Luchuan Song

10 papers · 2021–2026 · 5 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (15) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (4) 🏃 Academic Marathon (5) 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (15) 🧭 Keyword Pioneer 🔥 Unstoppable (5) 💎 Century Club (10)

Conferences

ECCV (4) CVPR (2) ICCV (2) AAAI (1) NIPS (1)

Top co-authors

Chenliang Xu (4) Zhenchao Jin (4) Guojun Yin (3) Pinxin Liu (3) Haiyang Liu (2) Lequan Yu (2) Xiaoyi Dong (2) Siyu Chen (1) Jingqun Tang (1) Jiebo Luo (1)

Keywords

pose estimation (1) video captioning (1) video classification (1) multimodal learning (1) object tracking (1) flow matching (1) context modeling (1) spatial localization (1) diffusion model (1) benchmark dataset (1) vision language model (1) controllable generation (1) face forgery detection (1) temporal coherence (1) spatial-temporal modeling (1) attention map (1) feature enhancement (1) image manipulation (1) gesture generation (1) semantic segmentation (1)

Papers

Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting AAAI 2026

Free-viewpoint Human Animation with Pose-correlated Reference Selection CVPR 2025

GestureLSM: Latent Shortcut based Co-Speech Gesture Generation with Spatial-Temporal Modeling ICCV 2025

Tri^{2}-plane: Thinking Head Avatar via Feature Pyramid ECCV 2024

IDRNet: Intervention-Driven Relation Network for Semantic Segmentation NIPS 2023

Emotional Listener Portrait: Neural Listener Head Generation with Emotion ICCV 2023

Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learning ECCV 2022

You Should Look at All Objects ECCV 2022

Adaptive Face Forgery Detection in Cross Domain ECCV 2022

ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis CVPR 2021