Skip to content
conftrace_

Erika Lu

9 papers · 2017–2025 · 4 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 ↓
+3 more ↓ 🌍 Conference Polyglot Β· Bronze πŸƒ Academic Marathon Β· Sprint πŸŒ‰ Interdisciplinary Bridge Β· Bronze πŸ—ΊοΈ Taxonomy Completionist (22) 🐣 Hot Topic Early Bird
πŸ”₯ Unstoppable Β· Bronze πŸ—ƒοΈ Keyword Collector (51) πŸ“ˆ Trend Setter

Venues

CVPR (5) NeurIPS (2) ECCV (1) ICCV (1)

Top co-authors

Forrester Cole (5) Tali Dekel (3) Weidi Xie (3) Andrew Zisserman (3) Michael Rubinstein (2) Bill Freeman (2) Viraj Shah (1) Jia-Bin Huang (1) Yao-Chih Lee (1) Svetlana Lazebnik (1)

Research topics

Computer Vision (8) Processing (6) Machine Learning (5) Deep Learning (4) Analysis (4) Learning Types Β· Machine Learning (4) Artificial Intelligence (2) Core AI (2) Generation (2) Learning Types Β· Deep Learning (2) Models (2) Core Methods (1) Domain-Specific (1) Learning Paradigms (1)

Keywords

self-supervised learning (5) layer decomposition (2) alpha matte (2) video object segmentation (2) optical flow (2) video decomposition (2) object tracking (1) video understanding (1) motion estimation (1) motion segmentation (1) visual tracking (1) generative model (1) convolutional network (1) monocular video (1) depth estimation (1) camera pose (1) video diffusion (1) state estimation (1) video processing (1) pseudo label (1)

Papers

Generative Omnimatte: Learning to Decompose Video into Layers CVPR 2025 ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs ECCV 2024 Omnimatte3D: Associating Objects and Their Effects in Unconstrained Monocular Video CVPR 2023 Self-Supervised AutoFlow CVPR 2023 Associating Objects and Their Effects in Video through Coordination Games NeurIPS 2022 Omnimatte: Associating Objects and Their Effects in Video CVPR 2021 Self-Supervised Video Object Segmentation by Motion Grouping ICCV 2021 MAST: A Memory-Augmented Self-Supervised Tracker CVPR 2020 Learning to See Physics via Visual De-animation NeurIPS 2017