3 papers
cs.CV2025
MS-DETR: Towards Effective Video Moment Retrieval and Highlight Detection by Joint Motion-Semantic Learning
Hongxu Ma, Guanshuo Wang, Fufu Yu +2
Video Moment Retrieval (MR) and Highlight Detection (HD) aim to pinpoint specific moments and assess clip-wise relevance based on the text query. While DETR-based joint frameworks…
cs.CV2025
Fine-Grained Zero-Shot Object Detection
Hongxu Ma, Chenbo Zhang, Lu Zhang +3
Zero-shot object detection (ZSD) aims to leverage semantic descriptions to localize and recognize objects of both seen and unseen classes. Existing ZSD works are mainly coarse-grai…
cs.LG2024
Generative Regression Based Watch Time Prediction for Short-Video Recommendation
Hongxu Ma, Kai Tian, Tao Zhang +6
Watch time prediction (WTP) has emerged as a pivotal task in short video recommendation systems, designed to quantify user engagement through continuous interaction modeling. Predi…