Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks119 from public data
- Relation-Aware Global Attention for Person Re-Identification654
This work proposes an effective Relation-Aware Global Attention (RGA) module which captures the global structural information for better attention learning and proposes to stack the relations, i.e., its pairwise correlations/affinities with all the feature positions together to learn the attention with a shallow convolutional model.
- Style Normalization and Restitution for Generalizable Person Re-Identification440
The aim of this paper is to design a generalizable person ReID framework which trains a model on source domains yet is able to generalize/perform well on target domains, and to enforce a dual causal loss constraint in SNR to encourage the separation of identity-relevant features and identity-irrelevant features.
- MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs420
A set of diagnosis tools to monitor system components and events deep in the stack, identify root causes, and derive effective techniques to achieve fault tolerance and mitigate stragglers are developed.
- Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey224
This first to present a comprehensive review of recent diffusion model-based methods on image restoration, encompassing the learning paradigm, conditional strategy, framework design, modeling strategy, and evaluation, and proposes nine potential and challenging directions for the future research of diffusion model-based IR.
- Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptation218
A Nuclear-norm Wasserstein discrepancy (NWD) that has definite guidance meaning for performing discrimination is introduced that can be coupled with the classifier to serve as a discriminator satisfying the K-Lipschitz constraint without the requirements of additional weight clipping or gradient penalty strategy.
- Region Normalization for Image Inpainting207
It is shown that the mean and variance shifts caused by full-spatial FN limit the image inpainting network training and a spatial region-wise normalization named Region Normalization (RN) is proposed to overcome the limitation.
- Task Residual for Tuning Vision-Language Models182
A new efficient tuning approach for VLMs named Task Residual Tuning (TaskRes), which performs directly on the text-based classifier and explicitly decouples the prior knowledge of the pre-trained models and new knowledge regarding a target task.
- Semantics-Aligned Representation Learning for Person Re-Identification164
A framework that drives the reID network to learn semantics-aligned feature representation through delicate supervision designs is proposed and achieves the state-of-the-art performances on the benchmark datasets CUHK03, Market1501, MSMT17, and the partial person reID dataset Partial REID.
- Learning for Video Compression144
The proposed PixelMotionCNN (PMCNN) which includes motion extension and hybrid prediction networks can model spatiotemporal coherence to effectively perform predictive coding inside the learning network and provides a possible new direction to further improve compression efficiency and functionalities of future video coding.
- Uncertainty-Aware Multi-Shot Knowledge Distillation for Image-Based Object Re-Identification127
This paper designs an Uncertainty-aware Multi-shot Teacher-Student (UMTS) Network that consists of a teacher network that learns the comprehensive features from multiple images of the same object, and a student network that takes a single image as input.
- Style Normalization and Restitution for Domain Generalization and Adaptation113
A novel Style Normalization and Restitution module (SNR) is designed to simultaneously ensure high generalization and discrimination capability of the networks and enforce a dual restitution loss constraint to encourage the better separation of task-relevant and task-irrelevant features.
- Is Network the Bottleneck of Distributed Training?106
A first-principles approach to measure and analyze the network performance of distributed training finds that the network is running at low utilization and that if the network can be fully utilized, distributed training can achieve a scaling factor of close to one.
- Unsupervised Single Image Deraining with Self-Supervised Constraints87
An Unsupervised Deraining Generative Adversarial Network (UD-GAN) is proposed to tackle single image deraining problems by introducing self-supervised constraints from the intrinsic statistics of unpaired rainy and clean images.
- Dense Interaction Learning for Video-based Person Re-identification77
A hybrid framework that takes the principal advantages of both CNN-based and Attention-based architectures to tackle video-based person re-ID difficulties and introduces Spatio-TEmporal Positional Embedding into the DI decoder to investigate the positional relation among the spatial-temporal inputs.
- Global Distance-Distributions Separation for Unsupervised Person Re-identification75
A global distance-distributions separation (GDS) constraint over the two distributions is introduced to encourage the clear separation of positive and negative samples from a global view and validation of the effectiveness of the GDS constraint in unsupervised ReID networks is validated.
- Learned Block-Based Hybrid Image Compression74
This paper introduces explicit intra prediction into a learned image compression framework to utilize the relation among adjacent blocks and proposes a contextual prediction module (CPM) to better capture long-range correlations by utilizing the strip pooling to extract the most relevant information in neighboring latent space, thus achieving effective information prediction.
- 73
- Particle swarm optimization using dimension selection methods69
Based on the analysis of the importance of the randomness in the PSO, another way of using randomness is proposed in PSO with random dimension selection (PSORDS) algorithm, which utilizesrandom dimension selection instead of stochastic coefficients.
- MiCS60
MiCS, which Minimizes the Communication Scale to bring down communication overhead is proposed, which can utilize heterogeneous network bandwidth, reduce network traffic over slower links, reduce the latency of communications for maintaining high network bandwidth utilization, and amortize expensive global gradient synchronization overhead.
- Multi-Prompts Learning with Cross-Modal Alignment for Attribute-based Person Re-Identification53
A new framework called Multi-Prompts ReID (MP-ReID), based on prompt learning and language models, to fully dip fine attributes to assist ReID task with off-the-shelf models for more accurate retrieval results.
- Learning Omni-Frequency Region-adaptive Representations for Real Image Super-Resolution53
This paper designs a Frequency Decomposition module to separate different frequency components to comprehensively compensate the information lost for real LR image and designs a Region-adaptive Frequency Aggregation module by leveraging dynamic convolution and spatial attention to adaptively restore frequency components for different regions.
- AI-GAN: Asynchronous interactive generative adversarial network for single image rain removal51
An Asynchronous Interactive Generative Adversarial Network (AI-GAN) is proposed to progressively disentangle the rainy image into background and rain spaces in feature level through a two-branch structure that outperforms state-of-the-art deraining methods and benefits various typical multimedia applications.
- Learning Disentangled Feature Representation for Hybrid-Distorted Image Restoration50
This work introduces the concept of Disentangled Feature Learning to achieve the feature-level divide-and-conquer of hybrid distortions and proposes the feature disentanglement module (FDM) to distribute feature representations of different distortions into different channels by revising gain-control-based normalization.
- Binary Code Summarization: Benchmarking ChatGPT/GPT-4 and Other Large Language Models45
Binary code summarization, while invaluable for understanding code semantics, is challenging due to its labor-intensive nature, and BinSum, a comprehensive benchmark and dataset of over 557K binary functions, is presented and a new semantic similarity metric is proposed that surpasses traditional exact-match approaches.
- AIM 2020 Challenge on Real Image Super-Resolution: Methods and Results43
This paper introduces the real image Super-Resolution challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020, and gauges the state-of-the-art approaches for real image SR in terms of PSNR and SSIM.
- MSSF: A 4D Radar and Camera Fusion Framework With Multi-Stage Sampling for 3D Object Detection in Autonomous Driving36
A simple but effective multi-stage sampling fusion network based on 4D radar and camera that surpasses classical LiDAR-based methods on the VoD dataset and proposes a semantic-guided head to perform foreground-background segmentation on voxels with voxel feature re-weighting, further alleviating the problem of feature blurring.
- Learning Cross-Scale Weighted Prediction for Efficient Neural Video Compression34
A novel cross-scale prediction module is proposed that achieves more effective motion compensation and a multi-stage quantization strategy is proposed, which improves the rate-distortion performance with no extra computational penalty during inference.
- FAN: Frequency Aggregation Network for Real Image Super-Resolution32
This work proposes FAN, a frequency aggregation network, to address the real-world image super-resolu-tion problem by extracting different frequencies of the LR image and passing them to a channel attention-grouped residual dense network (CA-GRDB) individually to output corresponding feature maps.
- 31
- 30
- Semantically Structured Image Compression via Irregular Group-Based Decoupling28
This paper proposes the concept of group-independent transform that maintain the independence among distinct groups that decouple an image into multiple groups with irregular shapes based on a customized group mask and compress them independently.
- 23
- 22
- 22
- Re-energizing Domain Discriminator with Sample Relabeling for Adversarial Domain Adaptation22
This work proposes an efficient optimization strategy named Re-enforceable Adversarial Domain Adaptation (RADA), which aims to re-energize the domain discriminator during the training by using dynamic domain labels, and relabeling makes the less separable distributions more separable, and thus leads to a more powerful domain classifier w.r.t. the new data distributions.
- Information transmission rate changes of retinal ganglion cells during contrast adaptation22
It is revealed that the information carried by each spike was increased as compared to pre-adaptation, suggesting that retinal ganglion cells' information processing strategies during contrast adaptation may reflect economical principle by promoting each spike more informative.
- A Survey of Behavior Foundation Model: Next-Generation Whole-Body Control System of Humanoid Robots17
This paper presents a comprehensive overview of BFMs for humanoid WBC, tracing their development across diverse pre-training pipelines, and discusses real-world applications, current limitations, urgent challenges, and future opportunities.
- A combined rotated general regression neural network method for river flow forecasting17
The results indicate that the combined RGRNN model could be a useful river flow forecasting tool for the chosen arid and semi-arid region in China.
- 16
- 15
- AppScalpel: Combining static analysis and outlier detection to identify and prune undesirable usage of sensitive data in Android applications15
It is demonstrated that AppScalpel precisely identifies undesirable usage of sensitive data and effectively protects users’ private information in a fine-grained mode, and the robustness of the instrumented apps is also achieved.
- Design and Experiment of Variable-Spray System Based on Deep Learning14
Results further demonstrated that the system can automatically adjust the spray volume based on different travel speeds and weed densities, and can provide theoretical and reference support for the development of new precision-spray plant-protection machinery for wheat fields.
- One at a Time: Progressive Multi-Step Volumetric Probability Learning for Reliable 3D Scene Perception14
A multi-step learning framework dedicated to progressively refining the Volumetric Probability in a Diffusion process, dubbed as VPD, is introduced, which first build a coarse probability volume from input images with the off-the-shelf scene perception baselines, which is then conditioned as the basic geometry prior before being fed into a 3D diffusion UNet.
- RailPC: A large‐scale railway point cloud semantic segmentation dataset14
This work introduces RailPC, a new point cloud benchmark that contains twice the number of annotated points compared to the largest available mobile laser scanning (MLS) point cloud dataset and is the first railway‐specific 3D dataset for semantic segmentation.
- InternEvo: Efficient Long-sequence Large Language Model Training via Hybrid Parallelism and Redundant Sharding13
The design of InternEvo decouples all of the sharding dimensions into a new hierarchical space, and systematically analyzes the memory and communication cost of LLM training, generates an effective hybrid parallelism strategy, and implements memory management techniques to reduce GPU memory fragmentation.
- Multi-task Learning-based All-in-one Collaboration Framework for Degraded Image Super-resolution13
Extensive experimental results on synthetic and real-world low-resolution images show that the proposed all-in-one collaboration framework not only produces favorable high-resolution results while removing serious degradation, but also has high computational efficiency, outperforming state-of-the-art methods.
- Hierarchical Context Alignment With Disentangled Geometric and Temporal Modeling for Semantic Occupancy Prediction12
Hi-SOP first disentangles the geometric and temporal context for separate alignment, which two branches are then composed to enhance the reliability of SOP, which outperforms SOTAs for semantic scene completion on the SemanticKITTI & NuScenes-Occupancy datasets and LiDAR semantic segmentation on the NuScenes dataset.
- Scaling up Occupancy-Centric Driving Scene Generation: Dataset and Method12
A unified framework that jointly synthesizes high-quality semantic occupancy, multi-view videos, and LiDAR point clouds is developed, which incorporates a spatio-temporal disentangled architecture to support high-fidelity spatial expansion and temporal forecasting of 4D dynamic occupancy.
- 11
- StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization11
This paper proposes a simple yet effective scheme, termed as StyDeSty, to explicitly account for the alignment of the source and pseudo domains in the process of data augmentation, enabling them to interact with each other in a self-consistent manner and further giving rise to a latent domain with strong generalization power.
- 11
- A Decomposed Dual-Cross Generative Adversarial Network for Image Rain Removal.10
The proposed Decomposed Dual-Cross Generative Adversarial Network (DDC-GAN) shows performance improvement compared with state-of-the-art methods on both synthetic and real-world images in terms of qualitative and quantitative measures.
- 9
- 9
- Double JPEG Compression Detection Based on Extended First Digit Features of DCT Coefficients9
This paper proposes a powerful recompression detection method by extending the first digit features of quantized DCT coefficients that can achieve a satisfactory classification accuracy even for the double JPEG compression with quality factor 95 followed by 50 or 55, while many previous works fail in the detection.
- MaskMol: knowledge-guided molecular image pre-training framework for activity cliffs with pixel masking7
MaskMol is developed, a knowledge-guided molecular image selfsupervised learning framework that introduces a novel method for molecular image representation learning and virtual screening, advancing drug discovery and providing new insights into structure-activity relationships (SAR).
- CASINet: Content-Adaptive Scale Interaction Networks for scene parsing7
A Content-Adaptive Scale Interaction Network (CASINet) to exploit the multi-scale features for scene parsing based on the classic Atrous Spatial Pyramid Pooling module, followed by a proposed contextual scale interaction (CSI) module, and a scale adaptation (SA) module.
- Large-Scale KPI Anomaly Detection Based on Ensemble Learning and Clustering7
This paper proposes an automatic and generic transfer learning strategy, called KADT (KPI Anomaly Detection based on Transfer Learning), which integrates KPI clustering and model pretrained techniques and can significantly reduce the time overhead of the model training with little loss of accuracy.
- Knowledge Regularized Negative Feature Tuning of Vision-Language Models for Out-of-Distribution Detection6
This work proposes a novel method called Knowledge Regularized Negative Feature Tuning (KR-NFT), which integrates an innovative adaptation architecture termed Negative Feature Tuning (NFT) and a corresponding knowledge-regularization (KR) optimization strategy, designed to enhance the discrimination between ID and OOD sets while mitigating pre-trained knowledge forgetting.
- TeamShakespeare at SemEval-2023 Task 6: Understand Legal Documents with Contextualized Large Language Models6
The Legal-BERT-HSLN model is developed that considers the com-prehensive context information in both intra-and inter-sentence levels to predict rhetoricalroles and a Legal-LUKE model, which is legal-contextualized and entity-aware, to recognize legal entities is trained.
- Extracting weld seam by Hough transform based on dynamic windows6
Experiments indicate that this method can greatly increased computational speed and algorithm stability and accuracy of fitted straight line, and meet the requirements of real-time seam tracking.
- 6
- Fault identification of a chain conveyor based on functional data feature engineering and optimized multi-layer kernel extreme learning machine5
The experimental results show that the proposed fault identification method can effectively extract the fault features of function time series signals, and then accurately identify the faults of electromechanical systems.
- Optimization of Small Object detection based on Generative Adversarial Networks5
This paper proposes an Optimized Perceptual Generative Adversarial Network (OPGAN) to present more features of small objects and demonstrates the effectiveness of OPGAN in detecting small objects.
- 5
- Augmented Coarse-to-Fine Video Frame Synthesis with Semantic Loss5
This paper introduces augmented inputs to compensate texture details and motion information and presents a coarse-to-fine guidance scheme with a well-designed semantic loss to improve the capability of video frame synthesis.
- 5
- Stock Price Predicting Using SVM Optimized by Particle Swarm Optimization Based on Uncertain Knowledge5
Experimental results showed that PSO-UK-SVM model performed better degree of fitting and accuracy, and the model proposed in this paper has some guiding significance for investors.
- Image Processing Methods for V-Shape Weld Seam Based on Laser Structured Light5
This method starts with image preprocessing, including median filtering, one-dimensional LOG (Laplace of Gaussian) operations, morphological operations, and scattered clusters filtering, and can find a target window dynamically.
- 5
- Possible mechanism of flicking-induced short-term plasticity in retinal cone-LHC synapse: a computational study5
The computational simulation results suggest that the short-term modification of signal transmission between the retinal graded neurons is likely to be attributed to the regulatory effects that calcium-dependent process exerts on the single-channel properties of the postsynaptic AMPA receptors.
- 4
- 4
- Image dehazing with uneven illumination prior by dense residual channel attention network4
DRCAN is built based on the proposed dense residual block (DRB) and dense residual channel attention block (DRCAB) and uses an image segmentation strategy to predict scene lights and is comparable to most of existing methods.
- 4
- A Federated Learning Algorithm That Combines DCScaffold and Differential Privacy for Load Prediction3
A novel differential privacy federated learning algorithm that incorporates weather and temporal factors as key variables influencing load patterns, thereby creating a privacy-preserving load forecasting solution and exhibits superior prediction accuracy and communication efficiency compared to existing federated learning methods.
- 3
- 3
- 3
- 3
- 3
- 3
- Modeling the pre- and post-synaptic components involved in the synaptic modification between cones and horizontal cells in carp retina3
Based on an ion-channel model described mainly in the form of Hodgkin–Huxley equations, possible mechanisms of the short-term synaptic modification are investigated and simulation results suggest the auto-enhancement effect might be induced by the Ca2+-dependent process on the post-synaptic AMPA receptors.
- A close look at few-shot real image super-resolution from the distortion relation perspective2
This work is the first to have a close look at the under-explored direction for RealSR, i.e., few-shot real-world image super-resolution, and proposes Distortion Relation guided Transfer Learning (DRTL) for the few- shot RealSR by transferring the rich restoration knowledge from auxiliary distortions to the target RealSR under the guidance of distortion relation.
- 2
- Demand response potential evaluation based on feature fusion with expert knowledge and multi‐image2
An evaluation method that fuses expert features with multi‐image inputs and analyses the model evaluation process based on gradient is proposed, providing new insights for demand response potential evaluation.
- 2
- 2
- 2
- 2
- Application of Optimized BP Neural Network in Fault Diagnosis Against Avionics2
It is proved that when BP based on the conjugate gradient is applied in fault diagnosis, its diagnosis efficiency is higher, and this method has strong practical value.
- Real-time seam tracking based on fuzzy-gaussian neural netwrok for welding mobile robot2
Kinematics modeling of the developed welding mobile robot was presented and a real time seam tracking algorithm based on fuzzy neural network was proposed, which has excellent tracing accuracy and can satisfy the requirement of practical welding project.
- 1
- 1
- NaviNeRF++: Towards Interpretable 3D Reconstruction via Unsupervised Disentangled Representation Learning1
This work achieves interpretable 3D reconstruction and fine-grained 3D disentanglement in an unsupervised manner, and is the first to achieve interpretable 3D reconstruction and fine-grained 3D disentanglement in an unsupervised manner.
- 1
- 1
- Trajectory Planning and Tracking of Hybrid Flying-Crawling Quadrotors1
A kinodynamic path-searching method with the crawling limitation of HyFCQs is proposed to guarantee the dynamical feasibility of trajectories, and a hierarchical motion controller is designed to map the execution of the flight autopilot to both crawling and flying modes.
- 1
- Bag of little bootstraps on features for enhancing classification performance1
This work proposes a new procedure, Bag of Little Bootstraps on Features (BLBF), which works by combining the results of bootstrapping multiple feature subsets of the original dataset using the random subspace method.
- Particle Swarm Optimization with Particle Similarity Based Mutation1
Experimental results show that the proposed PSO variant with particle similarity based mutation has apparently improved performance in complex multimodal functions and solves the premature convergence problem to some extent.
- –
- Challenger: Affordable Adversarial Driving Video Generation for Safety Testing–
Challenger is introduced, a framework that generates physically plausible yet photorealistic adversarial driving videos to support safety testing, and the collection of evidence for safety arguments, through a physics-aware multi-round trajectory refinement process that narrows down candidate adversarial maneuvers.
- –
- –
- –
- –
- –
- –
- Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning–
CoWorld performs domain-collaborative representation learning to bridge the gap between online and offline hidden state distributions and performs domain-collaborative behavior learning that enables the source RL agent to provide target-aware value estimation, allowing for effective offline policy regularization.
- –
- –
- –
- –
- –
- RDSC_IC: A Real Time Detection Algorithm for Scene Change based on Image Complexity–
An improved real-time algorithm of scene change detection – RDSC_IC is presented, which calculates absolute differences and corresponding ratio of image complexity between or among different GOP units, and judges the existence and type ofscene change.
- –
- –
- A Multi-Agent-Based Data Management Model for Wireless Sensor Networks–
An evaluation framework for WSN (wireless sensor network) data management system is proposed, and the drawbacks of traditional methods are analyzed.
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.