2.5k citations · 4.7k across the 18 of their papers we have counts for
18 papers
Recovering Complete Actions for Cross-dataset Skeleton Action Recognition
Hanchao Liu, Yujiang Li, Tai-Jiang Mu +1
Despite huge progress in skeleton-based action recognition, its generalizability to different domains remains a challenging issue. In this paper, to solve the skeleton action gener…
A New Split Algorithm for 3D Gaussian Splatting
Qiyuan Feng, Gengchen Cao, Haoxiang Chen +3
3D Gaussian splatting models, as a novel explicit 3D representation, have been applied in many domains recently, such as explicit geometric editing and geometry generation. Progres…
Theoretically Achieving Continuous Representation of Oriented Bounding Boxes
Zi-Kai Xiao, Guo-Ye Yang, Xue Yang +3
Considerable efforts have been devoted to Oriented Object Detection (OOD). However, one lasting issue regarding the discontinuity in Oriented Bounding Box (OBB) representation rema…
Semantic-Aware Transformation-Invariant RoI Align
Guo-Ye Yang, George Kiyohiro Nakayama, Zi-Kai Xiao +3
Great progress has been made in learning-based object detection methods in the last decade. Two-stage detectors often have higher detection accuracy than one-stage detectors, due t…
Long Range Pooling for 3D Large-Scale Scene Understanding
Xiang-Li Li, Meng-Hao Guo, Tai-Jiang Mu +2
Inspired by the success of recent vision transformers and large kernel design in convolutional neural networks (CNNs), in this paper, we analyze and explore essential reasons for t…
MonoNeuralFusion: Online Monocular Neural 3D Reconstruction with Geometric Priors
Zi-Xin Zou, Shi-Sheng Huang, Yan-Pei Cao +3
High-fidelity 3D scene reconstruction from monocular videos continues to be challenging, especially for complete and fine-grained geometry reconstruction. The previous 3D reconstru…
ClusterGNN: Cluster-based Coarse-to-Fine Graph Neural Network for Efficient Feature Matching
Yan Shi, Jun-Xiong Cai, Yoli Shavit +3
Graph Neural Networks (GNNs) with attention have been successfully applied for learning visual feature matching. However, current methods learn with complete graphs, resulting in a…
CIRCLE: Convolutional Implicit Reconstruction and Completion for Large-scale Indoor Scene
Haoxiang Chen, Jiahui Huang, Tai-Jiang Mu +1
We present CIRCLE, a framework for large-scale scene completion and geometric refinement based on local implicit signed distance functions. It is based on an end-to-end sparse conv…
Attention Mechanisms in Computer Vision: A Survey
Meng-Hao Guo, Tian-Xing Xu, Jiang-Jiang Liu +7
Humans can naturally and effectively find salient regions in complex scenes. Motivated by this observation, attention mechanisms were introduced into computer vision with the aim o…
Subdivision-Based Mesh Convolution Networks
Shi-Min Hu, Zheng-Ning Liu, Meng-Hao Guo +4
Convolutional neural networks (CNNs) have made great breakthroughs in 2D computer vision. However, their irregular structure makes it hard to harness the potential of CNNs directly…
Can Attention Enable MLPs To Catch Up With CNNs?
Meng-Hao Guo, Zheng-Ning Liu, Tai-Jiang Mu +3
In the first week of May, 2021, researchers from four different institutions: Google, Tsinghua University, Oxford University and Facebook, shared their latest work [16, 7, 12, 17]…
Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks
Meng-Hao Guo, Zheng-Ning Liu, Tai-Jiang Mu +1
Attention mechanisms, especially self-attention, have played an increasingly important role in deep feature representation for visual tasks. Self-attention updates the feature at e…
Recursive-NeRF: An Efficient and Dynamically Growing NeRF
Guo-Wei Yang, Wen-Yang Zhou, Hao-Yang Peng +3
View synthesis methods using implicit continuous shape representations learned from a set of images, such as the Neural Radiance Field (NeRF) method, have gained increasing attenti…
PCT: Point cloud transformer
Meng-Hao Guo, Jun-Xiong Cai, Zheng-Ning Liu +3
The irregular domain and lack of ordering make it challenging to design deep neural networks for point cloud processing. This paper presents a novel framework named Point Cloud Tra…
Alternating ConvLSTM: Learning Force Propagation with Alternate State Updates
Congyue Deng, Tai-Jiang Mu, Shi-Min Hu
Data-driven simulation is an important step-forward in computational physics when traditional numerical methods meet their limits. Learning-based simulators have been widely studie…
VGPN: Voice-Guided Pointing Robot Navigation for Humans
Jun Hu, Zhongyu Jiang, Xionghao Ding +2
Pointing gestures are widely used in robot navigationapproaches nowadays. However, most approaches only use point-ing gestures, and these have two major limitations. Firstly, they…
ClusterVO: Clustering Moving Instances and Estimating Visual Odometry for Self and Surroundings
Jiahui Huang, Sheng Yang, Tai-Jiang Mu +1
We present ClusterVO, a stereo Visual Odometry which simultaneously clusters and estimates the motion of both ego and surrounding rigid clusters/objects. Unlike previous solutions…
S4Net: Single Stage Salient-Instance Segmentation
Ruochen Fan, Ming-Ming Cheng, Qibin Hou +3
We consider an interesting problem-salient instance segmentation in this paper. Other than producing bounding boxes, our network also outputs high-quality instance-level segments.…