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
- Zhen YangSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works174 from public data
- Review of Visual Saliency Detection With Comprehensive Information419
Different types of saliency detection algorithms are reviewed, the important issues of the existing methods are summarized, the existent problems and future works are discussed, and the experimental analysis and discussion are conducted to provide a holistic overview of differentSaliency detection methods.
- Saliency Detection for Stereoscopic Images Based on Depth Confidence Analysis and Multiple Cues Fusion235
A measure to evaluate the reliability of depth map, and use it to reduce the influence of poor depth map on saliency detection, and two saliency maps are integrated into a final saliency map through weighted-sum method according to their importance.
- 215
- 150
- 123
- An Iterative Co-Saliency Framework for RGBD Images123
An iterative RGBD co-saliency framework is proposed, which utilizes the existing single saliency maps as the initialization, and generates the final RGBD Co-Saliency map by using a refinement-cycle model.
- 113
- HSCS: Hierarchical Sparsity Based Co-saliency Detection for RGBD Images104
A novel co-saliency detection method for RGBD images based on hierarchical sparsity reconstruction and energy function refinement is proposed, which outperforms the state-of-the-art algorithms both qualitatively and quantitatively.
- 103
- 100
- 98
- Fast reference frame selection based on content similarity for low complexity HEVC encoder93
A fast reference frame selection algorithm for the HEVC encoder that efficiently removes the encoding complexity of the best reference frame decision process and the rate distortion performance degradation is negligible.
- 92
- 90
- 87
- Transferred deep learning based waveform recognition for cognitive passive radar81
A novel transferred deep learning waveform recognition method which makes use of multi-scale convolution and temporal dependency characteristics to improve the recognition performance and significantly outperforms the state-of-the-art methods.
- 80
- Joint spatial-spectral hyperspectral image classification based on convolutional neural network72
Experimental results on two datasets demonstrate that the proposed joint spatial-spectral hyperspectral image classification method outperforms other state-of-the-art methods qualitatively and quantitatively.
- 71
- Adaptive Fractional-Pixel Motion Estimation Skipped Algorithm for Efficient HEVC Motion Estimation69
An adaptive fractional-pixel ME skipped scheme is proposed for low-complexity HEVC ME, which reduces ME encoding time by an average of 63.22% while encoding efficiency performance is maintained.
- 64
- 63
- 62
- Semi-Heterogeneous Three-Way Joint Embedding Network for Sketch-Based Image Retrieval61
A novel semi-heterogeneous three-way joint embedding network (Semi3-Net) is proposed, which integrates three branches (a sketch branch, a natural image branch, and an edgemap branch) to learn more discriminative cross-domain feature representations for the SBIR task.
- 59
- 56
- 56
- No-reference stereoscopic image quality assessment based on global and local content characteristics54
This paper proposes a no-reference stereoscopic image quality assessment method based on global and local content characteristics, and derives features from the fused view and single view through the global feature fusion sub-network and local feature enhancement sub- network.
- 54
- 53
- PSNet: Parallel Symmetric Network for Video Salient Object Detection52
A VSOD network with up and down parallel symmetry, named PSNet is proposed and the Importance Perception Fusion (IPF) module is used to fuse the features from two parallel branches according to their different importance in different scenarios.
- 50
- 49
- 47
- 46
- 43
- Keyword extraction by entropy difference between the intrinsic and extrinsic mode40
A new metric to evaluate and rank the relevance of words in a text using the Shannon’s entropy difference between the intrinsic and extrinsic mode is proposed, suitable for single documents of which there is no a priori information available.
- Color-Guided Depth Map Super Resolution Using Convolutional Neural Network39
A dual-stream convolutional neural network, which integrates the color and depth information simultaneously, is proposed for depth map super resolution and experimental results demonstrate the effectiveness of the proposed method compared with the state-of-the-art methods.
- 37
- 37
- 36
- Modeling Long-range Dependencies and Epipolar Geometry for Multi-view Stereo35
This article proposes a network, referred to as Multi-View Stereo TRansformer (MVSTR), capable of extracting dense features with global context and 3D consistency, which are crucial for reliable matching in multi-view stereo (MVS).
- Deep video action clustering via spatio-temporal feature learning34
A novel deep video action clustering network which aims to learn the similarity relationship among the unlabeled video samples, and generate the clustering label for each video sample under a jointly optimized framework is proposed.
- 34
- 33
- Person Re-Identification by Semantic Region Representation and Topology Constraint33
A novel person re-identification method is proposed, which consists of a reliable representation called semantic region representation (SRR), and an effective metric learning with mapping space topology constraint (MSTC).
- 32
- 32
- 31
- Deep Stereo Image Compression via Bi-directional Coding28
Experimental results on the InStereo2K and KITTI datasets demonstrate that the proposed BCSIC-Net can effectively reduce the inter-view redundancy and out-performs state-of-the-art methods.
- 27
- Saliency-based stereoscopic image retargeting27
Experimental results have shown that both the stereoscopic saliency detection and image retargeting methods can obtain better performance than the existing related methods on the public databases.
- New metric for stereo image quality assessment based on HVS27
The experimental results are presented to show that the proposed metric provides results consistent with the subjective assessment and thus can be employed to reflect image quality and stereo sense.
- 25
- Multi-Projection Fusion and Refinement Network for Salient Object Detection in 360° Omnidirectional Image25
Experimental results on two omnidirectional datasets demonstrate that the proposed approach outperforms the state-of-the-art methods both qualitatively and quantitatively.
- 25
- 25
- 24
- Shape-Preserving Object Depth Control for Stereoscopic Images24
Experimental results show that the proposed shape-preserving object depth control method can control object depth and preserve the shape of the object effectively without sensible background distortion.
- View generation with DIBR for 3D display system24
Experimental results show that the proposed novel virtual view rendering method based on DIBR can obtain high-quality virtual view images and achieve satisfactory subjective visual effects.
- 23
- Evaluation and modeling of depth feature incorporated visual attention for salient object segmentation23
This work compares previously proposed saliency models and proposes a new depth feature incorporated saliency model focusing on suppression of background saliency through piecewise function, which outperforms existing depth feature combination methods on the precision rate, when evaluated using the ground truth.
- 22
- 20
- Edge-Guided Cross-Domain Learning with Shape Regression for Sketch-Based Image Retrieval20
By training the proposed network in an end-to-end process, the sketch and natural image domains can be effectively associated, which potentially overcomes the challenge of the common feature learning for two heterogeneous domains.
- 20
- 19
- The objective quality assessment of stereo image19
A new quality assessment method of evaluating the performance of stereo images from the perspective of image quality and stereo sense based on objective quality assessment of 2D image and absolute disparity image is proposed.
- 18
- 18
- 17
- 16
- 16
- 16
- 16
- 15
- 14
- 14
- 14
- RGB-D salient object detection via cross-modal joint feature extraction and low-bound fusion loss14
A novel RGB-D salient object detection method via cross-modal joint feature extraction and low-bound fusion loss, designed to constrain the predictions of the two streams, to improve the lower bound of saliency values and generate a distinct saliency map.
- Learning visual saliency from human fixations for stereoscopic images14
A novel stereoscopic saliency detection algorithm by machine learning technique that can predict better saliency results for stereoscopic images than other existing ones is designed.
- A divide-and-conquer hole-filling method for handling disocclusion in single-view rendering14
A divide-and-conquer hole-filling method which refines the background depth pixels around the sharp depth discontinuities to address the disocclusion problem and can effectively improve the quality of the synthesized view subjectively and objectively.
- 13
- Self-Supervised Monocular Depth Estimation via Binocular Geometric Correlation Learning12
A binocular cue prediction module is presented to generate the auxiliary vision cue for the self-supervised learning of monocular depth estimation and an occlusion interference attenuated constraint is developed to guide the supervision of the network.
- 12
- 12
- 12
- 12
- 12
- 11
- Rate control of hierarchical B prediction structure for multi-view video coding11
An enhanced prediction method is proposed in which a proportional relationship of the header bits is introduced if the frames are located in different TLs and can achieve both accurate target bit rate and good coding performance.
- 11
- 10
- Unsupervised stereoscopic image retargeting via view synthesis and stereo cycle consistency losses10
An unsupervised stereoscopic image retargeting network (USIR-Net), which consists of a content consistency term and a disparity consistency term, is proposed to preserve the structure information and prevent binocular disparity inconsistency and achieves superior performance compared with state-of-the-art methods.
- 10
- Early DIRECT mode decision based on all‐zero block and rate distortion cost for multiview video coding10
An early DIRECT mode decision method based on the property of the all-zero block and rate distortion (RD) cost of the DIRECT mode as well as the correlations between the current macroblock and its spatial–temporal nearby MBs is proposed for reducing the encoding complexity of the MVC.
- 9
- 9
- 9
- 9
- 8
- 8
- 8
- 8
- 8
- 7
- 7
- 7
- Novel View Synthesis from a Single Unposed Image via Unsupervised Learning7
Experiments on the widely used view synthesis datasets have demonstrated that the proposed network is able to produce comparable results to the state-of-the-art methods despite the fact that learning is unsupervised and only a single source image is required for generating a novel view.
- 7
- 7
- 7
- 6
- 6
- 6
- 5
- 5
- 5
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- Meta-Learned Zero-Shot Sketch-Based Point Cloud Retrieval via Perspective-Predicted Feature Learning–
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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 2026-10-16. 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.