Awesome Multimodal
📄
Papers
🧭
Topics
🔥
Trending
🗺️
Map
🏆
Leaderboards
🎓
Learn
🤖
Ask AI
⋯
More
👥
Authors
📚
Reading Packs
📊
Datasets
🛠️
Tools
📰
News
📝
Blogs
✉️
Newsletter
🎯
Research Radar
🔖
Saved
+ Add Paper
☾
☀
← authors
·
overview
Loading author…
🤖
Ask AI
Lixin Duan — most-cited papers & profile · Multimodal
← authors
·
overview
Lixin Duan
17
papers ·
42
citations ·
37
h-index
University of Electronic Science and Technology of China · Institute for Advanced Study
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
Learning Transferable Self-attentive Representations for Action Recognition in Untrimmed Videos with Weak Supervision
2019 · 5 citations
Domain Adversarial Reinforcement Learning for Partial Domain Adaptation
2019 · 4 citations
Deeply Aligned Adaptation for Cross-domain Object Detection
2020 · 4 citations
SSR: SAM is a Strong Regularizer for domain adaptive semantic segmentation
2024 · 2 citations
Powerful and Flexible: Personalized Text-to-Image Generation via Reinforcement Learning
2024 · 1 citations
MixRea: Benchmarking Explicit-Implicit Reasoning in Large Language Models
2026
FedCoE: Bridging Generalization and Personalization via Federated Coordinated Dual-level MoEs
2026
Semantic segmentation with reward
2025
Adversarial Multimodal Network for Movie Question Answering
2019
Open-Ended Visual Question Answering by Multi-Modal Domain Adaptation
2019
Topics
Segmentation
Video Understanding
Visual Language
Evaluation
Prompting
Safety & Alignment
cs.LG
Value-Based
Model-Based RL
Object Detection