2 citations · 8 across the 8 of their papers we have counts for
8 papers
MXM-CLR: A Unified Framework for Contrastive Learning of Multifold Cross-Modal Representations
Ye Wang, Bowei Jiang, Changqing Zou +1
Multifold observations are common for different data modalities, e.g., a 3D shape can be represented by multi-view images and an image can be described with different captions. Exi…
P3DC-Shot: Prior-Driven Discrete Data Calibration for Nearest-Neighbor Few-Shot Classification
Shuangmei Wang, Rui Ma, Tieru Wu +1
Nearest-Neighbor (NN) classification has been proven as a simple and effective approach for few-shot learning. The query data can be classified efficiently by finding the nearest s…
Shape-Aware Fine-Grained Classification of Erythroid Cells
Ye Wang, Rui Ma, Xiaoqing Ma +4
Fine-grained classification and counting of bone marrow erythroid cells are vital for evaluating the health status and formulating therapeutic schedules for leukemia or hematopathy…
FD-CAM: Improving Faithfulness and Discriminability of Visual Explanation for CNNs
Hui Li, Zihao Li, Rui Ma +1
Class activation map (CAM) has been widely studied for visual explanation of the internal working mechanism of convolutional neural networks. The key of existing CAM-based methods…
SAC-GAN: Structure-Aware Image Composition
Hang Zhou, Rui Ma, Ling-Xiao Zhang +3
We introduce an end-to-end learning framework for image-to-image composition, aiming to plausibly compose an object represented as a cropped patch from an object image into a backg…
Spatial-Temporal Residual Aggregation for High Resolution Video Inpainting
Vishnu Sanjay Ramiya Srinivasan, Rui Ma, Qiang Tang +2
Recent learning-based inpainting algorithms have achieved compelling results for completing missing regions after removing undesired objects in videos. To maintain the temporal con…
RaidaR: A Rich Annotated Image Dataset of Rainy Street Scenes
Jiongchao Jin, Arezou Fatemi, Wallace Lira +5
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,…
Analysis and Modeling of 3D Indoor Scenes
Rui Ma
We live in a 3D world, performing activities and interacting with objects in the indoor environments everyday. Indoor scenes are the most familiar and essential environments in eve…