Sanath Narayan

papers

810

total citations

papers (11)

Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification

ECCV 2020arXiv

257

citations

OW-DETR: Open-World Detection Transformer

CVPR 2022arXiv

241

citations

Spatio-Temporal Relation Modeling for Few-Shot Action Recognition

CVPR 2022arXiv

112

citations

D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations

ICCV 2021arXiv

citations

Discriminative Region-Based Multi-Label Zero-Shot Learning

ICCV 2021arXiv

citations

Do Vision and Language Encoders Represent the World Similarly?

CVPR 2024arXiv

citations

Video Instance Segmentation via Multi-Scale Spatio-Temporal Split Attention Transformer

ECCV 2022arXiv

citations

Lip2Vec: Efficient and Robust Visual Speech Recognition via Latent-to-Latent Visual to Audio Representation Mapping

ICCV 2023arXiv

citations

Sanath Narayan

papers (11)

Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification

OW-DETR: Open-World Detection Transformer

Spatio-Temporal Relation Modeling for Few-Shot Action Recognition

D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations

Discriminative Region-Based Multi-Label Zero-Shot Learning

Do Vision and Language Encoders Represent the World Similarly?

Video Instance Segmentation via Multi-Scale Spatio-Temporal Split Attention Transformer

Lip2Vec: Efficient and Robust Visual Speech Recognition via Latent-to-Latent Visual to Audio Representation Mapping

Vision-Language Models Can't See the Obvious

Generative Multiplane Neural Radiance for 3D-Aware Image Generation

Harnessing Frozen Unimodal Encoders for Flexible Multimodal Alignment

papers (11)

Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification

OW-DETR: Open-World Detection Transformer

Spatio-Temporal Relation Modeling for Few-Shot Action Recognition

D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations

Discriminative Region-Based Multi-Label Zero-Shot Learning

Do Vision and Language Encoders Represent the World Similarly?

Video Instance Segmentation via Multi-Scale Spatio-Temporal Split Attention Transformer

Lip2Vec: Efficient and Robust Visual Speech Recognition via Latent-to-Latent Visual to Audio Representation Mapping

Vision-Language Models Can't See the Obvious

Generative Multiplane Neural Radiance for 3D-Aware Image Generation

Harnessing Frozen Unimodal Encoders for Flexible Multimodal Alignment