Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks134 from public data
- 3D Recurrent Neural Networks with Context Fusion for Point Cloud Semantic Segmentation287
A novel end-to-end approach for unstructured point cloud semantic segmentation, named 3P-RNN, is proposed to exploit the inherent contextual features of 3D point clouds to demonstrate robust performance superior to state-of-the-arts.
- Rethinking the Open-Loop Evaluation of End-to-End Autonomous Driving in nuScenes222
An MLP-based method that takes raw sensor data as input and directly outputs the future trajectory of the ego vehicle, without using any perception or prediction information such as camera images or LiDAR, achieves similar end-to-end planning performance on the nuScenes dataset with other perception-based methods.
- Rope3D: The Roadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Task182
The first high-diversity challenging Roadside Perception 3D dataset- Rope3D from a novel view is presented, which tailor the existing frontal-view monocular 3D object detection approaches and propose to leverage the geometry constraint to solve the inherent ambiguities caused by various sensors, viewpoints.
- 171
- Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection170
A depth-conditioned dynamic message propagation (DDMP) network to effectively integrate the multi-scale depth information with the image context and dynamically predicting hybrid depth-dependent filter weights and affinity matrices for propagating information is proposed.
- CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model115
This work proposes a novel unsupervised framework for crowd counting, named CrowdCLIP, which is the first to investigate the vision-language knowledge to solve the counting problem and surpasses some pop-ular fully-supervised methods under the cross-dataset setting.
- 110
- Associate-3Ddet: Perceptual-to-Conceptual Association for 3D Point Cloud Object Detection104
A domain adaptation like approach is innovatively proposed to enhance the robustness of the feature representation in 3D object detection and mimics the functionality of the human brain when proceeding object perception.
- 96
- DrivingDiffusion: Layout-Guided multi-view driving scene video generation with latent diffusion model90
This work proposes a spatial-temporal consistent diffusion framework DrivingDiffusion, to generate realistic multi-view videos controlled by 3D layout and introduces the local prompt to effectively improve the quality of generated instances.
- Forward Flow for Novel View Synthesis of Dynamic Scenes90
Thorough experiments show that the proposed neural radiance field approach outperforms existing methods in both novel view rendering and motion modeling, demonstrating the effectiveness of the forward flow motion modeling.
- IST-Net: Prior-free Category-level Pose Estimation with Implicit Space Transformation81
A simple prior-free implicit space transformation network, namely IST-Net, is introduced to transform camera-space features to world-space counterparts and build correspondences between them in an implicit manner without relying on 3D priors, with state-of-the-art performance based on prior-free design.
- ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection78
A novel framework named ZoomNet for stereo imagery-based 3D detection, which surpasses all previous state-of-the-art methods by large margins and introduces to learn part locations as complementary features to improve the resistance against occlusion and put forward the 3D fitting score to better estimate the3D detection quality.
- SAM3D: zero-shot 3D object detection via the segment anything model72
This paper proposes a SAM-powered BEV processing pipeline to detect objects and gets promising results on the large-scale Waymo open dataset and presents the opportunity to unleash their power on 3D vision tasks.
- SOOD: Towards Semi-Supervised Oriented Object Detection70
A novel Semi-supervised Oriented Object Detection model, termed SOOD, built upon the mainstream pseudo-labeling framework is proposed, which surpasses the state-of-the-art SSOD methods under various settings on the DOTAv1.5 benchmark.
- The Devil is in the Task: Exploiting Reciprocal Appearance-Localization Features for Monocular 3D Object Detection67
This paper digs into the 3D object detection task and reformulate it as the sub-tasks of object localization and appearance perception, which benefits to a deep excavation of reciprocal information underlying the entire task.
- CAPE: Camera View Position Embedding for Multi-View 3D Object Detection60
This paper proposes a novel method based on CAmera view Position Embedding, called CAPE, which form the 3D position embed-dings under the local camera-view coordinate system instead of the global coordinate system, such that3D position em-bedding is free of encoding camera extrinsic parameters.
- Multi-camera vehicle tracking and re-identification based on visual and spatial-temporal features54
A novel framework for multi-camera tracking, which integrates visual features, orientation prediction and temporal-spatial information of the trajectories for optimization is proposed, which achieves the first place in vehicle re-identification at the NVIDIA AI City Challenge 2019.
- ByteTrackV2: 2D and 3D Multi-Object Tracking by Associating Every Detection Box51
A complementary motion prediction strategy that incorporates the detected velocities with a Kalman filter to address the problem of abrupt motion and short-term disappearing is proposed.
- Monocular 3D Object Detection via Feature Domain Adaptation50
A novel domain adaptation based monocular 3D object detection framework named DA-3Ddet is proposed, which adapts the feature from unsound image-based pseudo-LiDAR domain to the accurate real LiDAR domain for performance boosting and introduces a context-aware foreground segmentation module.
- VLM2Scene: Self-Supervised Image-Text-LiDAR Learning with Foundation Models for Autonomous Driving Scene Understanding49
This paper introduces Region Caption Prompts to generate fine-grained language descriptions for the corresponding regions, utilizing the language foundation model, and proposes a Region Semantic Concordance Regularization, which involves a semantic-filtered region learning and a region semantic assignment strategy.
- AGO-Net: Association-Guided 3D Point Cloud Object Detection Network45
This work introduces an attention-based re-weighting module that adaptively strengthens the feature adaptation of more informative regions and achieves new state-of-the-art performance on the KITTI 3D detection benchmark in both accuracy and speed.
- 44
- Fermentation characteristics of Pixian broad bean paste in closed system of gradient steady-state temperature field43
The results indicated that the fermentation characteristics in the FG had been further improved compared with the CTF, and its flavor properties were more stable.
- SGM3D: Stereo Guided Monocular 3D Object Detection42
This paper proposes a stereo-guided monocular 3D object detection framework, dubbed SGM3D, which aligns the monocular feature to the stereo feature and exploits the network's ability of generating the cross-modal feature for accurate 3Dobject detection.
- SoccerNet 2022 Challenges Results42
The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team, and tasks (3-6) were novel, including their underlying data and annotations.
- Efficient Stereo Matching Leveraging Deep Local and Context Information42
A deep learning framework that focuses on the first and last stage of typical stereo methods: the matching cost computation and the disparity refinement, which attains near-peak accuracy both in non-occluded and occluded region and achieves competitive performance against the fast algorithms on Middlebury benchmark.
- Coarse to Fine: Domain Adaptive Crowd Counting via Adversarial Scoring Network40
A novel adversarial scoring network (ASNet) to gradually bridge the gap across domains from coarse to fine granularity, and designs a dual-discriminator strategy to adapt source domain to be close to the targets from the perspectives of both global and local feature space via adversarial learning.
- 38
- 38
- 38
- 37
- 36
- 36
- DuARE: Automatic Road Extraction with Aerial Images and Trajectory Data at Baidu Maps34
This paper presents an automatic road extraction solution named DuARE, which is designed to exploit the multimodal knowledge for underlying road extraction in a fully automatic manner and has been deployed in production at Baidu Maps since June 2021 and keeps updating the road network by 100,000 km per month.
- CLIP-GS: CLIP-Informed Gaussian Splatting for View-Consistent 3D Indoor Semantic Understanding31
CLIP-GS is presented, efficiently achieving a coherent semantic understanding of 3D indoor scenes via the proposed Semantic Attribute Compactness (SAC) and 3D Coherent Regularization (3DCR), which remarkably suppresses existing state-of-the-art approaches.
- BRD4 as a therapeutic target for nonfunctioning and growth hormone pituitary adenoma31
The findings suggest that BRD4 is a promising therapeutic target for NFPA and GHPA and the effects of BRD 4 inhibitors on PA cells in vitro and in vivo are assessed.
- 30
- DANet30
This paper proposes a multi-scale U-Net style network architecture termed DANet for radar object detection task and achieves superior performance on the radar detection task at much less computational cost, compared to previous pioneer works.
- BEVSpread: Spread Voxel Pooling for Bird's-Eye-View Representation in Vision-Based Roadside 3D Object Detection29
Instead of bringing the image features contained in a frustum point to a single BEV grid, BEVSpread considers each frustum point as a source and spreads the image features to the surrounding BEV grids with adaptive weights to achieve superior prop- agation performance.
- 24
- 24
- 23
- The devil is in the face: Exploiting harmonious representations for facial expression recognition21
A novel Harmonious Representation Learning (HRL) model is formulated for joint learning of landmark-guided graph message propagation, and spatially invariant feature learning using only generic matching metrics.
- 21
- SOOD++: Leveraging Unlabeled Data to Boost Oriented Object Detection20
This paper proposes a simple yet effective Semi-supervised Oriented Object Detection method termed SOOD++ and demonstrates stable generalization ability across different oriented detectors, even for multi-view oriented 3D object detectors.
- Multi-Dimensional Residual Dense Attention Network for Stereo Matching19
An end-to-end multi-dimensional residual dense attention network (MRDA-Net) is proposed, focusing on more comprehensive pixel-wise feature extraction, and achieves the state-of-the-art accuracy on Scene Flow dataset and KITTI 2012 and KittI 2015 Stereo datasets.
- Exploring the Causality of End-to-End Autonomous Driving18
This work is the first to unveil the mystery of end-to-end autonomous driving and turn the black box into a white one by developing a strong baseline and a tool for exploring causality in the close-loop simulator CARLA.
- Multi-Modal 3D Object Detection by Box Matching16
A novel Fusion network by Box Matching (FBMNet) for multi-modal 3D detection is proposed, which provides an alternative way for cross-modal feature alignment by learning the correspondence at the bounding box level to free up the dependency of calibration during inference.
- 16
- Paint and Distill16
This work proposes a novel semantic passing framework, named SPNet, to boost the performance of existing lidar-based 3D detection models with the guidance of rich context painting, with no extra computation cost during inference.
- 16
- 16
- 15
- Characterization of volatile compounds of Pixian Douban fermented in closed system of gradient steady‐state temperature field15
It is indicated that the closed system of GSTF could be applied in PXDB fermentation to obtain higher quality products, which brought a bright prospect of replacing the traditional fermentation process to realize the controllable industrialized production of PX DB.
- 14
- 14
- 14
- 14
- 14
- Multi-arm covariate-adaptive randomization13
This paper proposes a general framework for multi-arm covariate-adaptive designs which also includes the two-arm case, and establishes the corresponding theory under widely satisfied conditions.
- Learning Multiple Probabilistic Decisions from Latent World Model in Autonomous Driving12
LatentDriver, a framework models the environment's next states and the ego vehicle's possible actions as a mixture distribution, from which a deterministic control signal is then derived, and achieves expert-level performance on the recently released closed-loop benchmark Waymax.
- 12
- Estimation of an unbalanced panel data Tobit model with interactive effects12
An unbalanced panel data Tobit model with interactive effects is considered, and an estimator based on the iteration of Tobit factor analysis and maximum likelihood estimation is provided.
- 10
- 10
- carat : An R Package for Covariate-Adaptive Randomization in Clinical Trials9
The R package carat facilitates a broad range of covariate-adaptive randomization and testing procedures, such as the most common and classical methods, and also reflects recent developments in the field.
- Modify Self-Attention via Skeleton Decomposition for Effective Point Cloud Transformer9
This paper proposes a novel skeleton decomposition-based self-attention (SD-SA) which has no sequence length limit and exhibits favorable scalability in long-sequence models and significantly improves the efficiency of the point cloud transformer and exceeds other efficient transformers on point cloud tasks in terms of the speed at comparable performance.
- 9
- AggNet for Self-supervised Monocular Depth Estimation: Go An Aggressive Step Furthe8
The AggNet framework is based on a training-only progressive two-stage module to perform pseudo counter-surveillance as well as a simple yet effective dual-warp loss function between image pairs to encourage the MDE network to keep depth consistency between stereo image pairs.
- 8
- 8
- U-ViLAR: Uncertainty-Aware Visual Localization for Autonomous Driving via Differentiable Association and Registration7
U-ViLAR is proposed, a novel uncertainty-aware visual localization framework designed to address challenges of accurate localization using visual information while enabling adaptive localization using high-definition (HD) maps or navigation maps.
- SemFlow: Semantic-Driven Interpolation for Large Displacement Optical Flow7
This paper presents a semantic-guided interpolation scheme (SemFlow) to handle motion boundaries and occlusions in large displacement optical flow, and puts forward a homography estimation model weighted by the distance between each superpixel and its $K$ -nearest neighbors.
- UniLION: Towards Unified Autonomous Driving Model with Linear Group RNNs5
A unified autonomous driving model, UniLION, which efficiently handles large-scale LiDAR point clouds, high-resolution multi-view images, and even temporal sequences based on the linear group RNN operator (i.e., performs linear RNN for grouped features).
- 5
- 5
- Effect of the Visual Landscape and Soundscape Factors on Attention Restoration in the Public Space of Old Residential Areas by VR5
The results showed that the attention restoration benefits of the central square in the old residential area were better than those of the public space along the street, and greenery satisfaction, environmental cleanliness, architectural aesthetics, sky visibility, and soundscape evaluation are all significantly positively correlated with the attention Restoration level.
- 4
- Lifting the Veil of Frequency in Joint Segmentation and Depth Estimation4
A Frequency Aware Feature Enhancement (FAFE) network that can effectively enhance the reciprocal relationship whereas avoiding the competition is proposed, and a novel local-aware consistency loss function is proposed to impose on the predicted segmentation and depth so as to strengthen the cooperation.
- 4
- Three-dimensional panel data models with interactive effects: Estimation and simulation4
An iterated OLS (IOLS) approach for the estimation of the static model and an iterated GMM (IGMM) method for the dynamic model are proposed for three-dimensional panel data models with unobservable multiple interactive effects, which are potentially correlated with the covariates.
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- Repainting and Imitating Learning for Lane Detection2
This paper proposes a novel Repainting and Imitating Learning (RIL) framework containing a pair of teacher and student without any extra data or extra laborious labeling to find an enhanced feature space where the lane features are distinctive while maintaining a similar distribution of lanes in the wild.
- Detaching and Boosting: Dual Engine for Scale-Invariant Self-Supervised Monocular Depth Estimation2
A scale-invariant approach for self-supervised MDE is presented, in which scale-sensitive features (SSFs) are detached away while scale- Invariant features (SIFs) are boosted further, making the model robust to scale changes.
- 2
- 2
- Weakly Supervised Deep Depth Prediction Leveraging Ground Control Points for Guidance2
This work proposes a novel weakly supervised approach, namely, the Guided-Net, by incorporating robust ground control points for guidance, which achieves results comparable to those of the semisupervised and supervised frameworks.
- 2
- 2
- Explore the LiDAR-Camera Dynamic Adjustment Fusion for 3D Object Detection1
This paper introduces a dynamic adjustment technology aimed at aligning modal distributions and learning effective modality representations to enhance the fusion process, and proposes a triphase domain aligning module.
- MRI radiomics and clinical feature model for predicting postoperative functional outcome of lumbar disc herniation: a multicenter retrospective study1
A combined model integrating preoperative MRI radiomics and clinical parameters was developed and demonstrated excellent performance in predicting postoperative functional outcomes and strong generalizability across centers.
- 1
- 1
- Feature Ensemble Network with Occlusion Disambiguation for Accurate Patch-Based Stereo Matching1
This letter presents a novel stereo matching method, consisting of leveraging feature ensemble network to compute matching cost, error detection network to predict outliers and priority-based occlusion disambiguation for refinement, which yields competitive results against the state-of-the-art algorithms.
- Estimating three-dimensional nonlinear panel data models with interactive effects1
A Nonlinear Least Squares-Principal Component Analysis-Grid Search iterated approach to estimate the static model, and a GMM-PCA-GS iterated method to the dynamic model are proposed.
- 1
- 1
- 1
- –
- –
- Guiding significance of the autophagy intensity of lumbar intervertebral discs and the Charlson Comorbidity Index in predicting the postoperative curative effect of patients with single-level lumbar disc herniation–
It was found that only CCI classification was an independent risk factor for the difference in postoperative improvement in patients with single-level lumbar discectomy, and patients with a CCI ≥ 2 were more likely to have a poor postoperative improvement rate.
- –
- –
- –
- –
- –
- Analysis and countermeasures of various alarm in hemodialysis–
Through the summary and training of all kinds of alarm in the dialysis process, it can effectively reduce the alarm frequency of the dialsis process, improve the work efficiency of nurses, and improve the satisfaction degree of patients.
- Analysis on Demography Character of Sleep Quality Among 424 Hemodialysis Patients–
The sleep quality could be influenced by age, economic income, education background and occuation, and it is suggested that effective management strategies should be relieve the quality of patients.
- An analysis on drug resistance of 108 staphylococcus aureus strains–
M methieillin-sensitive Staphylococcus aureus have good sensitivity for most of the antibiotics in addition to penicillin, and methicillin-resistant StaphyllococcusAureus detection rate is still high and more for multi-drug resistance.
- Detection of the internal arteriovenous fistulas in maintenance hemodialysis patients–
AVF detection plays an important role in the monitor of AVF function in hemodialysis patients as to explore the recirculation, blood flow and cardiac output of the internal AVF and provide basis for the he modialysis project.
- Health promoting behaviors and its related factors of maintenance hemodialysis patients–
Better health promoting behaviours are found among the MHD patients with high self-efficacy of health behaviours, better perceived health status and more social support.
- –
- –
- Modeling and Control Technology in Power Monitor System Base on Java 3D–
The class structure and key function for 3D power monitor system was given and JAVA 3D technology may draw out a new model for monitoring system development.
- –
- –
- –
- An Analysis on Failure of Qing Terminal New Deal from the Reason of Corruption of the Administration of Officials–
Aiming at rejuvenation, the new policy of late Qing dynasty carried out reformation itself, but it was impossible to vitalize the decayed system by infusing fresh blood to it, and it will lead to the death of thedecayed system at last with more and more severe corruption.
- Evaluation for the Lectures of Family Nursing Health Education–
The hospital should develop nursing health education according to the clients' needs, so as to provide evidence to develop health education in hospital.
- –
- –
- Analyses for investigation about the clinical nurses' knowledge degree about the diabetes–
The clinical nurses haven't mastered all the knowledge of the diabetes well, they only know one aspect of it and don't do well in the knowledge about diabetes complication, medical treatment and blood sugar examination.
- [Medical devices' management and medical safety].–
This article presents some suggestions about how to strengthen the management of medical devices so as to remove the hidden perils and risks of medical safety.
- –
- [Cardiopulmonary bypass of orthotopic heart transplantation].–
Proper ECC management, importment organs and donor heart protection are the key to success in heart transplant operations.
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.