1

EPSD: Early Pruning with Self-Distillation for Efficient Model Compression
Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software. Create your slides in Markdown - click the Slides button to check out the example.
Dong Chen, Ning Liu, Yichen Zhu, Zhengping Che, Rui Ma # , Fachao Zhang, Xiaofeng Mou, Yi Chang, Jian Tang #
PDF Cite
EPSD: Early Pruning with Self-Distillation for Efficient Model Compression
P2M2-Net: Part-Aware Prompt-Guided Multimodal Point Cloud Completion
Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software. Create your slides in Markdown - click the Slides button to check out the example.
Linlian Jiang, Pan Chen, Ye Wang, Tieru Wu, Rui Ma #
Cite Code
P2M2-Net: Part-Aware Prompt-Guided Multimodal Point Cloud Completion
MXM-CLR: A Unified Framework for Contrastive Learning of Multifold Cross-Modal Representations
Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software. Create your slides in Markdown - click the Slides button to check out the example.
Ye Wang, Changqing Zou, Rui Ma #
PDF Cite Code
MXM-CLR: A Unified Framework for Contrastive Learning of Multifold Cross-Modal Representations
FD-CAM: Improving Faithfulness and Discriminability of Visual Explanation for CNNs
We propose FD-CAM, a novel CAM (Class activation map) weighting scheme, to improve both the faithfulness and discriminability of the CAM-based CNN visual explanation.
Hui Li, Zihao Li, Rui Ma # , Tieru Wu #
PDF Cite Code
FD-CAM: Improving Faithfulness and Discriminability of Visual Explanation for CNNs
Spatial-Temporal Residual Aggregation for High Resolution Video Inpainting
We propose STRA-Net, a novel spatial-temporal residual aggregation framework for high resolution video inpainting. Our method can produce temporal-coherent inpainting results for high resolution videos efficiently.
Vishnu Sanjay Ramiya Srinivasan * , Rui Ma * , Qiang Tang # , Zili Yi, Zhan Xu
PDF Cite
Spatial-Temporal Residual Aggregation for High Resolution Video Inpainting
RaidaR: A Rich Annotated Image Dataset of Rainy Street Scenes
We introduce RaidaR, a rich annotated image dataset of rainy street scenes, to support autonomous driving research. The new dataset contains the largest number of rainy images (58,542) to date, 5,000 of which provide semantic segmentations and 3,658 provide object instance segmentations.
Jiongchao Jin * , Arezou Fatemi * , Wallace Lira, Fenggen Yu, Biao Leng, Rui Ma # , Ali Mahdavi-Amiri, Hao Zhang
Cite Project
RaidaR: A Rich Annotated Image Dataset of Rainy Street Scenes
GaussianPrediction: Dynamic 3D Gaussian Prediction for Motion Extrapolation and Free View Synthesis
Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software. Create your slides in Markdown - click the Slides button to check out the example.
Boming Zhao * , Yuan Li * , Ziyu Sun, Lin Zeng, Yujun Shen, Rui Ma, Yinda Zhang, Hujun Bao, Zhaopeng Cui
Cite Code Project
GaussianPrediction: Dynamic 3D Gaussian Prediction for Motion Extrapolation and Free View Synthesis