Da Song
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Da Song has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Chuanxu Wang
Qingdao University of Science and Technology, School of Information Science and Technology, Qingdao, China
5 shared publications - Binghui Wang3 shared publications
Binghui Wang
Qingdao University of Science and Technology
2 shared publications- Chunjuan Yan2 shared publications
- Jiajiong Li
Qingdao University of Science and Technology
2 shared publications - Lanxiao Li2 shared publications
Latest Publications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (11) , 16153-16163
PVContrast: Point-Voxel Contrastive Learning Network for Point Cloud Semantic Segmentation
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (11) , 16153-16163
PVContrast: Point-Voxel Contrastive Learning Network for Point Cloud Semantic Segmentation
- 24 March 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 320
IPG-FRN: Intrinsic prototype-guided feature reconstruction network for industrial anomaly detection
- 24 March 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 320
IPG-FRN: Intrinsic prototype-guided feature reconstruction network for industrial anomaly detection
- 18 February 2026
- Published by Elsevier in Pattern Recognition
- Vol. 177
A prototype correction multi-scale feature reconstruction network for industrial anomaly detection
- 18 February 2026
- Published by Elsevier in Pattern Recognition
- Vol. 177
A prototype correction multi-scale feature reconstruction network for industrial anomaly detection
- 18 January 2026
- Published by Elsevier in Pattern Recognition
- Vol. 175
GMSFormer: Geometric-aware multi-structured transformer for point cloud understanding
- 18 January 2026
- Published by Elsevier in Pattern Recognition
- Vol. 175
GMSFormer: Geometric-aware multi-structured transformer for point cloud understanding
- 11 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (5) , 6651-6660
Align and Blend: A Unified Multi-Modal LiDAR Segmentation Network
The multimodal fusion of point cloud data is a challenging task in 3D computer vision, particularly in fine object segmentation. In this study, we propose an innovative unified multimodal LiDAR segmentation network, named Align and Blend (A2Blend for short), which skillfully integrates three representative forms of point clouds: point view, voxel view, and range view. The core innovation of A2Blend lies in addressing two primary tasks: Align and Blend. For the “Align” task, we have carefully designed a learnable cross-modal association module, whose core is a unique “Cross-Modal Triplet Alignment Loss” mechanism. To the best of our knowledge, this is the first application of such a mechanism in the field of LiDAR segmentation. This mechanism applies principles from contrastive learning, promoting the tight clustering of similar semantic groups both within and across modalities, while increasing the separation between dissimilar groups by expanding the distance between similar and dissimilar sample clusters in the feature space. This significantly enhances the discriminative power and representational capacity of the feature embeddings. For the “Blend” task, we propose a fusion strategy that integrates intragroup self-attention within modalities and intergroup self-attention across modalities. This approach combines key concepts from standard self-attention and cross-self-attention mechanisms to achieve more comprehensive multimodal fusion. The segmentation performance on two large-scale outdoor datasets and one indoor dataset surpasses that of most state-of-the-art algorithms.
- 11 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (5) , 6651-6660
Align and Blend: A Unified Multi-Modal LiDAR Segmentation Network
The multimodal fusion of point cloud data is a challenging task in 3D computer vision, particularly in fine object segmentation. In this study, we propose an innovative unified multimodal LiDAR segmentation network, named Align and Blend (A2Blend for short), which skillfully integrates three representative forms of point clouds: point view, voxel view, and range view. The core innovation of A2Blend lies in addressing two primary tasks: Align and Blend. For the “Align” task, we have carefully designed a learnable cross-modal association module, whose core is a unique “Cross-Modal Triplet Alignment Loss” mechanism. To the best of our knowledge, this is the first application of such a mechanism in the field of LiDAR segmentation. This mechanism applies principles from contrastive learning, promoting the tight clustering of similar semantic groups both within and across modalities, while increasing the separation between dissimilar groups by expanding the distance between similar and dissimilar sample clusters in the feature space. This significantly enhances the discriminative power and representational capacity of the feature embeddings. For the “Blend” task, we propose a fusion strategy that integrates intragroup self-attention within modalities and intergroup self-attention across modalities. This approach combines key concepts from standard self-attention and cross-self-attention mechanisms to achieve more comprehensive multimodal fusion. The segmentation performance on two large-scale outdoor datasets and one indoor dataset surpasses that of most state-of-the-art algorithms.