default author photo

Kun Ding

affiliation not provided to SSRN

SCHOLARLY PAPERS

2

DOWNLOADS

31

TOTAL CITATIONS

0

Scholarly Papers (2)

1.

Taming Modality Entanglement in Continual Audio-Visual Segmentation

Number of pages: 34 Posted: 12 Jan 2026
affiliation not provided to SSRN, University of Chinese Academy of Sciences, affiliation not provided to SSRN, University of Chinese Academy of Sciences, University of Science and Technology Beijing, affiliation not provided to SSRN, University of Science and Technology Beijing and affiliation not provided to SSRN
Downloads 17 (1,491,251)

Abstract:

Loading...

Multimodal Learning, Continual Learning, Audio-visual Segmentation, Class-Incremental Segmentation

2.

DSFC-Net: A Dual-Encoder Spatial and Frequency Co-Awareness Network for Rural Road Extraction

Number of pages: 12 Posted: 03 Apr 2026
affiliation not provided to SSRN, affiliation not provided to SSRN, Tsinghua University - Tsinghua Shenzhen International Graduate School, affiliation not provided to SSRN, affiliation not provided to SSRN, affiliation not provided to SSRN, affiliation not provided to SSRN, Tsinghua University - Department of Earth System Science and affiliation not provided to SSRN
Downloads 14 (1,534,404)

Abstract:

Loading...

Road Extraction, Remote sensing, Semantic segmentation, Rural Infrastructure, Vision Transformer, Convolutional Neural Network