← Authors

Sanath Narayan

16 papers · 2014–2025 · 4 conferences · across top CS/AI conferences

Achievements

πŸ—ΊοΈ Taxonomy Completionist (35) 🧭 Keyword Pioneer 🌍 Conference Polyglot (4) 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (15) 🌈 Renaissance Researcher (7) πŸŒ‰ Interdisciplinary Bridge πŸƒ Academic Marathon (11) 🧬 Topic Evolution πŸ“ˆ Trend Setter πŸ’Ž Century Club (16) πŸ”₯ Unstoppable (7) ❓ The Questioner (2) πŸ—ƒοΈ Keyword Collector (75)

Conferences

CVPR (6) ICCV (6) ECCV (3) WACV (1)

Top co-authors

Fahad Shahbaz Khan (9) Salman Khan (6) Hisham Cholakkal (5) Ling Shao (5) Rao Muhammad Anwer (4) Yasser Abdelaziz Dahou Djilali (4) Akshita Gupta (3) Mayug Maniparambil (2) Merouane Debbah (2) Ankit Singh (2)

Research topics

Representation (1)

Keywords

attention mechanism (3) action recognition (3) zero-shot learning (2) action localization (2) representation learning (2) multimodal learning (2) domain shift (2) visual speech recognition (2) temporal localization (2) vision language model (2) lip reading (2) weakly-supervised learning (2) video classification (1) embedding learning (1) few-shot learning (1) graph matching (1) incremental learning (1) visual saliency (1) metric learning (1) 3d vision (1)

Papers

Harnessing Frozen Unimodal Encoders for Flexible Multimodal Alignment CVPR 2025
Vision-Language Models Can't See the Obvious ICCV 2025
Do VSR Models Generalize Beyond LRS3? WACV 2024
Do Vision and Language Encoders Represent the World Similarly? CVPR 2024
Efficient 3D-Aware Facial Image Editing via Attribute-Specific Prompt Learning ECCV 2024
Lip2Vec: Efficient and Robust Visual Speech Recognition via Latent-to-Latent Visual to Audio Representation Mapping ICCV 2023
Generative Multiplane Neural Radiance for 3D-Aware Image Generation ICCV 2023
OW-DETR: Open-World Detection Transformer CVPR 2022
Spatio-Temporal Relation Modeling for Few-Shot Action Recognition CVPR 2022
Video Instance Segmentation via Multi-Scale Spatio-Temporal Split Attention Transformer ECCV 2022
Discriminative Region-Based Multi-Label Zero-Shot Learning ICCV 2021
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations ICCV 2021
Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification ECCV 2020
3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization ICCV 2019
Out-Of-Distribution Detection for Generalized Zero-Shot Action Recognition CVPR 2019
A Cause and Effect Analysis of Motion Trajectories for Modeling Actions CVPR 2014