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
- Peng Un MakSuggested from co-authorship
- Michael Rung-Tsong LyuSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works165 from public data
- A Scale Adaptive Kernel Correlation Filter Tracker with Feature Integration1,469
This paper presents a very appealing tracker based on the correlation filter framework and suggests an effective scale adaptive scheme to tackle the problem of the fixed template size in kernel correlation filter tracker.
- Deep Learning for Content-Based Image Retrieval941
This paper investigates a framework of deep learning with application to CBIR tasks with an extensive set of empirical studies by examining a state-of-the-art deep learning method (Convolutional Neural Networks) for CBIr tasks under varied settings.
- Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions674
A differentiable image processing (DIP) module is presented to take into account the adverse weather conditions for YOLO detector, whose parameters are predicted by a small convolutional neural network (CNN-PP).
- Oriented RepPoints for Aerial Object Detection552
This paper proposes an effective adaptive points learning approach to aerial object detection by taking advantage of the adaptive points representation, which is able to capture the geometric information of the arbitrary-oriented instances.
- Batch mode active learning and its application to medical image classification524
A framework for "batch mode active learning" that applies the Fisher information matrix to select a number of informative examples simultaneously and is more effective than the state-of-the-art algorithms for active learning.
- 356
- Osprey: Pixel Understanding with Visual Instruction Tuning212
Osprey is proposed, a mask-text instruction tuning approach, to extend MLLMs by incor-porating fine-grained mask regions into language instruction, aiming at achieving pixel-wise visual understanding.
- 190
- Semisupervised SVM batch mode active learning with applications to image retrieval182
This work proposes a novel scheme for explicitly addressing the drawbacks of conventional SVM active learning, which first learns a kernel function from a mixture of labeled and unlabeled data, and therefore alleviates the problem of small-sized training data.
- AI Coach: Deep Human Pose Estimation and Analysis for Personalized Athletic Training Assistance166
This paper proposes to create an AI coach system to provide personalized athletic training experiences with several distinct features, and shows that the proposed system can lead to a remarkably better user training experience by extensive user studies.
- 147
- 145
- 143
- SuPer: A Surgical Perception Framework for Endoscopic Tissue Manipulation With Surgical Robotics128
This letter proposes a novel surgical perception framework, SuPer, for surgical robotic control that successfully completed soft tissue manipulation tasks with high accuracy and was implemented on the da Vinci Surgical System in real-time with an end-effector controller.
- Feature agglomeration networks for single stage face detection128
A novel framework of "Feature Agglomeration Networks" (FAN) is proposed to build a new single stage face detector, which not only achieves state-of-the-art performance but also runs efficiently.
- A survey of human pose estimation: The body parts parsing based methods126
A general framework of human pose estimation is presented, and the latest technical progress on each stage is discussed, to discuss the limitations of the existing approaches and foresee the future directions to be explored.
- Near-duplicate keyframe retrieval by nonrigid image matching112
A novel and effective Nonrigid Image Matching (NIM) approach to tackle the task of near-duplicate keyframe retrieval from real-world video corpora and promising results show that the proposed method is more effective than other state-of-the-art approaches for near- DUplicateKeyframe retrieval.
- Robust Estimation of Similarity Transformation for Visual Object Tracking105
This paper proposes a novel correlation filter-based tracker with robust estimation of similarity transformation on the large displacements to tackle this challenging problem of efficiently search in such a large 4-DoF space in real-time.
- 102
- DeepFacade: A Deep Learning Approach to Facade Parsing100
This paper is the first to employ end-to-end deep convolutional neural network on full image scale in the task of building facades parsing, and pro-poses a symmetric regularizer for training the neural network.
- Distance metric learning from uncertain side information with application to automated photo tagging97
A novel probabilistic distance metric learning scheme is proposed that automatically derives constraints from the uncertain side information, and efficiently learns a distance metric from the derived constraints.
- A Spatial-Temporal QoS Prediction Approach for Time-aware Web Service Recommendation91
This work proposes a novel spatial-temporal QoS prediction approach for time-aware Web service recommendation, where a sparse representation is employed to model QoS variations, and uses the geo-location of web service to effectively select the nearest neighbor for the sparse representation of temporal QoS values.
- 90
- Improving Nighttime Driving-Scene Segmentation via Dual Image-Adaptive Learnable Filters88
DAIL-Filters can significantly improve the supervised segmentation performance on ACDC_Night and NightCity datasets, while it demonstrates the state-of-the-art performance on unsupervised nighttime semantic segmentation on Dark Zurich and Nighttime Driving testbeds.
- 81
- Attribute-Aware Pedestrian Detection in a Crowd80
An attribute-aware pedestrian detector to explicitly model people's semantic attributes in a high-level feature detection fashion is proposed and outperforms state-of-the-art methods at a large margin on pedestrian detection.
- MGMap: Mask-Guided Learning for Online Vectorized HD Map Construction75
This work proposes MGMap, a mask-guided approach that effectively highlights the informative regions and achieves precise map element localization by introducing the learned masks based on the enhanced multi-scale BEV features from two perspectives.
- Box2Mask: Box-Supervised Instance Segmentation via Level-Set Evolution74
This paper presents a novel single-shot instance segmentation approach, namely Box2Mask, which integrates the classical level-set evolution model into deep neural network learning to achieve accurate mask prediction with only bounding box supervision.
- 72
- Efficient Convex Relaxation for Transductive Support Vector Machine70
This work proposes solving Transductive SVM via a convex relaxation, which converts the NP-hard problem to a semi-definite programming, and shows the promising performance of the proposed algorithm in comparison with other state-of-the-art implementations of Transductives SVM.
- 67
- Efficient LiDAR Odometry for Autonomous Driving63
This work proposes a novel efficient LiDAR odometry approach by taking advantage of both non-ground spherical range image and bird’s-eye-view map for ground points and a range adaptive method is introduced to robustly estimate the local surface normal.
- 61
- Traj-LO: In Defense of LiDAR-Only Odometry Using an Effective Continuous-Time Trajectory60
This letter demonstrates that LiDAR is enough to achieve the similar capability through a continuous-time perspective, and can recover the spatial-temporal consistent movement of LiDAR by tightly coupling the geometric information from LiDAR points and kinematic constraints from trajectory smoothness.
- Meta-RangeSeg: LiDAR Sequence Semantic Segmentation Using Multiple Feature Aggregation60
This work proposes a novel approach to semantic segmentation for LiDAR sequences named Meta-RangeSeg, where a new range residual image representation is introduced to capture the spatial-temporal information and Meta-Kernel is employed to extract the meta features.
- 58
- Learning Bregman Distance Functions and Its Application for Semi-Supervised Clustering53
This paper proposes a novel scheme that learns nonlinear Bregman distance functions from side information using a non-parametric approach that is similar to support vector machines and presents an efficient learning algorithm for the proposed scheme.
- 52
- Sparse Online Learning of Image Similarity51
This article addresses the fundamental problem of learning to optimize image similarity with sparse and high-dimensional representations from large-scale training data, and proposes a novel scheme of Sparse Online Learning of Image Similarity (SOLIS), which enjoys significant advantages in computational efficiency, model sparsity, and retrieval scalability.
- 50
- 48
- Face Annotation Using Transductive Kernel Fisher Discriminant47
The main idea of the approach is to solve the Fisher's discriminant using deformed kernels incorporating the information of both labeled and unlabeled data, which is more effective than traditional supervised approaches, especially when there are very few training data.
- 46
- An Effective Approach to 3D Deformable Surface Tracking40
This paper reformulates the 3D deformable surface tracking problem into an unconstrained quadratic optimization problem, and finds that this problem can be solved very efficiently by resolving a set of sparse linear equations.
- Scalable Image Retrieval by Sparse Product Quantization37
Sparse product quantization (SPQ) is proposed, a novel approach to encoding the high-dimensional feature vectors into sparse representation that optimize the sparse representations of the feature vectors by minimizing their quantization errors, making the resulting representation is essentially close to the original data in practice.
- Single-shot bidirectional pyramid networks for high-quality object detection35
The experiments showed that the proposed BPN achieves the best performances among all the single-stage object detectors on both PASCAL VOC and MS COCO datasets, especially for high-quality detections.
- Hypergraph-based multi-example ranking with sparse representation for transductive learning image retrieval34
A novel QBME method for fast image retrieval based on transductive learning framework that accepts one input example at a time and all the input examples are processed at the same time in this strategy.
- Image Gradient-based Joint Direct Visual Odometry for Stereo Camera31
A novel scheme for stereo odometry is proposed, which is able to improve the convergence with more accurate pose and introduces a gradient-based feature representation, which enjoys the merit of being robust to illumination changes.
- 30
- 30
- 30
- 29
- 29
- 29
- 29
- 28
- 28
- 28
- 26
- 25
- 25
- 24
- 23
- 22
- 21
- 21
- 20
- 19
- PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learning18
This paper proposes PointLoRA, a simple yet effective method that combines low-rank adaptation (LoRA) with multi-scale token selection to efficiently fine-tune point cloud models, reducing the need for tunable parameters while enhancing global feature capture.
- 18
- 18
- 18
- 17
- SLED: Structure Learning based Denoising for Recommendation16
It is identified that an interaction’s related structural patterns in its neighborhood graph are potentially correlated with some outcome of implicit feedback (i.e., users’ ratings after consuming items), analogous to findings in other domains such as social networks.
- 14
- Realtime and robust object matching with a large number of templates14
This work proposes a compact DOT representation with a fast partial occlusion handling approach, and introduces the C-DOT similarity map to store the matching scores of individual grids in each sliding window, which is used to further infer the Occlusion map.
- 14
- 14
- 14
- 13
- 13
- 12
- 12
- Moiré Backdoor Attack (MBA): A Novel Trigger for Pedestrian Detectors in the Physical World12
It is demonstrated that individuals wearing such clothes can effectively evade detection by the backdoored model while wearing regular clothes does not trigger the attack, ensuring the attack remains covert.
- 12
- 12
- 12
- 11
- 11
- 11
- 11
- 10
- 10
- 10
- 10
- 9
- 9
- 8
- 8
- 8
- 7
- 7
- Interp3D: Correspondence-aware Interpolation for Generative Textured 3D Morphing6
The proposed Interp3D is a novel training-free framework for textured 3D morphing that harnesses generative priors and adopts a progressive alignment principle to ensure both geometric fidelity and texture coherence.
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 5
- 5
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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.