Xunzhi Xiang

4 papers · 2024–2026 · 3 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 (11)

Venues

CVPR (2) AAAI (1) AISTATS (1)

Top co-authors

Minglei Li (1) Haiwei Xue (1) Junyuan Ma (1) Weijiang Yu (1) Kun Jing (1) Jungang Xu (1) Qi Fan (1) Heng Chang (1) Yang Gao (1) Yabo Chen (1)

Research topics

Computer Vision (3) Deep Learning (3) Generation (2) Learning Types (2) Artificial Intelligence (1) Machine Learning (1) Analysis (1) Application Areas (1) Architectures (1) Core AI · Artificial Intelligence (1) Core AI · Computer Vision (1) Processing (1)

Keywords

semantic segmentation (1) few-shot learning (1) self-attention mechanism (1) domain adaptation (1) video generation (1) neural architecture search (1) parameter-efficient fine-tuning (1) motion control (1) vision foundation model (1) pose sequence (1) camera trajectory (1) architecture predictor (1) trajectory embedding (1) character animation (1) object dynamics (1) image animation (1) graph neural network (1) pose-controlled human video generation (1) character image animation (1) identity consistency (1)

Papers

Selective, Regularized, and Calibrated: Harnessing Vision Foundation Models for Cross-Domain Few-Shot Semantic Segmentation CVPR 2026 SymphoMotion: Joint Control of Camera Motion and Object Dynamics for Coherent Video Generation CVPR 2026 ReMask-Animate: Refined Character Image Animation Using Mask-Guided Adapters AAAI 2025 A Neural Architecture Predictor based on GNN-Enhanced Transformer AISTATS 2024