Changsong Wen
8 papers · 2023–2026 · 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 · Bronze
🗺️
Taxonomy Completionist
(18)
🐣
Hot Topic Early Bird
🗃️
Keyword Collector
(53)
Top co-authors
Research topics
Keywords
clip model
(2)
vision-language model
(2)
multimodal learning
(2)
contrastive learning
(1)
domain generalization
(1)
ordinal regression
(1)
image segmentation
(1)
domain adaptation
(1)
sentiment analysis
(1)
multi-label learning
(1)
knowledge distillation
(1)
hierarchical alignment
(1)
sarcasm detection
(1)
point cloud
(1)
feature embedding
(1)
transfer learning
(1)
affective computing
(1)
cross-modal alignment
(1)
label distribution learning
(1)
semantic segmentation
(1)
Papers
Efficient Segmentation with Multimodal Large Language Model via Token Routing
AAAI 2026
Unlocking 3D Affordance Segmentation with 2D Semantic Knowledge
CVPR 2026
Domain Generalization in CLIP via Learning with Diverse Text Prompts
CVPR 2025
Retaining Knowledge and Enhancing Long-Text Representations in CLIP through Dual-Teacher Distillation
CVPR 2025
Tackling View-Dependent Semantics in 3D Language Gaussian Splatting
ICML 2025
Understanding Fine-tuning CLIP for Open-vocabulary Semantic Segmentation in Hyperbolic Space
CVPR 2025
DIP: Dual Incongruity Perceiving Network for Sarcasm Detection
CVPR 2023
Ordinal Label Distribution Learning
ICCV 2023