Tat‐Jen Cham lists you as their PhD student. Claim this profile to confirm it and keep the rest of your record right.
Claim this profileAcademic lineage
Traced back 11 generations →Advisors
Works74 from public data
- 929
- 530
- Weakly-Supervised 3D Hand Pose Estimation from Monocular RGB Images319
A weakly-supervised method, adaptating from fully-annotated synthetic dataset toWeakly-labeled real-world dataset with the aid of a depth regularizer, which generates depth maps from predicted 3D pose and serves as weak supervision for3D pose regression.
- 311
- Mixup for Node and Graph Classification243
The two-stage Mixup framework is proposed, which uses each node’s neighbors’ representations before Mixup for graph convolutions, which effectively regularizes popular graph neural networks for better generalization without increasing their time complexity.
- 199
- DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learning191
The extensive experiments validate the effectiveness of the EMD algorithm which outperforms state-of-the-art methods by a significant margin on five widely used few-shot classification benchmarks, namely, miniImage net, tieredImageNet, Fewshot-CIFAR100 (FC100), Caltech-UCSD Birds-200-2011 (CUB), and CIFAR-FewShot (CIFar-FS).
- NodeAug: Semi-Supervised Node Classification with Data Augmentation160
The NodeAug (Node-Parallel Augmentation) scheme, that creates a 'parallel universe' for each node to conduct DA, to block the undesired effects from other nodes, yields significant gains for strong GCN models on the Cora, Citeseer, Pubmed, and two co-authorship networks, with a more efficient training process thanks to the proposed subgraph mini-batch training approach.
- Effects of Acute and Chronic Exercises on Executive Function in Children and Adolescents: A Systemic Review and Meta-Analysis146
Acute and chronic exercises can effectively improve the executive function of children and adolescents, and the effects on inhibitory control and cognitive flexibility are considered as moderate effect size.
- UmeTrack: Unified multi-view end-to-end hand tracking for VR102
This paper presents a unified end-to-end differentiable framework for multi-view, multi-frame hand tracking that directly predicts 3D hand pose in world space and presents a new large-scale egocentric hand pose dataset that consists of both real and synthetic data.
- 87
- 80
- 69
- 67
- Results from the China 2018 Report Card on physical activity for children and youth66
Recently regional and national surveillance data show that only a few Chinese young people meet the guideline of at least 60min of MVPA daily and over three quarters of them have more than 2 h SB time.
- CurGraph: Curriculum Learning for Graph Classification65
This work argues that GNNs can benefit from an easy-to-difficult curriculum, similar to the learning process of humans, and presents the CurGraph (Curriculum Learning for Graph Classification) framework, that analyzes the graph difficulty in the high-level semantic feature space.
- Geometry-Guided Progressive NeRF for Generalizable and Efficient Neural Human Rendering61
To better tackle self-occlusion, a geometry-guided multi-view feature integration approach that utilizes the estimated geometry prior to integrate the incomplete information from input views and construct a complete geometry volume for the target human body is devised.
- LLMs are Good Action Recognizers60
This work proposes a novel LLM-AR framework, in which it in-vestigate treating the Large Language Model as an Action Recognizer, and proposes a linguistic pro-jection process to project each input action signal into its “sentence format”.
- Results from the China 2022 report card on physical activity for children and adolescents59
Levels of PA among Chinese youth were low and most young people were below the recommended guidelines, although the grade of Overall PA has been improved since the modified benchmark.
- 6D-Diff: A Keypoint Diffusion Framework for 6D Object Pose Estimation42
This work proposes a novel diffusion-based framework (6D-Diff) to handle the noise and indeterminacy in object pose estimation for better performance, and designs a Mixture-of-Cauchy-based forward diffusion process and condition the reverse process on the object appearance features.
- 29
- 27
- 24
- LMC: Large Model Collaboration with Cross-assessment for Training-Free Open-Set Object Recognition23
This paper proposes a novel framework named Large Model Collaboration (LMC) to tackle the above challenge via collaborating different off-the-shelf large models in a training-free manner and incorporates the proposed framework with several novel designs to effectively extract implicit knowledge from large models.
- 21
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 2026-10-13. 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.