5 citations · 6 across the 6 of their papers we have counts for
6 papers
CAMs as Shapley Value-based Explainers
Huaiguang Cai
Class Activation Mapping (CAM) methods are widely used to visualize neural network decisions, yet their underlying mechanisms remain incompletely understood. To enhance the underst…
LoRAP: Transformer Sub-Layers Deserve Differentiated Structured Compression for Large Language Models
Guangyan Li, Yongqiang Tang, Wensheng Zhang
Large language models (LLMs) show excellent performance in difficult tasks, but they often require massive memories and computational resources. How to reduce the parameter scale o…
Cross-Domain Label Propagation for Domain Adaptation with Discriminative Graph Self-Learning
Lei Tian, Yongqiang Tang, Liangchen Hu +1
Domain adaptation manages to transfer the knowledge of well-labeled source data to unlabeled target data. Many recent efforts focus on improving the prediction accuracy of target p…
Leveraging Summary Guidance on Medical Report Summarization
Yunqi Zhu, Xuebing Yang, Yuanyuan Wu +1
This study presents three deidentified large medical text datasets, named DISCHARGE, ECHO and RADIOLOGY, which contain 50K, 16K and 378K pairs of report and summary that are derive…
Attentive pooling for Group Activity Recognition
Ding Li, Yuan Xie, Wensheng Zhang +2
In group activity recognition, hierarchical framework is widely adopted to represent the relationships between individuals and their corresponding group, and has achieved promising…
Active Learning with Effective Scoring Functions for Semi-Supervised Temporal Action Localization
Ding Li, Xuebing Yang, Yongqiang Tang +2
Temporal Action Localization (TAL) aims to predict both action category and temporal boundary of action instances in untrimmed videos, i.e., start and end time. Fully-supervised so…