Yongxin Ge
YOU?
Author Swipe
View article: Artificial Nanofluidic Iontronic Retina
Artificial Nanofluidic Iontronic Retina Open
Biological vision acquires external information through light-induced transmembrane ion transport, generating electrical impulses. While reproducing biological visual function is highly significant, mimicking the retina with dual photorece…
View article: Hierarchical Multi-Graphs Learning for Robust Group Re-Identification
Hierarchical Multi-Graphs Learning for Robust Group Re-Identification Open
Group Re-identification (G-ReID) faces greater complexity than individual Re-identification (ReID) due to challenges like mutual occlusion, dynamic member interactions, and evolving group structures. Prior graph-based approaches have aimed…
View article: Deep Learning-Enabled Integration of Histology and Transcriptomics for Tissue Spatial Profile Analysis
Deep Learning-Enabled Integration of Histology and Transcriptomics for Tissue Spatial Profile Analysis Open
Spatially resolved transcriptomics enable comprehensive measurement of gene expression at subcellular resolution while preserving the spatial context of the tissue microenvironment. While deep learning has shown promise in analyzing SCST d…
View article: Two-stream joint matching method based on contrastive learning for few-shot action recognition
Two-stream joint matching method based on contrastive learning for few-shot action recognition Open
Although few-shot action recognition based on metric learning paradigm has achieved significant success, it fails to address the following issues: (1) inadequate action relation modeling and underutilization of multi-modal information; (2)…
View article: Multi-Stage Coarse-to-Fine Contrastive Learning for Conversation Intent Induction
Multi-Stage Coarse-to-Fine Contrastive Learning for Conversation Intent Induction Open
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 conversation due to time-consuming data annotation and comparativ…
View article: Forcing the Whole Video as Background: An Adversarial Learning Strategy for Weakly Temporal Action Localization
Forcing the Whole Video as Background: An Adversarial Learning Strategy for Weakly Temporal Action Localization Open
With video-level labels, weakly supervised temporal action localization (WTAL) applies a localization-by-classification paradigm to detect and classify the action in untrimmed videos. Due to the characteristic of classification, class-spec…
View article: Deep Domain Adaptation for Pavement Crack Detection
Deep Domain Adaptation for Pavement Crack Detection Open
Deep learning-based pavement cracks detection methods often require large-scale labels with detailed crack location information to learn accurate predictions. In practice, however, crack locations are very difficult to be manually annotate…
View article: Fractional Distance Regularized Level Set Evolution With Its Application to Image Segmentation
Fractional Distance Regularized Level Set Evolution With Its Application to Image Segmentation Open
To avoid the irregularities during the level set evolution, a fractional distance regularized variational model is proposed for image segmentation. We first define a fractional distance regularization term which punishes the deviation of t…
View article: Clustering With Orthogonal AutoEncoder
Clustering With Orthogonal AutoEncoder Open
Recently, clustering algorithms based on deep AutoEncoder attract lots of attention due to their excellent clustering performance. On the other hand, the success of PCA-Kmeans and spectral clustering corroborates that the orthogonality of …
View article: Person Re-Identification by Pose Invariant Deep Metric Learning With Improved Triplet Loss
Person Re-Identification by Pose Invariant Deep Metric Learning With Improved Triplet Loss Open
Person re-identification (re-ID) is a challenging problem in the community which aims at identifying person in a surveillance video. Despite recent advance in the field of computer vision, person re-ID still presents great challenge since …