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
- Heung‐Yeung ShumSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works78 from public data
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks76,422
This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features.
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification21,102
This work proposes a Parametric Rectified Linear Unit (PReLU) that generalizes the traditional rectified unit and derives a robust initialization method that particularly considers the rectifier nonlinearities.
- 6,578
- 6,240
- 4,187
- Cascaded Pyramid Network for Multi-person Pose Estimation1,799
A novel network structure called Cascaded Pyramid Network (CPN) is presented which targets to relieve the problem from these "hard" keypoints, with state-of-art results on the COCO keypoint benchmark, with average precision at 73.0.
- Large Kernel Matters — Improve Semantic Segmentation by Global Convolutional Network1,671
This work proposes a Global Convolutional Network to address both the classification and localization issues for the semantic segmentation and suggests a residual-based boundary refinement to further refine the object boundaries.
- Convolutional neural networks at constrained time cost1,509
This paper investigates the accuracy of CNNs under constrained time cost, and presents an architecture that achieves very competitive accuracy in the ImageNet dataset, yet is 20% faster than “AlexNet” [14] (16.0% top-5 error, 10-view test).
- Instance-Aware Semantic Segmentation via Multi-task Network Cascades1,279
This paper presents Multitask Network Cascades for instance-aware semantic segmentation, which consists of three networks, respectively differentiating instances, estimating masks, and categorizing objects, and develops an algorithm for the nontrivial end-to-end training of this causal, cascaded structure.
- ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation1,154
This paper proposes to use scribbles to annotate images, and develops an algorithm to train convolutional networks for semantic segmentation supervised by scribbles, which shows excellent results on the PASCALCONTEXT dataset thanks to extra inexpensive scribble annotations.
- BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation1,125
This paper proposes a method that achieves competitive accuracy but only requires easily obtained bounding box annotations, and yields state-of-the-art results on PASCAL VOC 2012 and PASCal-CONTEXT.
- 583
- Convolutional feature masking for joint object and stuff segmentation456
This paper proposes a joint method to handle objects and “stuff” (e.g., grass, sky, water) in the same framework and presents state-of-the-art results on benchmarks of PASCAL VOC and new PASCal-CONTEXT.
- 415
- Instance-Sensitive Fully Convolutional Networks413
This paper develops FCNs that are capable of proposing instance-level segment candidates that do not have any high-dimensional layer related to the mask resolution, but instead exploits image local coherence for estimating instances.
- 345
- MegDet: A Large Mini-Batch Object Detector338
This paper proposes a Large Mini-Batch Object Detector (MegDet) to enable the training with a large minibatch size up to 256, so that it can effectively utilize at most 128 GPUs to significantly shorten the training time.
- Efficient and accurate approximations of nonlinear convolutional networks270
This paper aims to accelerate the test-time computation of deep convolutional neural networks (CNNs), and takes the nonlinear units into account, subject to a low-rank constraint which helps to reduce the complexity of filters.
- 259
- Learning Delicate Local Representations for Multi-person Pose Estimation242
This paper proposes an efficient attention mechanism - Pose Refine Machine (PRM) to make a trade-off between local and global representations in output features and further refine the keypoint locations.
- 216
- Learning Dynamic Routing for Semantic Segmentation190
A conceptually new method to alleviate the scale variance in semantic representation, named dynamic routing, which generates data-dependent routes, adapting to the scale distribution of each image, and compares with several static architectures, which can be modeled as special cases in the routing space.
- 184
- Supervised Transformer Network for Efficient Face Detection176
A new cascaded Convolutional Neural Network, dubbed the name Supervised Transformer Network, to address the challenge of large pose variations in real-word face detection, which achieves state-of-the-art detection accuracies on several public benchmarks.
- 154
- 147
- Paint selection137
Paint Selection facilitates users to progressively make a selection by roughly painting the object of interest using a brush, and is efficient enough that instant feedback can be provided to users as they drag the mouse.
- 130
- Disentangled Image Matting128
This paper proposes AdaMatting, a new end-to-end matting framework that disentangles this problem into two sub-tasks: trimap adaptation and alpha estimation, which achieves the state-of-the-art performance on Adobe Composition-1k dataset both qualitatively and quantitatively.
- 111
- Pop-up light field110
An image-based modeling and rendering system that models a sparse light field using a set of coherent layers, and introduces a Bayesian approach, coherence matting, to estimate alpha matting around segmented layer boundaries by incorporating a coherence prior in order to maintain coherence across images.
- 89
- Progressive End-to-End Object Detection in Crowded Scenes87
A progressive predicting method that first select accepted queries prone to generate true positive predictions, then refine the rest noisy queries according to the previously accepted predictions, and can significantly boost the performance of query-based detectors in crowded scenes.
- 70
- 51
- 37
- PointINS: Point-Based Instance Segmentation34
This paper proposes an instance-aware convolution that decomposes this mask representation learning task into two tractable modules as instance- aware weights and instance-agnostic features, improving mask learning efficiency by avoiding employing several independent convolutions.
- 34
- 33
- Relieving Long-tailed Instance Segmentation via Pairwise Class Balance32
This paper proposes a novel Pairwise Class Balance (PCB) method, built upon a confusion matrix which is updated during training to accumulate the ongoing prediction preferences, and generates fightback soft labels for regularization during training.
- 32
- 31
- Detecting glaucoma from multi-modal data using probabilistic deep learning28
The findings suggest that models based on combined visual field and fundus photograph modalities detects glaucoma with higher accuracy, thus providing another level of confidence in decision making.
- 20
- 19
- DIC-Transformer: interpretation of plant disease classification results using image caption generation technology16
A two-stage model called DIC-Transformer, which encompasses three tasks (detection, interpretation, and classification), was proposed and indicates that the DIC-Transformer outperforms other comparison models in classification and caption generation.
- 16
- Joint metric learning of local and global features for vehicle re-identification15
This work presents an end-to-end Partition and Fusion Multi-branch Network (PFMN), a novel approach to effectively learn discriminative features without any annotations or additional attributes to solve vehicle re-identification.
- 15
- 12
- Efficient Human Pose Estimation by Learning Deeply Aggregated Representations11
This paper proposes an efficient human pose estimation network (DANet) by learning deeply aggregated representations and proposes an orthogonal attention block (OAB) and a second-order fusion unit (SFU) that could achieve comparable or even better accuracy with much smaller model complexity.
- 7
- 7
- 7
- 5
- 5
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- Multimodality pedestrian detection based on YOLOv52
A pedestrian detection method based on YoloV5 RGB and thermal image data fusion that uses two yolov5 branch structures to learn the features of RGB and Thermal image data respectively, and finally uses multimodal features for fusion detection.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- Decoupling Vocal and Rhythmic Conditioning for Music-Driven Singing Avatar Animation–
This work proposes MusicAvatar, a diffusion-based framework that directly synthesizes 2D singing avatars without relying on 3D priors, and designs a dual-stream music attention module that decouples the roles of singing voice and BGM.
- –
- –
- –
- –
- –
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 2026-10-16. 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.