22 citations · 40 across the 16 of their papers we have counts for
7 papers · 1 filter
iKUN: Speak to Trackers without Retraining
Yunhao Du, Cheng Lei, Zhicheng Zhao +1
Referring multi-object tracking (RMOT) aims to track multiple objects based on input textual descriptions. Previous works realize it by simply integrating an extra textual module i…
Video-based Visible-Infrared Person Re-Identification with Auxiliary Samples
Yunhao Du, Cheng Lei, Zhicheng Zhao +2
Visible-infrared person re-identification (VI-ReID) aims to match persons captured by visible and infrared cameras, allowing person retrieval and tracking in 24-hour surveillance s…
Automatic Synthetic Data and Fine-grained Adaptive Feature Alignment for Composed Person Retrieval
Delong Liu, Haiwen Li, Zhaohui Hou +3
Person retrieval has attracted rising attention. Existing methods are mainly divided into two retrieval modes, namely image-only and text-only. However, they are unable to make ful…
Now and Future of Artificial Intelligence-based Signet Ring Cell Diagnosis: A Survey
Zhu Meng, Junhao Dong, Limei Guo +4
Signet ring cells (SRCs), associated with a high propensity for peripheral metastasis and poor prognosis, critically influence surgical decision-making and outcome prediction. Howe…
Boundary-Refined Prototype Generation: A General End-to-End Paradigm for Semi-Supervised Semantic Segmentation
Junhao Dong, Zhu Meng, Delong Liu +3
Semi-supervised semantic segmentation has attracted increasing attention in computer vision, aiming to leverage unlabeled data through latent supervision. To achieve this goal, pro…
Text-guided Image Restoration and Semantic Enhancement for Text-to-Image Person Retrieval
Delong Liu, Haiwen Li, Zhicheng Zhao +1
The goal of Text-to-Image Person Retrieval (TIPR) is to retrieve specific person images according to the given textual descriptions. A primary challenge in this task is bridging th…
Dynamic Clustering and Cluster Contrastive Learning for Unsupervised Person Re-identification
Ziqi He, Mengjia Xue, Yunhao Du +2
Unsupervised Re-ID methods aim at learning robust and discriminative features from unlabeled data. However, existing methods often ignore the relationship between module parameters…