Teng Wang

机构：University of Chinese Academy of Sciences · ORCID：0000-0002-5799-7361

发表论文 61 篇 · 总被引 480 次 · h-index 11

代表论文

• Caption Anything: Interactive Image Description with Diverse Multimodal Controls (2023 · arXiv (Cornell University) · 被引 19)
• SeqInfo-SAWGAN-GP: Adaptive feature extraction from vibration time data under variable operating conditions for imbalanced bearing fault diagnosis (2024 · Measurement · 被引 17)
• LANDMARK: language-guided representation enhancement framework for scene graph generation (2023 · Applied Intelligence · 被引 10)
• Video Understanding with Large Language Models: A Survey (2023 · arXiv (Cornell University) · 被引 8)
• Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos (2023 · arXiv (Cornell University) · 被引 7)
• LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos (2025 · 被引 5)