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
- Guosheng LinSuggested from co-authorship
- Chunhua ShenSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works26 from public data
- 69
- Self-Point-Flow: Self-Supervised Scene Flow Estimation from Point Clouds with Optimal Transport and Random Walk67
This paper designs the transport cost by considering multiple descriptors and encourage one-to-one matching by mass equality constraints and achieves state-of-the-art performance among self-supervised learning methods.
- HCRF-Flow: Scene Flow from Point Clouds with Continuous High-order CRFs and Position-aware Flow Embedding63
A high-order CRFs based relation module (Con-HCRFs) is deployed to explore both point-wise smoothness and region-wise rigidity, and a position-aware flow estimation module is introduced to empower the CRFs to have a discriminative unary term.
- Meta Navigator: Search for a Good Adaptation Policy for Few-shot Learning54
Inspired by the recent success in Automated Machine Learning literature, this paper presents Meta Navigator, a framework that attempts to solve the aforementioned limitation in few-shot learning by seeking a higher-level strategy and proffer to automate the selection from various few- shot learning designs.
- Efficient Few-Shot Object Detection via Knowledge Inheritance53
This work presents an efficient pretrain-transfer framework (PTF) baseline with no computational increment, which achieves comparable results with previous state-of-the-art (SOTA) methods and devise an initializer named knowledge inheritance (KI) to reliably initialize the novel weights for the box classifier, which effectively facilitates the knowledge transfer process and boosts the adaptation speed.
- 39
- Unsupervised 3D Pose Transfer With Cross Consistency and Dual Reconstruction31
This work proposes a cross consistency learning scheme and a dual reconstruction objective to learn the pose transfer without supervision and adopts an as-rigid-as-possible deformer in the training process to fine-tune the body shape of the generated results.
- 30
- Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator25
This study shows that, under recent distillation paradigms (e.g., shared-context distillation), normalization is not always necessary, as omitting it can help mitigate the impact of noisy supervision, and proposes Cross-Context Distillation, which integrates both global and local depth cues to enhance pseudo-label quality.
- TacoDepth: Towards Efficient Radar-Camera Depth Estimation with One-stage Fusion17
TacoDepth is proposed, an efficient and accurate Radar-Camera depth estimation model with one-stage fusion designed to capture and integrate the graph structures of Radar point clouds, delivering superior model efficiency and robustness without relying on the intermediate depth results.
- 15
- 12
- 11
- 10
- 8
- 8
- Self-Supervised 3D Scene Flow Estimation and Motion Prediction Using Local Rigidity Prior6
This article proposes to generate pseudo scene flow labels for self-supervised learning through piecewise rigid motion estimation, in which the source point cloud is decomposed into local regions and each region is treated as rigid.
- 5
- Collaborative Propagation on Multiple Instance Graphs for 3D Instance Segmentation with Single-point Supervision5
A Cross-graph Competing Random Walks (CRW) algorithm that encourages competition among different instance graphs to resolve ambiguities in closely placed objects, improving instance assignment accuracy.
- 3
- Hierarchical optimization method for a class of nonlinear bilevel programming problems2
A novel method that can finally solve the optimal solution of the bilevel programming problem in an iterative fashion based on decomposition-coordination principle is proposed.
- Synthetic-to-Real Translation for Class-Agnostic Motion Prediction1
This work proposes a novel approach integrating a motion knowledge translation framework with two key components: 1) objectness-aware motion prediction, which explicitly models the joint distribution of motion patterns and objectness priors to improve domain-invariant feature learning, and 2) objectness-aided motion enhancement, a motion label refinement mechanism that leverages learned objectness priors to filter motion noise.
- 1
- –
- –
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-11. 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. You will be asked to sign in.