Junyu Xie

5 papers · 2022–2026 · 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 ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (16)

Venues

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

Top co-authors

Andrew Zisserman (4) Weidi Xie (3) Raia Hadsell (1) Rahul Sukthankar (1) Guillaume Le Moing (1) Tengda Han (1) Mehdi S. M. Sajjadi (1) Iro Laina (1) Shuyang Sun (1) Liliane Momeni (1)

Research topics

Computer Vision (4) Deep Learning (3) Processing (3) Analysis (2) Architectures (2) Generation · Computer Vision (2) Artificial Intelligence (1) Natural Language Processing (1) Core AI (1) Generation · Natural Language Processing (1) Learning Types (1) Models (1) Techniques (1)

Keywords

feed-forward network (2) depth estimation (2) video segmentation (1) knowledge distillation (1) video understanding (1) image editing (1) object tracking (1) neural network optimization (1) object segmentation (1) optical flow (1) latent space (1) neural radiance field (1) 3d representation (1) dynamic scene reconstruction (1) visual language model (1) temporal context (1) 4d reconstruction (1) moving object segmentation (1) layer representation (1) audio description (1)

Papers

Efficiently Reconstructing Dynamic Scenes One D4RT at a Time CVPR 2026 Shot-by-Shot: Film-Grammar-Aware Training-Free Audio Description Generation ICCV 2025 Appearance-based Refinement for Object-Centric Motion Segmentation ECCV 2024 SHAP-EDITOR: Instruction-Guided Latent 3D Editing in Seconds CVPR 2024 Segmenting Moving Objects via an Object-Centric Layered Representation NeurIPS 2022