152 citations · 788 across the 49 of their papers we have counts for
13 papers · 1 filter
Time-Aware Neighbor Sampling for Temporal Graph Networks
Yiwei Wang, Yujun Cai, Yuxuan Liang +3
We present a new neighbor sampling method on temporal graphs. In a temporal graph, predicting different nodes' time-varying properties can require the receptive neighborhood of var…
Structure-Aware Label Smoothing for Graph Neural Networks
Yiwei Wang, Yujun Cai, Yuxuan Liang +5
Representing a label distribution as a one-hot vector is a common practice in training node classification models. However, the one-hot representation may not adequately reflect th…
Meta Navigator: Search for a Good Adaptation Policy for Few-shot Learning
Chi Zhang, Henghui Ding, Guosheng Lin +3
Few-shot learning aims to adapt knowledge learned from previous tasks to novel tasks with only a limited amount of labeled data. Research literature on few-shot learning exhibits g…
Calibrating Class Activation Maps for Long-Tailed Visual Recognition
Chi Zhang, Guosheng Lin, Lvlong Lai +2
Real-world visual recognition problems often exhibit long-tailed distributions, where the amount of data for learning in different categories shows significant imbalance. Standard…
Vision-Language Transformer and Query Generation for Referring Segmentation
Henghui Ding, Chang Liu, Suchen Wang +1
In this work, we address the challenging task of referring segmentation. The query expression in referring segmentation typically indicates the target object by describing its rela…
M2IOSR: Maximal Mutual Information Open Set Recognition
Xin Sun, Henghui Ding, Chi Zhang +2
In this work, we aim to address the challenging task of open set recognition (OSR). Many recent OSR methods rely on auto-encoders to extract class-specific features by a reconstruc…
Few-shot Segmentation with Optimal Transport Matching and Message Flow
Weide Liu, Chi Zhang, Henghui Ding +2
We tackle the challenging task of few-shot segmentation in this work. It is essential for few-shot semantic segmentation to fully utilize the support information. Previous methods…
Few-Shot Segmentation with Global and Local Contrastive Learning
Weide Liu, Zhonghua Wu, Henghui Ding +4
In this work, we address the challenging task of few-shot segmentation. Previous few-shot segmentation methods mainly employ the information of support images as guidance for query…
Recovering the Unbiased Scene Graphs from the Biased Ones
Meng-Jiun Chiou, Henghui Ding, Hanshu Yan +3
Given input images, scene graph generation (SGG) aims to produce comprehensive, graphical representations describing visual relationships among salient objects. Recently, more effo…
Improving Video Instance Segmentation via Temporal Pyramid Routing
Xiangtai Li, Hao He, Yibo Yang +5
Video Instance Segmentation (VIS) is a new and inherently multi-task problem, which aims to detect, segment, and track each instance in a video sequence. Existing approaches are ma…
Knowledge-aware Deep Framework for Collaborative Skin Lesion Segmentation and Melanoma Recognition
Xiaohong Wang, Xudong Jiang, Henghui Ding +2
Deep learning techniques have shown their superior performance in dermatologist clinical inspection. Nevertheless, melanoma diagnosis is still a challenging task due to the difficu…
MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesis
Jiaxin Li, Zijian Feng, Qi She +3
In this paper, we propose MINE to perform novel view synthesis and depth estimation via dense 3D reconstruction from a single image. Our approach is a continuous depth generalizati…
Towards Enhancing Fine-grained Details for Image Matting
Chang Liu, Henghui Ding, Xudong Jiang
In recent years, deep natural image matting has been rapidly evolved by extracting high-level contextual features into the model. However, most current methods still have difficult…