2 citations · 3 across the 3 of their papers we have counts for
3 papers
cs.CV2023
Video Timeline Modeling For News Story Understanding
Meng Liu, Mingda Zhang, Jialu Liu +5
In this paper, we present a novel problem, namely video timeline modeling. Our objective is to create a video-associated timeline from a set of videos related to a specific topic,…
eess.IV2022★ 1 cited
Hard Exudate Segmentation Supplemented by Super-Resolution with Multi-scale Attention Fusion Module
Jiayi Zhang, Xiaoshan Chen, Zhongxi Qiu +3
Hard exudates (HE) is the most specific biomarker for retina edema. Precise HE segmentation is vital for disease diagnosis and treatment, but automatic segmentation is challenged b…
cs.CV2020★ 2 cited
Dual-path CNN with Max Gated block for Text-Based Person Re-identification
Tinghuai Ma, Mingming Yang, Huan Rong +3
Text-based person re-identification(Re-id) is an important task in video surveillance, which consists of retrieving the corresponding person's image given a textual description fro…