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
- Xiaogang WangSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works54 from public data
- 1,350
- Finding Task-Relevant Features for Few-Shot Learning by Category Traversal400
A Category Traversal Module is introduced that can be inserted as a plug-and-play module into most metric-learning based few-shot learners, identifying task-relevant features based on both intra-class commonality and inter-class uniqueness in the feature space.
- 229
- Inner and Inter Label Propagation: Salient Object Detection in the Wild197
A co-transduction algorithm is devised to fuse both boundary and objectness labels based on an inter propagation scheme, which achieves superior performance compared with the newest state-of-the-arts in terms of different evaluation metrics.
- 177
- Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation158
This work argues that the image features extracted at a central point contain limited information for predicting distant keypoints or bounding box boundaries, due to object deformation and scale/orientation variation, and proposes to perform regression from a set of points placed at more advantageous positions to facilitate inference.
- Lite DETR : An Interleaved Multi-Scale Encoder for Efficient DETR154
Lite DETR is presented, a simple yet efficient end-to-end object detection framework that can effectively reduce the GFLOPs of the detection head by 60% while keeping 99% of the original performance, and the efficient encoder strategy can generalize well across existing DETR-based models.
- Visual Point Cloud Forecasting Enables Scalable Autonomous Driving142
ViDAR is presented, a general model to pre-train downstream visual encoders that captures the synergic learning of semantics, 3D structures, and temporal dynamics and shows superiority in various downstream tasks.
- Monocular 3D Object Detection: An Extrinsic Parameter Free Approach129
A novel method to capture camera pose to formulate the detector free from extrinsic perturbation is proposed and yields the best performance compared with the other state-of-the-arts by a large margin on both KITTI 3D and nuScenes datasets.
- 102
- CNN for saliency detection with low-level feature integration96
A novel deep neural network framework embedded with low-level features (LCNN) for salient object detection in complex images proposed for complex images by utilising the advantage of convolutional neural networks to automatically learn the high- level features that capture the structured information and semantic context in the image.
- Recurrent Scale Approximation for Object Detection in CNN92
This work designs a scale-forecast network to globally predict potential scales in the image since there is no need to compute maps on all levels of the pyramid and proposes a landmark retracing network (LRN) to retrace back locations of the regressed landmarks and generate a confidence score for each landmark.
- Fully Sparse 3D Occupancy Prediction89
A novel fully sparse occupancy network, termed SparseOcc, which initially reconstructs a sparse 3D representation from camera-only inputs and subsequently predicts semantic/instance occupancy from the 3D sparse representation by sparse queries, and a thoughtful ray-based evaluation metric, namely RayIoU, to solve the inconsistency penalty along the depth axis raised in traditional voxel-level mIoU criteria.
- SOGNet: Scene Overlap Graph Network for Panoptic Segmentation65
This study aims to model overlap relations among instances and resolve them for panoptic segmentation, Inspired by scene graph representation, and forms the overlapping problem as a simplified case, named scene overlap graph.
- Neural Network Encapsulation54
The proposed EncapNet performs favorably better against previous state-of-the-arts on CIFAR10/100, SVHN and a subset of ImageNet and an add-on to send back higher capsules as feedback is devised, achieving the optimal transport divergence between two distributions.
- Towards Improving the Consistency, Efficiency, and Flexibility of Differentiable Neural Architecture Search52
This paper introduces EnTranNAS that is composed of Engine-cells and Transit-cells, and develops an architecture derivation method to replace the traditional one that is based on a hand-crafted rule, which enables differentiable sparsification, and keeps the derived architecture equivalent to that of engines, which further improves the consistency between search and evaluation.
- 46
- 45
- 45
- 36
- Open-sourced Data Ecosystem in Autonomous Driving: the Present and Future35
This comprehensive review, conducted in collaboration with esteemed colleagues from both academia and industry, systematically assesses over seventy open-source autonomous driving datasets from domestic and international sources and offers insights into various aspects, such as the principles underlying the creation of high-quality datasets.
- Mimic before Reconstruct: Enhancing Masked Autoencoders with Feature Mimicking35
Mimic before Reconstruct for Masked Autoencoders is proposed, named as MR-MAE, which jointly learns high-level and low-level representations without interference during pre-training, and achieves high-level and low-level accuracy on ImageNet-1K.
- 30
- 23
- SceneMaker: Open-set 3D Scene Generation with Decoupled De-occlusion and Pose Estimation Model21
This work decouple the de-occlusion model from 3D object generation, and enhance it by leveraging image datasets and collected de-occlusion datasets for much more diverse open-set occlusion patterns.
- 20
- Sparse Dense Fusion for 3D Object Detection17
This work introduces Sparse Dense Fusion (SD-Fusion), an innovative framework combining both sparse and dense fusion modules via the Transformer architecture, which enhances semantic texture and simultaneously leverages spatial structure data in 3D object detection.
- Decoupled Diffusion Sparks Adaptive Scene Generation16
Nexus is introduced, a decoupled scene generation framework that improves reactivity and goal conditioning by simulating both ordinary and challenging scenarios from fine-grained tokens with independent noise states that achieves superior generation realism while preserving reactivity and goal orientation with a 40 % reduction in displacement error.
- 16
- SCMEA: A stacked co-enhanced model for entity alignment based on multi-aspect information fusion and bidirectional contrastive learning15
This paper suggests SCMEA, a novel cross-lingual entity alignment framework based on multi-aspect information fusion and bidirectional contrastive learning, and proposes a stacked relation-entity co-enhanced model to further improve the representations of entities.
- 15
- Introducing Depth into Transformer-based 3D Object Detection13
This paper presents DA-BEV, an implicit depth learning method for Transformer-based camera-only 3D object detection in bird’s eye view (BEV), and introduces an auxiliary learning task, called Depth-wise Contrastive Learning (DCL), to improve the BEV representation and make it more depth-aware.
- 13
- 11
- TAPTRv3: Spatial and Temporal Context Foster Robust Tracking of Any Point in Long Video9
TAPTRv3 improves TAPTRv2 by addressing its shortcomings in querying high-quality features from long videos, and introduces Visibility-aware Long-Temporal Attention (VLTA), which conducts temporal attention over past frames while considering their corresponding visibilities.
- 9
- 8
- FB-4D: Spatial-Temporal Coherent Dynamic 3D Content Generation with Feature Banks7
FB-4D, a novel 4D generation framework that integrates a Feature Bank mechanism to enhance both spatial and temporal consistency in generated frames, surpasses all multi-view generation tuning-free approaches by a large margin and achieves performance on par with training-based methods.
- 7
- A multimodal deep-learning model based on multichannel CT radiomics for predicting pathological grade of bladder cancer7
The CT-based combined model demonstrated considerable diagnostic capability in differentiating high-grade from low-grade bladder cancer, serving as a valuable noninvasive instrument for preoperative pathological evaluation.
- Global Contrast Based Salient Region Boundary Sampling for Action Recognition7
The iDT method is improved by advancing a novel salient region boundary based dense sampling strategy, which reduces the number of trajectories while preserves the discriminative power, and can improve the performance of action recognition with minor computational cost of mask production.
- 6
- OVSeg3R: Learn Open-vocabulary Instance Segmentation from 2D via 3D Reconstruction5
2D Instance Boundary-aware Superpoint is introduced, which leverages 2D masks to constrain the superpoint clustering, preventing superpoints from violating instance boundaries.
- 4
- Fuzzy Logic-Based Filter for Removing Additive and Impulsive Noise from Color Images4
Experimental results on several color images proves the efficacy of the proposed fuzzy filter, including noise detection and noise removal filtering.
- Compressed-Domain Based Camera Motion Estimation for Realtime Action Recognition3
This paper advances an efficient camera motion estimation and compensation method for realtime action recognition by exploiting motion vectors in video compressed-domain by taking advantage of geometric symmetry and differential theory of motion vectors.
- 2
- 1
- 1
- 1
- 1
- 1
- –
- –
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-15. 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.