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
- Gim Hee LeeSuggested from co-authorship
- Tat‐Seng ChuaSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works38 from public data
- Few-shot 3D Point Cloud Semantic Segmentation164
This work proposes a novel attention-aware multi-prototype transductive few-shot point cloud semantic segmentation method to segment new classes given a few labeled examples, and designs an attention- aware multi-level feature learning network to learn the discriminative features that capture the geometric dependencies and semantic correlations between points.
- SESS: Self-Ensembling Semi-Supervised 3D Object Detection157
This work designs a thorough perturbation scheme to enhance generalization of the network on unlabeled and new unseen data and proposes three consistency losses to enforce the consistency between two sets of predicted 3D object proposals, to facilitate the learning of structure and semantic invariances of objects.
- 96
- 77
- Style-Hallucinated Dual Consistency Learning: A Unified Framework for Visual Domain Generalization67
A unified framework to handle domain shift in various visual recognition tasks, constructed based on two consistency constraints, Style Consistency and Retrospection Consistency, and a novel style hallucination module (SHM) to generate style-diversified samples that are essential to consistency learning.
- 47
- Teaching with Soft Label Smoothing for Mitigating Noisy Labels in Facial Expressions45
This work introduces what it calls the Smooth Operator Framework for Teaching (SOFT), based on a mean-teacher architecture where SLS is applied over the teacher’s logits, and finds that the smoothed teacher’s logit provides a beneficial supervision to the student via a consistency loss.
- 33
- Static-Dynamic Co-teaching for Class-Incremental 3D Object Detection30
This paper studies the unexplored yet important class-incremental 3D object detection problem and presents the first solution - SDCoT, a novel static-dynamic co-teaching method that alleviates the catastrophic forgetting of old classes via a static teacher and regularizes the current model by extracting previous knowledge with a distillation loss.
- 28
- Discrete Image Hashing Using Large Weakly Annotated Photo Collections27
This work formulate a novel hashing objective that can effectively mine implicit weak supervision by collaborative filtering and proposes a discrete hashing algorithm, offered with efficient optimization, to overcome the inferior optimizations in obtaining binary codes from real-valued solutions.
- Generalized Few-Shot Point Cloud Segmentation Via Geometric Words20
This work proposes the geometric words to represent geometric components shared between the base and novel classes, and incorporates them into a novel geometric-aware semantic representation to facilitate better generalization to the new classes without forgetting the old ones.
- Look Before You Decide: Prompting Active Deduction of MLLMs for Assumptive Reasoning16
This paper curates a Multimodal Assumptive Assumptive Reas oning Benchmark (MARS-Bench) and finds that most prevalent MLLMs can be easily fooled by the introduction of a presupposition into the question, whereas such presuppositions appear naive to human reasoning.
- CT3D++: Improving 3D Object Detection with Keypoint-Induced Channel-wise Transformer13
This paper presents an enhanced network called CT3D++, which incorporates geometric and semantic fusion-based embedding to extract more valuable and comprehensive proposal-aware information and achieves state-of-the-art performance on both the KITTI dataset and the large-scale Waymo Open Dataset.
- On-the-fly Point Feature Representation for Point Clouds Analysis13
This paper proposes On-the-fly Point Feature Representation (OPFR), which captures abundant geometric information explicitly through Curve Feature Generator module, and introduces the novel Hierarchical Sampling module aimed at enhancing the quality of triangle sets, thereby ensuring robustness of the obtained geometric features.
- Learning content–social influential features for influence analysis12
A novel method to deeply learn the unified feature representations for both user pair and content, where the homogeneous feature similarity can be used to estimate the propagation probability between users with given content.
- 11
- Tuning-Free Long Video Generation via Global-Local Collaborative Diffusion10
Global-Local Collaborative Diffusion (GLC-Diffusion), a tuning-free method for long video generation, models the long video denoising process by establishing denoising trajectories through Global-Local Collaborative Denoising (GLCD) to ensure overall content consistency and temporal coherence between frames.
- Uncertainty Meets Diversity: A Comprehensive Active Learning Framework for Indoor 3D Object Detection10
This paper presents the first study on active learning for indoor 3D object detection, where a novel framework tailored for this task is proposed, and incorporates two key criteria - uncertainty and diversity - to actively select the most ambiguous and informative unlabeled samples for annotation.
- 10
- 9
- End2End Semantic Segmentation for 3D Indoor Scenes8
This paper aims to model the local and global geometric structures of 3D scenes by designing an end-to-end 3D semantic segmentation framework that captures the local geometries from point-level feature learning and voxel-level aggregation, models the global structures via 3D CNN, and enforces label consistency with high-order CRF.
- Syn-to-Real Unsupervised Domain Adaptation for Indoor 3D Object Detection5
A novel Object-wise Hierarchical Domain Alignment (OHDA) framework for syn-to-real unsupervised domain adaptation in indoor 3D object detection and introduces a two-branch adaptation framework consisting of an adversarial training branch and a pseudo labeling branch in order to simultaneously reach holistic-level and class-level domain alignment.
- Refining 6-DoF Grasps with Context-Specific Classifiers4
This work formulate the problem of grasp synthesis as a sampling problem: it seeks to sample from a context-conditioned probability distribution of successful grasps, and devise a discriminator gradient-flow method to evolvegrasps obtained from a simpler distribution in a manner that mimics sampling from the desired target distribution.
- PS2-Net: A Locally and Globally Aware Network for Point-Based Semantic Segmentation4
This paper presents the PS2-Net - a locally and globally aware deep learning framework for semantic segmentation on 3D scene-level point clouds designed to be permutation invariant, which is an essential property of any deep network used to process unordered point clouds.
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.