3 citations · 3 across the 5 of their papers we have counts for
5 papers
Multi-Stage Coarse-to-Fine Contrastive Learning for Conversation Intent Induction
Caiyuan Chu, Ya Li, Yifan Liu +4
Intent recognition is critical for task-oriented dialogue systems. However, for emerging domains and new services, it is difficult to accurately identify the key intent of a conver…
Forcing the Whole Video as Background: An Adversarial Learning Strategy for Weakly Temporal Action Localization
Ziqiang Li, Yongxin Ge, Jiaruo Yu +1
With video-level labels, weakly supervised temporal action localization (WTAL) applies a localization-by-classification paradigm to detect and classify the action in untrimmed vide…
Deep Domain Adaptation for Pavement Crack Detection
Huijun Liu, Chunhua Yang, Ao Li +4
Deep learning-based pavement cracks detection methods often require large-scale labels with detailed crack location information to learn accurate predictions. In practice, however,…
Local Contrast Learning
Chuanyun Xu, Yang Zhang, Xin Feng +3
Learning a deep model from small data is yet an opening and challenging problem. We focus on one-shot classification by deep learning approach based on a small quantity of training…
Face Recognition via Globality-Locality Preserving Projections
Sheng Huang, Dan Yang, Fei Yang +3
We present an improved Locality Preserving Projections (LPP) method, named Gloablity-Locality Preserving Projections (GLPP), to preserve both the global and local geometric structu…