Search Results for author:
Found 64 papers, 32 papers with code
Count- and Similarity-aware R-CNN for Pedestrian Detection
We further introduce a count-and-similarity branch within the two-stage detection framework, which predicts pedestrian count as well as proposal similarity.
iSeg: An Iterative Refinement-based Framework for Training-free Segmentation
To address this, we propose an iterative refinement framework for training-free segmentation, named iSeg, having an entropy-reduced self-attention module which utilizes a gradient descent scheme to reduce the entropy of self-attention map, thereby suppressing the weak responses corresponding to irrelevant global information.
Text2LiDAR: Text-guided LiDAR Point Cloud Generation via Equirectangular Transformer
The complex traffic environment and various weather conditions make the collection of LiDAR data expensive and challenging.
MSfusion: A Dynamic Model Splitting Approach for Resource-Constrained Machines to Collaboratively Train Larger Models
Training large models requires a large amount of data, as well as abundant computation resources.
FedMeS: Personalized Federated Continual Learning Leveraging Local Memory
We focus on the problem of Personalized Federated Continual Learning (PFCL): a group of distributed clients, each with a sequence of local tasks on arbitrary data distributions, collaborate through a central server to train a personalized model at each client, with the model expected to achieve good performance on all local tasks.
VFMM3D: Releasing the Potential of Image by Vision Foundation Model for Monocular 3D Object Detection
Therefore, an effective solution involves transforming monocular images into LiDAR-like representations and employing a LiDAR-based 3D object detector to predict the 3D coordinates of objects.
Implicit and Explicit Language Guidance for Diffusion-based Visual Perception
The explicit branch utilizes the ground-truth labels of corresponding images as text prompts to condition feature extraction of diffusion model.
Diff-Reg v1: Diffusion Matching Model for Registration Problem
Establishing reliable correspondences is essential for registration tasks such as 3D and 2D3D registration.
CLIP-VIS: Adapting CLIP for Open-Vocabulary Video Instance Segmentation
Open-vocabulary video instance segmentation strives to segment and track instances belonging to an open set of categories in a video.
Active Simultaneously Transmitting and Reflecting Surface Assisted NOMA Networks
The numerical results are presented and show that: 1) ASTARS-NOMA with pSIC outperforms ASTARS assisted-orthogonal multiple access (ASTARS-OMA) in terms of outage probability and ergodic data rate; 2) The outage probability of ASTARS-NOMA can be further reduced within a certain range by increasing the power amplification factors; 3) The system throughputs of ASTARS-NOMA are superior to that of ASTARS-OMA in both delay-limited and delay-tolerant transmission modes.
Multi-Attribute Interactions Matter for 3D Visual Grounding
3D visual grounding aims to localize 3D objects described by free-form language sentences.
Diff-PCR: Diffusion-Based Correspondence Searching in Doubly Stochastic Matrix Space for Point Cloud Registration
They typically compute candidate correspondences based on distances in the point feature space.
SPGroup3D: Superpoint Grouping Network for Indoor 3D Object Detection
To this end, we propose a novel superpoint grouping network for indoor anchor-free one-stage 3D object detection.
Ranked #5 on
3D Object Detection
on S3DIS
SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation
In this paper, we propose a simple encoder-decoder, named SED, for open-vocabulary semantic segmentation, which comprises a hierarchical encoder-based cost map generation and a gradual fusion decoder with category early rejection.
SGNet: Salient Geometric Network for Point Cloud Registration
These high-order features are then propagated to dense points and utilized by a Sinkhorn matching module to identify key correspondences for successful registration.
Implicit Obstacle Map-driven Indoor Navigation Model for Robust Obstacle Avoidance
Robust obstacle avoidance is one of the critical steps for successful goal-driven indoor navigation tasks. Due to the obstacle missing in the visual image and the possible missed detection issue, visual image-based obstacle avoidance techniques still suffer from unsatisfactory robustness.
Self-Supervised 3D Scene Flow Estimation Guided by Superpoints
In our superpoint generation module, we utilize the bidirectional flow information at the previous iteration to obtain the matching points of points and superpoint centers for soft point-to-superpoint association construction, in which the superpoints are generated for pairwise point clouds.
Transformer-based stereo-aware 3D object detection from binocular images
In this paper, we explore the model design of Transformers in binocular 3D object detection, focusing particularly on extracting and encoding task-specific image correspondence information.
Multi-Mode Online Knowledge Distillation for Self-Supervised Visual Representation Learning
Different from existing SSL-KD methods that transfer knowledge from a static pre-trained teacher to a student, in MOKD, two different models learn collaboratively in a self-supervised manner.
Hard Patches Mining for Masked Image Modeling
We observe that the reconstruction loss can naturally be the metric of the difficulty of the pre-training task.
Robust Outlier Rejection for 3D Registration with Variational Bayes
Embedded with the inlier/outlier label, the posterior feature distribution is label-dependent and discriminative.
LEAPS: End-to-End One-Step Person Search With Learnable Proposals
Given a set of sparse and learnable proposals, LEAPS employs a dynamic person search head to directly perform person detection and corresponding re-id feature generation without non-maximum suppression post-processing.
Graph Matching Optimization Network for Point Cloud Registration
Point Cloud Registration is a fundamental and challenging problem in 3D computer vision.
Efficient LiDAR Point Cloud Oversegmentation Network
Then, to generate homogeneous superpoints from the sparse LiDAR point cloud, we propose a LiDAR point grouping algorithm that simultaneously considers the similarity of point embeddings and the Euclidean distance of points in 3D space.
Center-Based Decoupled Point-cloud Registration for 6D Object Pose Estimation
Our method decouples the translation from the entire transformation by predicting the object center and estimating the rotation in a center-aware manner.
Semantics-Consistent Feature Search for Self-Supervised Visual Representation Learning
In contrastive self-supervised learning, the common way to learn discriminative representation is to pull different augmented "views" of the same image closer while pushing all other images further apart, which has been proven to be effective.
Learning Inter-Superpoint Affinity for Weakly Supervised 3D Instance Segmentation
Due to the few annotated labels of 3D point clouds, how to learn discriminative features of point clouds to segment object instances is a challenging problem.
Point Cloud Registration-Driven Robust Feature Matching for 3D Siamese Object Tracking
The core of Siamese feature matching is how to assign high feature similarity on the corresponding points between the template and search area for precise object localization.
Unsupervised Domain Adaptation for Point Cloud Semantic Segmentation via Graph Matching
Unsupervised domain adaptation for point cloud semantic segmentation has attracted great attention due to its effectiveness in learning with unlabeled data.
RA-Depth: Resolution Adaptive Self-Supervised Monocular Depth Estimation
In this paper, we propose a resolution adaptive self-supervised monocular depth estimation method (RA-Depth) by learning the scale invariance of the scene depth.
Generative Subgraph Contrast for Self-Supervised Graph Representation Learning
To this end, in this paper, we propose a novel adaptive subgraph generation based contrastive learning framework for efficient and robust self-supervised graph representation learning, and the optimal transport distance is utilized as the similarity metric between the subgraphs.
3D Siamese Transformer Network for Single Object Tracking on Point Clouds
Siamese network based trackers formulate 3D single object tracking as cross-correlation learning between point features of a template and a search area.
Unsupervised Visible-light Images Guided Cross-Spectrum Depth Estimation from Dual-Modality Cameras
Meanwhile, we release a large dual-spectrum depth estimation dataset with visible-light and far-infrared stereo images captured in different scenes to the society.
PSTR: End-to-End One-Step Person Search With Transformers
We propose a novel one-step transformer-based person search framework, PSTR, that jointly performs person detection and re-identification (re-id) in a single architecture.
Action Candidate Driven Clipped Double Q-learning for Discrete and Continuous Action Tasks
Finally, we use the maximum value in the second set of estimators to clip the action value of the chosen action in the first set of estimators and the clipped value is used for approximating the maximum expected action value.
The Design and Implementation of a Broadly Applicable Algorithm for Optimizing Intra-Day Surgical Scheduling
In order for an algorithm to see sustained use, it must be compatible with changes to hospital capacity, patient volumes, and scheduling practices.
Domain Disentangled Generative Adversarial Network for Zero-Shot Sketch-Based 3D Shape Retrieval
Then, we develop a generative adversarial network that combines the domain-specific features of the seen categories with the aligned domain-invariant features to synthesize samples, where the synthesized samples of the unseen categories are generated by using the corresponding word embeddings.
Reliable Inlier Evaluation for Unsupervised Point Cloud Registration
In this paper, we propose a neighborhood consensus based reliable inlier evaluation method for robust unsupervised point cloud registration.
3D Siamese Voxel-to-BEV Tracker for Sparse Point Clouds
The Siamese shape-aware feature learning network can capture 3D shape information of the object to learn the discriminative features of the object so that the potential target from the background in sparse point clouds can be identified.
Sampling Network Guided Cross-Entropy Method for Unsupervised Point Cloud Registration
Based on the reward function, for each state, we then construct a fused score function to evaluate the sampled transformations, where we weight the current and future rewards of the transformations.
A new neighborhood structure for job shop scheduling problems
According to the above finding, this paper proposes a new N8 neighborhood structure considering the movement of critical operations within a critical block and the movement of critical operations outside the critical block.
UnDeepLIO: Unsupervised Deep Lidar-Inertial Odometry
Nonetheless, few efforts are made on the unsupervised deep lidar odometry.
Planning with Learned Dynamic Model for Unsupervised Point Cloud Registration
By modeling the point cloud registration process as a Markov decision process (MDP), we develop a latent dynamic model of point clouds, consisting of a transformation network and evaluation network.
SSPU-Net: Self-Supervised Point Cloud Upsampling via Differentiable Rendering
To achieve this, we exploit the consistency between the input sparse point cloud and generated dense point cloud for the shapes and rendered images.
Action Candidate Based Clipped Double Q-learning for Discrete and Continuous Action Tasks
Finally, we use the maximum value in the second set of estimators to clip the action value of the chosen action in the first set of estimators and the clipped value is used for approximating the maximum expected action value.
SSPC-Net: Semi-supervised Semantic 3D Point Cloud Segmentation Network
In order to reduce the number of annotated labels, we propose a semi-supervised semantic point cloud segmentation network, named SSPC-Net, where we train the semantic segmentation network by inferring the labels of unlabeled points from the few annotated 3D points.
SIENet: Spatial Information Enhancement Network for 3D Object Detection from Point Cloud
Specifically, we design the Spatial Information Enhancement (SIE) module to predict the spatial shapes of the foreground points within proposals, and extract the structure information to learn the representative features for further box refinement.
MSCFNet: A Lightweight Network With Multi-Scale Context Fusion for Real-Time Semantic Segmentation
In recent years, how to strike a good trade-off between accuracy and inference speed has become the core issue for real-time semantic segmentation applications, which plays a vital role in real-world scenarios such as autonomous driving systems and drones.
Efficient 3D Point Cloud Feature Learning for Large-Scale Place Recognition
In this paper, we develop an efficient point cloud learning network (EPC-Net) to form a global descriptor for visual place recognition, which can obtain good performance and reduce computation memory and inference time.
Pyramid Point Cloud Transformer for Large-Scale Place Recognition
In order to obtain discriminative global descriptors, we construct a pyramid VLAD module to aggregate the multi-scale feature maps of point clouds into the global descriptors.
Ranked #3 on
3D Place Recognition
on Oxford RobotCar Dataset
Superpoint Network for Point Cloud Oversegmentation
Specifically, in our clustering network, we first jointly learn a soft point-superpoint association map from the coordinate and feature spaces of point clouds, where each point is assigned to the superpoint with a learned weight.
TJU-DHD: A Diverse High-Resolution Dataset for Object Detection
In addition, a new diverse pedestrian dataset is further built.
From Handcrafted to Deep Features for Pedestrian Detection: A Survey
In addition to single-spectral pedestrian detection, we also review multi-spectral pedestrian detection, which provides more robust features for illumination variance.
Cascaded Non-local Neural Network for Point Cloud Semantic Segmentation
In this paper, we propose a cascaded non-local neural network for point cloud segmentation.
Progressive Point Cloud Deconvolution Generation Network
Starting from the low-resolution point clouds, with the bilateral interpolation and max-pooling operations, the deconvolution network can progressively output high-resolution local and global feature maps.
PSC-Net: Learning Part Spatial Co-occurrence for Occluded Pedestrian Detection
On the heavy occluded (\textbf{HO}) set of CityPerosns test set, our PSC-Net obtains an absolute gain of 4. 0\% in terms of log-average miss rate over the state-of-the-art with same backbone, input scale and without using additional VBB supervision.
A Two-stream End-to-End Deep Learning Network for Recognizing Atypical Visual Attention in Autism Spectrum Disorder
In this study, we developed a novel two-stream deep learning network for this recognition based on 700 images and corresponding eye movement patterns of ASD and TD, and obtained an accuracy of 0. 95, which was higher than the previous state-of-the-art.
Mask-Guided Attention Network for Occluded Pedestrian Detection
Our approach obtains an absolute gain of 9. 5% in log-average miss rate, compared to the best reported results on the heavily occluded (HO) pedestrian set of CityPersons test set.
A Method to Facilitate Cancer Detection and Type Classification from Gene Expression Data using a Deep Autoencoder and Neural Network
Here we present models of deep learning (DL) and apply them to gene expression data for the diagnosis and categorization of cancer.
Learning Barycentric Representations of 3D Shapes for Sketch-Based 3D Shape Retrieval
For 3D shapes, we then compute the Wasserstein barycenters of deep features of multiple projections to form a barycentric representation.
Learned Binary Spectral Shape Descriptor for 3D Shape Correspondence
Different from these real-valued local shape descriptors, in this paper, we propose to learn a novel binary spectral shape descriptor with the deep neural network for 3D shape correspondence.
3D Deep Shape Descriptor
Shape descriptor is a concise yet informative representation that provides a 3D object with an identification as a member of some category.
DeepShape: Deep Learned Shape Descriptor for 3D Shape Matching and Retrieval
Then, by imposing the Fisher discrimination criterion on the neurons in the hidden layer, we developed a novel discriminative deep auto-encoder for shape feature learning.
