Search Results for author:
Found 16 papers, 7 papers with code
Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks
Attention mechanisms, especially self-attention, have played an increasingly important role in deep feature representation for visual tasks.
Ranked #16 on
Semantic Segmentation
on PASCAL VOC 2012 test
Attention Mechanisms in Computer Vision: A Survey
Humans can naturally and effectively find salient regions in complex scenes.
PCT: Point cloud transformer
It is inherently permutation invariant for processing a sequence of points, making it well-suited for point cloud learning.
Ranked #2 on
3D Point Cloud Classification
on IntrA
Subdivision-Based Mesh Convolution Networks
Meshes with arbitrary connectivity can be remeshed to have Loop subdivision sequence connectivity via self-parameterization, making SubdivNet a general approach.
Theoretically Achieving Continuous Representation of Oriented Bounding Boxes
Considerable efforts have been devoted to Oriented Object Detection (OOD).
S4Net: Single Stage Salient-Instance Segmentation
Taking into account the category-independent property of each target, we design a single stage salient instance segmentation framework, with a novel segmentation branch.
Recursive-NeRF: An Efficient and Dynamically Growing NeRF
Only query coordinates with high uncertainties are forwarded to the next level to a bigger neural network with a more powerful representational capability.
ClusterVO: Clustering Moving Instances and Estimating Visual Odometry for Self and Surroundings
We present ClusterVO, a stereo Visual Odometry which simultaneously clusters and estimates the motion of both ego and surrounding rigid clusters/objects.
Alternating ConvLSTM: Learning Force Propagation with Alternate State Updates
Experimental results show that Alt-ConvLSTM efficiently models the material kinetic features and greatly outperforms vanilla ConvLSTM with only the single state update.
Can Attention Enable MLPs To Catch Up With CNNs?
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] on arXiv. org almost at the same time, each proposing new learning architectures, consisting mainly of linear layers, claiming them to be comparable, or even superior to convolutional-based models.
CIRCLE: Convolutional Implicit Reconstruction and Completion for Large-scale Indoor Scene
We present CIRCLE, a framework for large-scale scene completion and geometric refinement based on local implicit signed distance functions.
ClusterGNN: Cluster-based Coarse-to-Fine Graph Neural Network for Efficient Feature Matching
Graph Neural Networks (GNNs) with attention have been successfully applied for learning visual feature matching.
MonoNeuralFusion: Online Monocular Neural 3D Reconstruction with Geometric Priors
This paper introduces a novel neural implicit scene representation with volume rendering for high-fidelity online 3D scene reconstruction from monocular videos.
Long Range Pooling for 3D Large-Scale Scene Understanding
To achieve the above properties, we propose a simple yet effective long range pooling (LRP) module using dilation max pooling, which provides a network with a large adaptive receptive field.
SLS4D: Sparse Latent Space for 4D Novel View Synthesis
It then learns the spatial features of a 3D position using another sparse latent space.
Semantic-Aware Transformation-Invariant RoI Align
In this paper, we propose a novel RoI feature extractor, termed Semantic RoI Align (SRA), which is capable of extracting invariant RoI features under a variety of transformations for two-stage detectors.
