Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Suggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works72 from public data
- TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers1,106
The proposed TransFusion, a robust solution to LiDAR-camera fusion with a soft-association mechanism to handle inferior image conditions, achieves state-of-the-art performance on large-scale datasets and is extended to the 3D tracking task.
- FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection854
The solution achieves 1st place out of all the vision-only methods in the nuScenes 3D detection challenge of NeurIPS 2020 and proposes a general framework FCOS3D, getting rid of any 2D detection or 2D-3D correspondence priors.
- Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation756
A new framework for the outdoor LiDAR segmentation is proposed, where cylindrical partition and asymmetrical 3D convolution networks are designed to explore the 3D geometric pattern while maintaining these inherent properties.
- TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents470
The proposed long short-term memory-based (LSTM-based) realtime traffic prediction algorithm, TrafficPredict, uses an instance layer to learn instances' movements and interactions and has a category layer to learning the similarities of instances belonging to the same type to refine the prediction.
- 386
- CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP273
A Semantic-driven Cross-modal Contrastive Learning framework that pre-trains a 3D network via semantic and spatial-temporal consistency regularization, which significantly outperforms other self-supervised methods and demonstrates the generalizability for handling cross-domain datasets.
- Depth Completion From Sparse LiDAR Data With Depth-Normal Constraints259
A unified CNN framework is proposed that models the geometric constraints between depth and surface normal in a diffusion module and predicts the confidence of sparse LiDAR measurements to mitigate the impact of noise.
- Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation256
This article addresses the problem of distilling knowledge from a large teacher model to a slim student network for LiDAR semantic segmentation by proposing the Point-to-Voxel Knowledge Distillation (PVD), which transfers the hidden knowledge from both point level and voxel level.
- Vision-Centric BEV Perception: A Survey245
This paper provides in-depth analyses and comparative results on various BEV perception tasks, facilitating the evaluation of future works and sparking new research directions, and discusses and shares valuable empirical implementation details to aid in the advancement of related algorithms.
- Rethinking Range View Representation for LiDAR Segmentation220
A range view method is able to surpass the point, voxel, and multi-view fusion counterparts in the competing LiDAR semantic and panoptic segmentation benchmarks, i.e., SemanticKITTI, nuScenes, and ScribbleKITTI.
- Pose Guided Human Video Generation163
A pose guided method to synthesize human videos in a disentangled way: plausible motion prediction and coherent appearance generation and enforce semantic consistency between the generated and ground-truth poses at a high feature level.
- LIF-Seg: LiDAR and Camera Image Fusion for 3D LiDAR Semantic Segmentation146
A coarse-to-fine LiDAR and camera fusion-based network, named LIF-Seg, for LiDAR segmentation, which introduces a simple but effective early-fusion strategy to fully utilize the contextual information of images and can effectively address the weak spatiotemporal synchronization problem.
- Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-Based Perception145
This paper proposes a new framework for the outdoor LiDAR segmentation, where cylindrical partition and asymmetrical 3D convolution networks are designed to explore the 3D geometric pattern while maintaining these inherent properties.
- SSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds142
A novel 3D shape signature is proposed to explore the shape information from point clouds and is not only compact and effective but also robust to the noise, which serves as a soft constraint to improve the feature capability of multi-class discrimination.
- SCPNet: Semantic Scene Completion on Point Cloud135
A novel knowledge distillation objective is designed, dubbed Dense-to-Sparse Knowledge Distillation (DSKD), which transfers the dense, relation-based semantic knowledge from the multi-frame teacher to the single-frame student, significantly improving the representation learning of thesingle-frame model.
- Dependency Exploitation: A Unified CNN-RNN Approach for Visual Emotion Recognition135
This paper proposes a unified CNNRNN model to predict the emotion based on the fused features from different levels by exploiting the dependency among them and leverages convolutional neural network with multiple layers to extract different levels of features within a multi-task learning framework.
- 127
- LiDAR-based Panoptic Segmentation via Dynamic Shifting Network121
This work proposes the Dynamic Shifting Network (DS-Net), which serves as an effective panoptic segmentation framework in the point cloud realm and presents an efficient learnable clustering module, dynamic shifting, which adapts kernel functions on-the-fly for different instances.
- GANet: Goal Area Network for Motion Forecasting117
A new goal area-based framework, named Goal Area Network (GANet), for motion forecasting, which models goal areas as preconditions for trajectory prediction, performing more robustly and accurately.
- UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebase113
A unified multi-modal LiDAR segmentation network, termed UniSeg, is presented, which leverages the information of RGB images and three views of the point cloud, and accomplishes semantic segmentation and panoptic segmentation simultaneously.
- Penalizing Top Performers: Conservative Loss for Semantic Segmentation Adaptation107
This work proposes a novel loss function, i.e., Conservative Loss, which penalizes the extreme good and bad cases while encouraging the moderate examples and enables the network to learn features that are discriminative by gradient descent and are invariant to the change of domains via gradient ascend method.
- 89
- AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching88
This work presents a novel domain-adaptive pipeline called AdaStereo that aims to align multi-level representations for deep stereo matching networks, and proposes a non-adversarial progressive color transfer algorithm for input image-level alignment.
- Tensor Low-Rank Reconstruction for Semantic Segmentation76
This paper proposes a new approach to model the 3D context representations, which not only avoids the space compression but also tackles the high-rank difficulty, and achieves state-of-the-art on various public datasets.
- 70
- STCrowd: A Multimodal Dataset for Pedestrian Perception in Crowded Scenes67
A novel method, Density-aware Hierarchical heatmap Aggregation (DHA), to enhance pedestrian perception in crowded scenes is proposed and achieves state-of-the-art performance for pedestrian detection on various datasets.
- Generative Adversarial Frontal View to Bird View Synthesis60
The BridgeGAN, a novel generative model for bird view synthesis, is proposed, which is much better than those generated by existing methods, with more consistent global appearance and sharper details.
- 47
- Efficient Point Cloud Analysis Using Hilbert Curve45
This work proposes the HilbertNet to maintain the locality advantage of voxel-based methods while significantly reducing the computational cost, and achieves state-of-the-art performance on ShapeNet, ModelNet40 and S3DIS datasets with smaller cost and GPU occupation.
- Human-centric Scene Understanding for 3D Large-scale Scenarios38
This paper presents a large-scale multi-modal dataset for human-centric scene under-standing, dubbed HuCenLife, which is collected in diverse daily-life scenarios with rich and fine-grained annotations and designs novel modules for LiDAR-based segmentation and action recognition.
- MV-FCOS3D++: Multi-View Camera-Only 4D Object Detection with Pretrained Monocular Backbones37
This solution is built upon a simple monocular detector FCOS3D++, pretrained only with object annotations of Waymo, and converts multi-view features to a 3D grid space to detect 3D objects thereon, and achieves 49.75% mAPL with a single model and wins 2nd place in the WOD challenge.
- A Hierarchical CNN-RNN Approach for Visual Emotion Classification34
A hierarchical convolutional neural network-recurrent neural network approach to predict the emotion based on the fused stimuli by exploiting the dependency among different-level features is proposed.
- See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Data32
This work proposes a novel multi-modal zero-shot learning method to better utilize the complementary information of point clouds and images for more accurate visual-semantic alignment.
- SIDE: Center-based Stereo 3D Detector with Structure-aware Instance Depth Estimation32
A stereo-image based anchor-free 3D detection method, called structure-aware stereo 3D detector (termed as SIDE), where the instance-level depth information is explored via constructing the cost volume from RoIs of each object.
- Learning to Adapt SAM for Segmenting Cross-Domain Point Clouds30
This work harnesses the corresponding images associated with point clouds to facilitate knowledge transfer and proposes an innovative hybrid feature augmentation methodology, which significantly enhances the alignment between the 3D feature space and SAM's feature space, operating at both the scene and instance levels.
- 30
- TASeg: Temporal Aggregation Network for LiDAR Semantic Segmentation28
A Temporal LiDAR Aggregation and Distillation (TLAD) algorithm, which leverages historical priors to assign dif-ferent aggregation steps for different classes, and a Static-Moving Switch Augmentation (SMSA) algorithm, which utilizes sufficient temporal information to enable objects to switch their motion states freely, thus greatly increasing static and moving training samples.
- PARTNER: Level up the Polar Representation for LiDAR 3D Object Detection26
Partner alleviates the dilemma of feature distortion with global representation re-alignment and facilitates the regression by introducing instance-level geometric information into the detection head, thus achieving competitive results over the state-of-the-art methods.
- 22
- 19
- AdaStereo: An Efficient Domain-Adaptive Stereo Matching Approach17
This work presents a novel domain-adaptive approach called AdaStereo that aims to align multi-level representations for deep stereo matching networks, and proposes a non-adversarial progressive color transfer algorithm for input image-level alignment.
- AutoTrajectory: Label-Free Trajectory Extraction and Prediction from Videos Using Dynamic Points17
This paper presents a novel, label-free algorithm, AutoTrajectory, for trajectory extraction and prediction to use raw videos directly, and is believed to be the first to achieve unsupervised learning of trajectory extracted and prediction.
- LiDAR-based 4D Panoptic Segmentation via Dynamic Shifting Network13
This work addresses the task of LiDAR-based panoptic segmentation, which aims to parse both objects and scenes in a unified manner, and proposes the Dynamic Shifting Network (DS-Net), which serves as an effective panopti segmentation framework in the point cloud realm.
- High Performance Gesture Recognition via Effective and Efficient Temporal Modeling13
A simple and efficient architectural unit, Multi-Kernel Temporal Block (MKTB), that models the multi-scale temporal responses by explicitly applying different temporal kernels and a Global Refinement Block (GRB), which is an attention module for shaping the global temporal features based on the cross-channel similarity.
- 12
- Input-Output Balanced Framework for Long-Tailed Lidar Semantic Segmentation11
An input-output balanced framework to handle the issue of long-tailed distribution is proposed and a multi-head block is proposed to group different categories based on their shapes and instance amounts, which alleviates the biased representation of dominating category during the feature learning.
- 10
- 8
- 8
- 8
- MoE3D: Mixture of Experts meets Multi-Modal 3D Understanding7
This paper proposes MoE3D, which integrates Mixture of Experts (MoE) into the multi-modal learning framework, and deploys a set of specialized "expert" networks, each adept at processing a specific modality or a mode of cross-modal interaction.
- 6
- 6
- 6
- 6
- 5
- Model2Scene: Learning 3D Scene Representation via Contrastive Language-CAD Models Pre-training4
This paper proposes Model2Scene, a novel paradigm that learns free 3D scene representation from Computer-Aided Design models and languages and proposes a novel feature regularization operation, termed Deep Convex-hull Regularization (DCR), to project point features into a unified convex hull space, reducing the domain gap.
- 4
- 4
- 3
- 3
- HUMOF: Human Motion Forecasting in Interactive Social Scenes2
This paper designs a hierarchical interaction feature representation so that high-level features capture the overall context of the interactions, while low-level features focus on fine-grained details, thereby enhancing the accuracy of motion predictions.
- 2
- 1
- 1
- 1
- Rethinking Trajectory Prediction via "Team Game"1
A novel formulation for multi-agent trajectory prediction is presented, which explicitly introduces the concept of interactive group consensus via an interactive hierarchical latent space and allows group-level and individual-level interactions to be captured jointly, thus substantially improving the capability of modeling complex dynamics.
- FIFA3D: Flow-Guided Feature Aggregation for Temporal Three-Dimensional Object Detection–
A novel flow-guided feature aggregation scheme for 3D object detection (FIFA3D) to align cross-frame information and utilize multi-scale feature maps to predict flow in a coarse-to-fine manner.
- –
- –
- –
- –
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-16. 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.