Lele Xue
Papers
1
Total Citations
11
H-Index
1
About
Lele Xue is a researcher whose work focuses on the intersection of computer vision and natural language processing, particularly in the domain of video understanding. Her key contributions center on temporal language grounding—the task of localizing specific moments in videos based on natural language queries. In her notable paper "STCM-Net: A Symmetrical One-Stage Network for Temporal Language Localization in Videos" (2021), which has garnered 11 citations, Xue introduced a novel symmetrical architecture that streamlines the process of aligning linguistic descriptions with video segments. This one-stage approach eliminates the need for complex, multi-step pipelines, offering a more efficient and accurate solution for video retrieval and event detection. Her work addresses critical challenges in cross-modal learning, demonstrating how symmetrical network designs can enhance the synergy between visual and textual data. While still early in her career, Xue's research has practical implications for applications like video search, surveillance analysis, and assistive technologies, marking her as a promising contributor to the growing field of multimodal AI.
Research Focus
Key Achievements
Top Papers
- 1