Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks293 from public data
- MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition2,241
A benchmark task to recognize one million celebrities from their face images, by using all the possibly collected face images of this individual on the web as training data, which could lead to one of the largest classification problems in computer vision.
- Suppress and Balance: A Simple Gated Network for Salient Object Detection529
A novel gated dual branch structure is designed to build the cooperation among different levels of features and improve the discriminability of the whole network and adopts the atrous spatial pyramid pooling based on the proposed "Fold" operation (Fold-ASPP) to accurately localize salient objects of various scales.
- 434
- Multi-Adversarial Faster-RCNN for Unrestricted Object Detection367
A multi-adversarial Faster-RCNN (MAF) framework for unrestricted object detection, which inherently addresses domain disparity minimization for domain adaptation in feature representation and improves the domain adaptability.
- Transfer Adaptation Learning: A Decade Survey305
The survey helps researchers rapidly but comprehensively understand and identify the research foundation, research status, theoretical limitations, future challenges, and understudied issues to be broken in the field toward generalizable representation in open-world scenarios.
- A Single Stream Network for Robust and Real-Time RGB-D Salient Object Detection258
A single stream network to directly use the depth map to guide early fusion and middle fusion between RGB and depth, which saves the feature encoder of the depth stream and achieves a lightweight and real-time model.
- 255
- Dynamic Weighted Learning for Unsupervised Domain Adaptation192
Dynamic Weighted Learning is proposed to avoid the discriminability vanishing problem caused by excessive alignment learning and domain misalignment problem causedby excessive discriminant learning and has an excellent performance in several benchmark datasets.
- Domain Adaptive Object Detection via Asymmetric Tri-Way Faster-RCNN168
This work proposes an asymmetric tri-way Faster-RCNN (ATF) for domain adaptive object detection, which has two distinct merits: 1) A ancillary net supervised by source label is deployed to learn anCillary target features and simultaneously preserve the discrimination of source domain, which enhances the structural discrimination of domain alignment.
- Classification of multiple indoor air contaminants by an electronic nose and a hybrid support vector machine166
Experimental results have demonstrated that the HSVM model outperforms other classifiers in general, and HSVM classifier preliminarily shows its superiority in solution to discrimination in various electronic nose applications.
- Evolutionary Cost-Sensitive Extreme Learning Machine160
This paper proposes an evolutionary cost-sensitive ELM, which to the best of the authors' knowledge, is the first proposal of ELM in evolutionary Cost-sensitive classification scenario, and well addresses the open issue of how to define the cost matrix in cost- sensitive learning tasks.
- 157
- 157
- 136
- 130
- A Data Augmentation Approach for Sign-Language-To-Text Translation In-The-Wild128
The goal is to build a state-of-the-art system for the automatic interpretation of sign language in unpredictable video framing conditions and the set of hypotheses to build such a system are described and the list of experiments that will lead to their verification are described.
- 122
- Manifold Criterion Guided Transfer Learning via Intermediate Domain Generation114
A novel local generative discrepancy metric-based intermediate domain generation learning called Manifold Criterion guided Transfer Learning (MCTL) is proposed in this paper and demonstrated the superiority of the proposed MC guided generative transfer method on a number of benchmark visual transfer tasks.
- 111
- Anchor Box Optimization for Object Detection108
This paper proposes to dynamically learn the anchor shapes, which allows the anchors to automatically adapt to the data distribution and the network learning capability, and achieves significant improvement over the baseline methods on several benchmark datasets.
- 107
- 103
- 96
- 94
- Self-adaptive Re-weighted Adversarial Domain Adaptation86
This paper proposes a novel trajectory representation learning framework Traj2SimVec that performs scalable and robust trajectory similarity computation and supports the point matching query by modeling the optimal matching relationship of trajectory points under different distance metrics.
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.