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
- Yuncai LiuSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works485 from public data
- Transformers in Time Series: A Survey1,712
This paper systematically review Transformer schemes for time series modeling by highlighting their strengths as well as limitations and categorizes time series Transformers based on common tasks including forecasting, anomaly detection, and classification.
- R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object1,234
This paper proposes an end-to-end refined single-stage rotation detector for fast and accurate object detection by using a progressive regression approach from coarse to fine granularity and designs a feature refinement module to improve detection performance by getting more accurate features.
- 1,040
- Image Matching from Handcrafted to Deep Features: A Survey988
This survey introduces feature detection, description, and matching techniques from handcrafted methods to trainable ones and provides an analysis of the development of these methods in theory and practice, and briefly introduces several typical image matching-based applications.
- Arbitrary-Oriented Object Detection with Circular Smooth Label640
This paper designs a new rotation detection baseline, to address the boundary problem by transforming angular prediction from a regression problem to a classification task with little accuracy loss, whereby high-precision angle classification is devised in contrast to previous works using coarse-granularity in rotation detection.
- Generalizing Face Forgery Detection with High-frequency Features638
This paper finds that current CNN-based detectors tend to overfit to method-specific color textures and thus fail to generalize, and proposes to utilize the high-frequency noises for face forgery detection with superior generalization performance.
- Ternary Weight Networks604
Extensive experiments show that the TWNs achieve much better result than the Binary-Weight-Networks (BWNs) and the classification performance on MNIST and CIFAR-10 is very close to the full precision networks.
- MMRotate490
An open-source toolbox, named MMRotate, which provides a coherent algorithm framework of training, inferring, and evaluation for the popular rotated object detection algorithm based on deep learning, and implements 18 state-of-the-art algorithms.
- Learning Modulated Loss for Rotated Object Detection412
This paper refers to the above issues as rotation sensitivity error (RSE) and proposes a modulated rotation loss to dismiss the discontinuity of loss and can achieve consistent improvement on the five parameter methods and the eight parameter methods.
- SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing372
Instance-level denoising on the feature map is performed to enhance the detection to small and cluttered objects and a novel IoU constant factor is added to the smooth L1 loss to address the long standing boundary problem.
- Dense Label Encoding for Boundary Discontinuity Free Rotation Detection357
This paper explores a relatively less-studied methodology based on classification for rotation detection, and proposes new techniques to inherently dismiss the boundary discontinuity issue as encountered by the regression-based detectors.
- Unsupervised Deep Learning for Optical Flow Estimation327
This work devise a simple yet effective unsupervised method for learning optical flow, by directly minimizing photometric consistency by using image warping by the estimated flow.
- Deep Spectral Clustering Using Dual Autoencoder Network313
A joint learning framework for discriminative embedding and spectral clustering is proposed, which can significantly outperform state-of-the-art clustering approaches and be more robust to noise.
- Modeling the intensity function of point process via recurrent neural networkss290
This paper model the background by a Recurrent Neural Network with its units aligned with time series indexes while the history effect is modeled by another RNN whose units are aligned with asynchronous events to capture the long-range dynamics.
- Modeling the Intensity Function of Point Process Via Recurrent Neural Networks290
This paper model the background by a Recurrent Neural Network with its units aligned with time series indexes while the history effect is modeled by another RNN whose units are aligned with asynchronous events to capture the long-range dynamics.
- HDGT: Heterogeneous Driving Graph Transformer for Multi-Agent Trajectory Prediction via Scene Encoding272
Heterogeneous Driving Graph Transformer (HDGT), a backbone modelling the driving scene as a heterogeneous graph with different types of nodes and edges, achieves state-of-the-art performance for the task of trajectory prediction, on INTERACTION Prediction Challenge and Waymo Open Motion Challenge.
- Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Driving258
The above refinement module could be stacked in a cascaded fashion, which extends the capacity of the decoder with spatial-temporal prior knowledge about the conditioned future, and achieves state-of-the-art performance in closed-loop benchmarks.
- 255
- Prediction of RNA-protein sequence and structure binding preferences using deep convolutional and recurrent neural networks252
This study shows that the iDeepS method identifies the sequence and structure motifs to accurately predict RBP binding sites, and outperforms the state-of-the-art methods.
- A Short Survey of Recent Advances in Graph Matching223
The aim is to provide a systematic and compact framework regarding the recent development and the current state-of-the-arts in graph matching.
- Anomaly Detection of Time Series With Smoothness-Inducing Sequential Variational Auto-Encoder214
This article proposes a smoothness-inducing sequential variational auto-encoder (VAE) model for the robust estimation and anomaly detection of multidimensional time series and shows the effectiveness of the model on both synthetic data sets and public real-world benchmarks.
- DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Driving204
This work aims to explore the possibility of directly adopting the strong teacher model to conduct planning while letting the student model focus more on the perception part, and proposes DriveAdapter, which employs adapters with the feature alignment objective function between the student (perception) and teacher (planning) modules.
- 199
- 199
- On the Arbitrary-Oriented Object Detection: Classification Based Approaches Revisited195
A Circular Smooth Label technique is devised to handle the periodicity of angle and increase the error tolerance to adjacent angles and an object heading detection module is developed, which can be useful when the exact heading orientation information is needed e.g. for ship and plane heading detection.
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.