Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks194 from public data
- 1,938
- Richer Convolutional Features for Edge Detection1,240
RCF encapsulates all convolutional features into more discriminative representation, which makes good usage of rich feature hierarchies, and is amenable to training via backpropagation, and achieves state-of-the-art performance on several available datasets.
- 790
- HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction435
Three benchmarking tasks to pro-mote category-level HOI from 4D visual signals are established including semantic segmentation of 4D dynamic point cloud se-quences, category- level object pose tracking, and egocen-tric action segmentation with diverse interaction targets.
- MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation352
A multi-stage architecture for the temporal action segmentation task that overcomes the limitations of the previous approaches and achieves state-of-the-art results on three datasets: 50Salads, Georgia Tech Egocentric Activities (GTEA), and the Breakfast dataset.
- P2T: Pyramid Pooling Transformer for Scene Understanding321
This paper proposes to adapt pyramid pooling to Multi-Head Self-Attention (MHSA) in the vision transformer, simultaneously reducing the sequence length and capturing powerful contextual features, in a universal vision transformer backbone, dubbed Pyramid Pooling Transformer (P2T).
- EDN: Salient Object Detection via Extremely-Downsampled Network284
This work introduces an Extremely-Downsampled Network (EDN), which employs an extreme downsampling technique to effectively learn a global view of the whole image, leading to accurate salient object localization and construct the Scale-Correlated Pyramid Convolution (SCPC) to accomplish better multi-level feature fusion.
- 275
- Pyramid Constrained Self-Attention Network for Fast Video Salient Object Detection184
A Constrained Self-Attention (CSA) operation to capture motion cues, based on the prior that objects always move in a continuous trajectory is designed, which outperforms previous state-of-the-art methods in both accuracy and speed.
- MobileSal: Extremely Efficient RGB-D Salient Object Detection176
This article proposes an implicit depth restoration (IDR) technique to strengthen the mobile networks’ feature representation capability for RGB-D SOD, and proposes compact pyramid refinement (CPR) for efficient multi-level feature aggregation to derive salient objects with clear boundaries.
- MiniSeg: An Extremely Minimum Network for Efficient COVID-19 Segmentation166
MiniSeg, a lightweight deep learning model for efficient COVID-19 segmentation, has several significant strengths: i) it only has 83K parameters and is thus not easy to overfit; ii) it has high computational efficiency and is therefore convenient for practical deployment; and iii) it can be fast retrained by other users using their private CO VID-19 data for further improving performance.
- 165
- 151
- 148
- 137
- 132
- 131
- Semantic Edge Detection with Diverse Deep Supervision113
A novel fully convolutional neural network using diverse deep supervision within a multi-task framework where bottom layers aim at generating category-agnostic edges, while top layers are responsible for the detection of category-aware semantic edges is proposed.
- DNA: Deeply Supervised Nonlinear Aggregation for Salient Object Detection113
The proposed saliency detector, a modified U-Net architecture with DNA, performs favorably against state-of-the-art methods on various datasets and evaluation metrics without bells and whistles and can successfully break through the bottleneck of the current linear approaches.
- Multi-Scale Interaction for Real-Time LiDAR Data Segmentation on an Embedded Platform105
The proposed Multi-scale Interaction Network (MINet) uses multiple paths with different scales and balances the computational resources between the scales and outperforms point-based, image- based, and projection-based methods in terms of accuracy, number of parameters, and runtime.
- Vision Transformers with Hierarchical Attention103
This paper proposes hierarchical MHSA (H-MHSA), a novel approach that computes sell-attention in a hierarchical fashion, and builds a family of hierarchical-attention-based transformer networks, namely HAT-Net, which provides a new perspective for vision transformers.
- Efficient semi-supervised feature selection with noise insensitive trace ratio criterion101
This paper proposes a noise insensitive trace ratio criterion for feature selection with a re-scale preprocessing and proposes an efficient semi-supervised feature selection algorithm to select relevant features using both labeled and unlabeled data.
- 100
- Stereoscopic image quality assessment method based on binocular combination saliency model93
An effective method to evaluate the quality of stereoscopic images that are afflicted by symmetric distortions is proposed and a new 3D saliency map is developed, which not only greatly reduces the computational complexity by avoiding calculation of the depth information, but also assigns appropriate weights to the image contents.
- Automated detection of cardiovascular disease by electrocardiogram signal analysis: a deep learning system81
The proposed CNN model could help reduce misdiagnosis and missed diagnosis in primary care settings and also improve efficiency and save manpower cost for large general hospitals.
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 2026-10-12. 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.