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
- Canhui CaiSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works241 from public data
- 184
- GiT: Graph Interactive Transformer for Vehicle Re-Identification178
A graph interactive transformer (GiT) is proposed, which is a newly-designed local correction graph, which learns discriminative local features within a patch by exploring nodes’ relationships and is superior to state-of-the-art vehicle re-identification approaches.
- Vehicle Re-Identification Using Quadruple Directional Deep Learning Features158
The proposed QD-DLF approach outperforms multiple state-of-the-art vehicle re-identification methods and is applicable to both VeRi and VehicleID databases.
- 148
- 134
- 125
- 118
- 108
- 104
- 90
- 87
- Deep Hybrid Similarity Learning for Person Re-Identification84
A deep hybrid similarity learning (DHSL) method based on a convolution neural network that is able to reasonably assign complexities of feature learning and metric learning in a CNN, so that the performance of person Re-ID is improved.
- 79
- 75
- High-Capacity Framework for Reversible Data Hiding in Encrypted Image Using Pixel Prediction and Entropy Encoding74
A generalized framework for high-capacity RDHEI for both the RRBE and VRBE cases, where the original image can be hardly discovered from the encrypted version before or after data hiding by unauthorized users and the experimental results show that the two proposed schemes outperform many state-of-the-artRDHEI schemes.
- Reversible data hiding in encrypted images using adaptive reversible integer transformation63
Compared with state-of-the-art RDH-EI methods, the proposed method can achieve a much higher embedding capacity and a better rate distortion performance.
- 60
- A multi-order derivative feature-based quality assessment model for light field image60
The proposed MDFM is more consistent with the perception of the HVS on the evaluation of LFI than the classical and state-of-the-art IQA methods.
- 55
- 52
- 52
- HOG-assisted deep feature learning for pedestrian gender recognition51
Extensive experiments have shown that the proposed HDFL method is able to effectively recognize the pedestrian gender, and consistently outperforms the state-of-the-art methods.
- 51
- 44
- 42
- 41
- 41
- 41
- Multiscale Attentive Image De-Raining Networks via Neural Architecture Search40
A high-performance multi-scale attentive neural architecture search (MANAS) framework is technically developed for image de-raining and extensive experimental results consistently demonstrate the superiority of the proposed method.
- 40
- 39
- Joint Feature and Similarity Deep Learning for Vehicle Re-identification38
The proposed JFSDL method applies a siamese deep network to extract deep learning features for an input vehicle image pair simultaneously and is superior to multiple state-of-the-art vehicle re-identification methods on both the VehicleID and VeRi data sets.
- A multi-scale contrast-based image quality assessment model for multi-exposure image fusion37
Simulation results have clearly shown that the proposed multi-scale contrast-based model (MCM) model is more consistent with the perception of the HVS on the evaluation of MEF images than multiple state-of-the-art IQA methods.
- 35
- Quad binary pattern and its application in mean-shift tracking35
The proposed QBP is with stronger robustness for feature extraction under complex scene (e.g., luminance change, similar target and background color) and with lower computational complexity and is applied on the mean-shift tracking.
- 34
- Multi-label learning with multi-label smoothing regularization for vehicle re-identification32
The proposed MLL with MLSR approach can effectively improve the performance delivered by the baseline and outperform multiple state-of-the-art vehicle re-ID methods as well.
- 31
- Perceptual feature guided rate distortion optimization for high efficiency video coding31
By incorporating the proposed method into the HEVC, extensive simulation results have demonstrated that the proposed approach can significantly improve the perceptual coding performance and obtain better visual quality of the reconstructed video, compared with the original RDO in HEVC.
- 31
- Semantic-embedded Unsupervised Spectral Reconstruction from Single RGB Images in the Wild30
A new lightweight and end-to-end learning-based framework that significantly outperforms state-of-the-art unsupervised methods and even exceeds the latest supervised method under some settings is proposed.
- 30
- 29
- 28
- 28
- Deep Posterior Distribution-Based Embedding for Hyperspectral Image Super-Resolution27
This paper incorporates the proposed feature embedding scheme into a source-consistent super-resolution framework that is physically-interpretable, producing PDE-Net, in which high-resolution HS images are iteratively refined from the residuals between input low-resolution (LR) HS images and pseudo-LR-HS images degenerated from reconstructed HR- HS images via probability-inspired HS embedding.
- Perceptual sensitivity-based rate control method for high efficiency video coding27
An efficient perceptual sensitivity-based rate control (PSRC) method for HEVC is proposed based on the human visual system (HVS) observation that the region with less perceptual sensitivity can tolerate more distortion.
- Fast motion estimation for H.26426
A fast ME algorithm is proposed to reduce the computational complexity, using a mode discriminant method to free the encoder from checking the small block size modes in homogeneous regions and a condensed hierarchical block matching method and a spatial neighbor searching scheme to find the best full-pixel motion vector.
- 25
- Statistical Early Termination and Early Skip Models for Fast Mode Decision in HEVC INTRA Coding25
In this article, statistical Early Termination (ET) and Early Skip (ES) models are proposed for fast Coding Unit (CU) and prediction mode decision in HEVC INTRA coding, in which three categories of ET and ES sub-algorithms are included.
- 24
- Viewpoint robust knowledge distillation for accelerating vehicle re-identification24
Experiments show that the proposed VRKD method outperforms many state-of-the-art vehicle re-identification approaches with better accurate and speed performance.
- 24
- 22
- 22
- Deep Diversity-Enhanced Feature Representation of Hyperspectral Images22
This paper rectify 3D convolution by modifying its topology to enhance the rank upper-bound and proposes a rank-enhanced spatial-spectral symmetrical convolution set (ReS) and a novel diversity-aware regularization term that directly acts on the feature maps to maximize independence among elements.
- Attribute-Image Person Re-identification via Modal-Consistent Metric Learning21
This paper proposes a modal-consistent metric learning (MCML) method that stably measures comprehensive similarities between attributes and images and integrates the CMMT loss function and MCMR, requiring no complex cross-modal feature alignments.
- 21
- 21
- 21
- 20
- 20
- 19
- Visual Attention Guided Pixel-Wise Just Noticeable Difference Model19
Experimental results indicate that compared with existing relevant JND profiles, the proposed JND model tolerates more distortion in the same perceptual quality, and brings better visual perception in the the same level of the injected JND-noise energy.
- Sum-of-gradient based fast intra coding in 3D-HEVC for depth map sequence (SOG-FDIC)19
A fast intra coding algorithm based on sum-of-gradient criterion for depth map coding in 3D-HEVC, named SOG-FDIC, is proposed, which can save about 21.8% coding time while keeping almost the same coding efficiency and the reconstructed video quality of depth maps and synthesized views, compared with the original 3D -HEVC.
- 18
- 18
- Unsupervised 3D Point Cloud Completion via Multi-View Adversarial Learning17
This paper proposes MAL-UPC, a framework that effectively leverages both region-level and category-specific geometric similarities to complete missing structures and outperforms current state-of-the-art self-supervised methods and even some unpaired approaches.
- 17
- 17
- 17
- 17
- Cross-modal group-relation optimization for visible–infrared person re-identification16
This paper explores a cross-modal group-relation (CMGR) to describe the relationship between the same group of people in two different modalities, and designs a group-relation correlation (GRC) loss function based on Pearson correlations to optimize CMGR.
- 16
- 16
- 15
- 14
- 14
- 14
- 14
- Content-Aware Warping for View Synthesis13
This paper proposes content-aware warping, which adaptively learns the interpolation weights for pixels of a relatively large neighborhood from their contextual information via a lightweight neural network, and proposes a new end-to-end learning-based framework for novel view synthesis from a set of input source views.
- 13
- A Challenging Benchmark of Anime Style Recognition13
A cross-role protocol to evaluate ASR performance, in which query and gallery images must come from different roles to validate an ASR model is to learn abstract painting style rather than learn discriminative features of roles, is designed.
- Object Re-identification Using Teacher-Like and Light Students13
This work proposes a joint distillation and pruning (JDP) method to learn teacher-like and light (TLL) students for object Re-ID and designs a pruner-convolution-pruner block to replace a K × K convolutional layer of the student network.
- 13
- Boosted unsupervised feature selection for tumor gene expression profiles12
A boosting scheme to sequentially learn multiple compressed feature subspaces by focusing on ambiguous samples and providing a consensus objective function with L2,1‐norm regularisation to combine these weighted feature subspaces and select discriminative features is proposed.
- Width-Adaptive CNN: Fast CU Partition Prediction for VVC Screen Content Coding12
This work makes the first attempt to reduce the encoding complexity from the perspective of CU partitioning for SCC in VVC by proposing a novel WA-CNN model, capable of predicting two large CUs for VVC-SCC by adjusting the feature channels based on the size of input CU blocks.
- 12
- A fast algorithm based on gray level co-occurrence matrix and Gabor feature for HEVC screen content coding12
A fast algorithm based on gray level co-occurrence matrix and Gabor feature model for HEVC-SCC, denoted as GGM, is proposed, which can achieve encoding time saving by 42.13% compared with SCM-8.3, and with only 1.85% bit-rate increasement.
- 11
- 11
- Learning Efficient and Effective Trajectories for Differential Equation-Based Image Restoration10
This paper reformulate the trajectory optimization of this kind of method, focusing on enhancing both reconstruction quality and efficiency, and fine-tune a foundational diffusion model (FLUX) with 12B parameters by using algorithms, producing a unified framework for handling 7 kinds of image restoration tasks.
- 10
- 10
- Deep-Learned and Hand-Crafted Features Fusion Network for Pedestrian Gender Recognition10
The proposed DHFFN method is superior to the state-of-the-art pedestrian gender recognition methods and the feature fusion process that is to combine these two features together for fully exploring the merits from both deep-learned and HOG features.
- 10
- 10
- 10
- Efficient early direct mode decision for multi-view video coding10
Experimental results have demonstrated that the proposed method is able to significantly reduce the computational complexity of MVC with negligible loss of coding efficiency, compared with the exhaustive mode decision in MVC.
- Fast-MFQE: A Fast Approach for Multi-Frame Quality Enhancement on Compressed Video9
Experimental results demonstrate that the proposed Fast-MFQE outperforms state-of-the-art methods in terms of lightweight parameters, inference speed, and quality enhancement performance.
- 9
- 9
- 9
- Bi-Layer Texture Discriminant Fast Depth Intra Coding for 3D-HEVC9
The experimental results show that the proposed algorithm reduces the depth encoding time by 44.8%, and the average bit rate of the synthetic viewpoint is only increased by 0.38%, which outperforms the state-of-the-art fast 3D-HEVC algorithms.
- 8
- 8
- Learning Spatial-angular Fusion for Compressive Light Field Imaging in a Cycle-consistent Framework8
A cycle-consistent reconstruction network based on the intrinsic linear imaging model of the coded aperture that reconstructs an LF through progressively eliminating the residuals between the projected measurements from the reconstructed LF and input measurements, and an adaptively learned spatial-angular fusion strategy.
- SIFT-flow-based color correction for multi-view video8
Experimental results have shown that the proposed SIFT flow-based color correction algorithm is able to effectively eliminate the color variation inherited in multi-view video and the coding efficiency of the color-corrected multi- view video can be greatly improved.
- 8
- 8
- FD-LSCIC: Frequency Decomposition-Based Learned Screen Content Image Compression7
This paper proposes a novel compression method that employs a multi-frequency two-stage octave residual block (MToRB) for feature extraction, a cascaded triple-scale feature fusion residual block (CTSFRB) for multi-scale feature integration and a multi-frequency context interaction module (MFCIM) to reduce inter-frequency correlations.
- Memory-augmented shuffled meta learning for visible–infrared person re-identification7
This work introduces a novel approach called memory-augmented shuffled meta (MASM) learning that not only enhances data utilization but also empowers the model to learn comprehensive global meta metrics, significantly improving its ability to distinguish individuals across modalities.
- 7
- 7
- 7
- 6
- 6
- 6
- 6
- Unsupervised video-based action recognition using two-stream generative adversarial network6
An unsupervised video-based action recognition method, called two-stream generative adversarial network (TS-GAN), which comprehensively learns the static texture and dynamic motion information inherited in videos with taking the detail information and global information into account is proposed.
- 6
- 6
- Joint Pyramid Feature Representation Network for Vehicle Re-identification6
Extensive experimental results on two commonly-used vehicle databases show that the proposed JPFRN is superior to multiple recently-developed vehicle Re-ID methods.
- 6
- 6
- 5
- 5
- Hierarchical Feature Fusion CNN: Fast Intra Prediction Mode Decision for VVC Screen Content Coding5
A Hierarchical Feature Fusion Convolutional Neural Network (HFF-CNN) for predicting the current CU best intra prediction mode based on the network out put best prediction mode, angle intra prediction mode indexes, and adjacent CU mode probability is designed.
- 5
- 5
- 5
- 5
- 5
- 5
- A spatial structural similarity triplet loss for auxiliary vehicle re-identification5
where Xi, j,k and Yi,j,k are n×n sized patches of X and Y lied at i-th row, j-th column and k-th channel, which are located by pixel-by-pixel sliding over the k- fourth channel feature map.
- 5
- 5
- 5
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- Content-adaptive temporal consistency enhancement for depth video4
A content-adaptive temporal consistency enhancement (CTCE) algorithm is proposed in this paper, which consists of two sequential stages: classification of stationary and non-stationary regions based on the texture video, and adaptive temporal consistency filtering on the depth video.
- 3
- 3
- 3
- 3
- 3
- Flexible, Fast and Accurate Densely-Sampled Light Field Reconstruction Network.3
This work proposes a novel learning-based method, an end-to-end trainable network, which reconstructs a densely-sampled LF in a coarse- to-fine manner, and produces densely-Sampled LFs with arbitrary angular resolution accurately and efficiently.
- 3
- 3
- 3
- Multiple description video coding based on adaptive data reuse3
Experimental results have shown that the proposed ADR-MDC scheme possesses higher error resilient ability and obtains better reconstructed video than the existing state-of-the-art MDC method.
- 2
- 2
- 2
- 2
- 2
- Focusing on pedestrians like human for clothes changing person re-identification2
This paper proposes a humanoid focus-inspired image augmentation (HFIA) method, which is intuitive image processing rather than a sophisticated network architecture designed to enhance local nuances of pedestrian images.
- 2
- 2
- Vehicle Re-identification Using Joint Pyramid Feature Representation Network2
The proposed JPFRN method obtains four vehicle feature blocks with different depths by designing pyramidal feature fusion of each convolution block in a basic network and is validated on a commonly used vehicle database.
- 2
- 2
- An Efficient Multiple Description Coding for Multi-View Video Based on the Correlation of Spatial Polyphase Transformed Subsequences2
An efficient multiple description coding for multi-view video based on the correlation of spatial polyphase transformed subsequences (CSPT_MDC_MVC) is proposed in this article and the effectiveness and robustness of the proposed algorithm is verified by experiments in the JMVC coding platform.
- Multi-task learning network for handwritten numeral recognition2
The determination of scratchy/non-scratchy in the writing style learning module can effectively assist the handwritten numeral learning module to obtain a more robust and distinguishable feature so as to improve the recognition performance.
- 2
- 2
- Multiple Description Coding for Multi-view Video2
A novel multiple description coding MDC scheme for multi-view video coding MVC is proposed that can deliver higher coding efficiency by separating one description into two subsequences and directly using the modes and prediction vectors computed during the encoding of one subsequence to the encoding process of the other subsequence from the same description.
- 2
- 2
- A Comprehensive Survey of Cross-Modal Retrieval: Breaking Through Modal Barriers1
This survey offers a comprehensive examination of cross-modal retrieval, starting with the fundamental concepts and significance of the field, and delves into various methods including supervised, unsupervised, and semi-supervised, categorized by the level of supervision.
- 1
- 1
- 1
- UDD: Unsupervised denoising diffusion for noisy multi-focus image fusion1
This work proposes an unsupervised denoising diffusion (UDD) framework for noise-robust fusion without relying on noise-specific training, and introduces three key components: an unsupervised pixel-space noise-aware conditional diffusion (NACD) that introduces a pixel-space conditional formulation, eliminating the need for explicit degradation matrices and their transformed-domain decomposition.
- 1
- 1
- 1
- 1
- A federated vehicle re-identification benchmark and performance optimization using dual-phase contrastive dynamic aggregation1
A dual-phase contrastive dynamic aggregation (DCDA) method is proposed, which adjusts aggregation weights based on model changes during training, allocating greater weights during significant early changes and smaller weights later, allowing clients with smaller datasets to effectively influence the model.
- 1
- 1
- 1
- Accelerating inter-frame prediction in Versatile Video Coding via deep learning-based mode selection1
- Global Instance Relation Distillation for convolutional neural network compression1
A Global Instance Relation Distillation (GIRD) for convolutional neural network compression is proposed, which improves both the instance-level and relation-level globality and outperforms state-of-the-art approaches in various visual tasks.
- 1
- 1
- Unimodal Model-Based Inter Mode Decision for High Efficiency Video Coding1
The extensive simulation results have shown that the proposed UMIMD algorithm is able to individually achieve a significant reduction on computational complexity at the encoder by 61.9% and 64.2% on average, compared with the exhaustive mode decision in the HEVC.
- 1
- 1
- Face Detection Based on Multi-block Quad Binary Pattern1
A novel local texture descriptor, called multi-block quad binary pattern (MB-QBP), is proposed, which has more features to conduct a better training process to refine the classifier and the over-fitting problem becomes much smaller in the MB-Q BP-based classifier.
- Efficient two-stage early SKIP mode termination for depth video coding1
Experimental results show that proposed algorithm significantly reduces computational complexity while keeping almost the same coding efficiency of depth video and quality of synthesized view, compared with exhaustive mode decision in multi-view video coding.
- –
- –
- –
- Uncertainty-driven Progressive Single Image De-raining–
The proposed Uncertainty-driven Progressive Single Image De-raining (UPSID) outperforms multiple state-of-the-art algorithms, including single-stage, progressive, and uncertainty-driven single image de-raining methods.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- NA-MMIF: a noise-agnostic multi-modal image fusion framework–
NA-MMIF consistently outperforms state-of-the-art fusion methods and denoise-then-fuse pipelines, particularly under challenging noise conditions, and is substantially outperforming the best competing fusion method by 19.5% and 9.9%, respectively.
- –
- Align What Truly Matters: Pedestrian‐Relevant Hierarchical Parsing Network for Text‐Based Person Retrieval–
This paper proposes a pedestrian‐relevant hierarchical parsing (PHP) module to extract well‐aligned fine‐grained visual and textual features for alignment, and designs an expert‐driven feature parsing (EFP) module, which integrates the representational power of a mixture of experts with a modality‐aware gating mechanism to uncover deep semantic associations between text and image features.
- –
- –
- –
- –
- –
- –
- –
- –
- Improved CNN Prediction Based Reversible Data Hiding–
An improved CNN predictor for reversible data hiding (RDH) in images, which consists of a feature extraction module, a pixel prediction module, and a complexity prediction module, which can achieve superior performance than the CNN predictor-based method.
- –
- –
- –
- An Adaptive Rate-Distortion Optimization Algorithm for HEVC-SCC with High Perceptual Quality–
Considering the characteristics of screen content video, an adaptive rate-distortion optimization algorithm based on CTU level of HEVC-SCC is proposed in this paper and an adaptive Lagrange operator is proposed to improve the rate- Distortion performance of the screencontent video coder.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Dual Cauchy rate-distortion model for video coding–
Experimental results have shown that the proposed model is better able to approximate the actual rate-distortion curve for various sequences with different motion activities.
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 2026-10-15. 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.