Brendan Duke

4 papers · 2021–2023 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (13) 🐣 Hot Topic Early Bird

Venues

CVPR (3) ECCV (1)

Top co-authors

Parham Aarabi (4) Graham W. Taylor (3) Florian Shkurti (2) Ruowei Jiang (2) Christian Wolf (1) Rohit Saha (1) Zikun Chen (1) Abdalla Ahmed (1) Han Zhao (1) Cong Wei (1)

Research topics

Computer Vision (3) Deep Learning (3) Machine Learning (2) Architectures (2) Processing (2) Analysis (1) Application Areas (1) Core AI (1) Generation (1) Learning Types (1) Models (1) Optimization & Theory · Deep Learning (1) Optimization & Theory · Machine Learning (1) Techniques (1)

Keywords

sparse attention (2) vision transformer (1) image generation (1) attention mechanism (1) visual object tracking (1) image synthesis (1) feature disentanglement (1) efficient computing (1) disentangled representation (1) latent optimization (1) latent space optimization (1) model efficiency (1) gan inversion (1) video object segmentation (1) token sparsity (1) spatio-temporal transformer (1) hairstyle transfer (1) correspondence computation (1) model compression (1) gradient orthogonalization (1)

Papers

Sparsifiner: Learning Sparse Instance-Dependent Attention for Efficient Vision Transformers CVPR 2023 Exploring Gradient-Based Multi-directional Controls in GANs ECCV 2022 LOHO: Latent Optimization of Hairstyles via Orthogonalization CVPR 2021 SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation CVPR 2021