AI seems like the perfect response to the growing challenges of content moderation on social media platforms: the immense scale of the data, the relentlessness of the violations, and the need for ...

Accurate segmentation is crucial for clinical applications, but existing models often assume fixed, high-resolution inputs and degrade significantly when faced with lower-resolution data in real-world ...

Abstract: In pedestrian detection, small-scale pedestrians often face challenges such as limited pixel values and insufficient features, often leading to wrong or missed detection. Therefore, this ...

This project introduces a novel Query-aware Multi-scale Proposal Network, designed for weakly supervised temporal sentence grounding in videos. The model effectively leverages query-aware multi-scale ...

Abstract: Existing projection-related point cloud quality assessment (PCQA) methods commonly adopt a straightforward but content-independent projection strategy, which selects a certain number of ...