

Ensemble Attention Distillation for Privacy-Preserving Federated Learning