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
- Xiao-Ping Steven ZhangSuggested from co-authorship
- You YangSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works55 from public data
- 26
- 22
- 21
- Multi-intent autonomous decision-making for air combat with deep reinforcement learning21
The Temporal Proximal Policy Optimization (T-PPO) algorithm is proposed, which optimizes the ProXimal Policyoptimization algorithm by integrating the long short-term memory network and feedforward neural network and extracts the historical temporal information to enhance situational awareness.
- Bitstream-Corrupted Video Recovery: A Novel Benchmark Dataset and Method20
The BSCV is a collection of a proposed three-parameter corruption model for video bitstream, a large-scale dataset containing rich error patterns, multiple corruption levels, and flexible dataset branches, and a plug-and-play module in video recovery framework that serves as a benchmark.
- 17
- 17
- Block-wise focal stack image representation for end-to-end applications15
A block-wise Gaussian based representation model for FoSIs is proposed and utilize this model to solve the problem of coding, reconstruction and rendering for end-to-end applications.
- End-to-end varifocal multiview images coding framework from data acquisition end to vision application end14
An end-to-end coding scheme for V FMV images is proposed, which provides a new paradigm for VFMV compression from data acquisition (source) end to vision application end, and extensive experiments demonstrate that the proposed coding scheme is superior to the comparison scheme in objective quality, subjective quality and computational complexity.
- A Byte Sequence is Worth an Image: CNN for File Fragment Classification Using Bit Shift and n-Gram Embeddings13
This work proposes Byte2Image, a novel data augmentation technique, to introduce the neglected intra-byte information into file fragments and re-treat them as 2d gray-scale images, which allows us to capture both inter-byte and intra- byte correlations simultaneously through powerful convolutional neural networks (CNNs).
- 12
- 12
- PromptSR: Cascade Prompting for Lightweight Image Super-Resolution10
The experimental results demonstrate the superiority of the PromptSR method, which outperforms state-of-the-art lightweight SR methods in quantitative, qualitative, and complexity evaluations.
- 10
- ASIFusion: An Adaptive Saliency Injection-Based Infrared and Visible Image Fusion Network9
This work presents ASIFusion, an adaptive saliency injection-based IVIF network that outperforms state-of-the-art (SOTA) approaches with regard to fusion performance and computational efficiency.
- 8
- Multifocal multiview imaging and data compression based on angular–focal–spatial representation8
To efficiently compress MFMV data, the first, to the authors' knowledge, MFMV data compression scheme based on angular-focal-spatial representation is proposed, which exploits inter-view, inter-stack, and intra-frame predictions to eliminate data redundancy in angular, focal, and spatial dimensions, respectively.
- Multi-Scale Dynamic Fusion for Visible-Infrared Person Re-Identification7
A Multi-scale Dynamic Fusion Network (MDFN) to address challenges in the VI-ReID task, which outperforms other state-of-the-art methods, especially in complex dynamic scenes with occlusions, background shifts, and pose changes.
- 7
- 7
- Building Egocentric Procedural AI Assistant: Methods, Benchmarks, and Challenges6
This paper identifies three core tasks in EgoProceAssist: egocentric procedural error detection, egocentric procedural learning, and egocentric procedural question answering, and introduces two enabling dimensions: real-time and streaming video understanding, and proactive interaction in procedural contexts.
- Towards Blind Bitstream-corrupted Video Recovery: A Visual Foundation Model-driven Framework6
This paper proposes the first blind bitstream-corrupted video recovery framework that integrates visual foundation models with recovery model, which is adapted to different types of corruption and bitstream-level prompts and introduces a novel Corruption-aware Feature Completion (CFC) module.
- Las-yolo: a lightweight detection method based on YOLOv7 for small objects in airport surveillance6
A lightweight airport surveillance detection based on YOLOv7 named LAS-YOLO is proposed, which significantly reduces network parameters while retaining certain local features and the attention mechanism and small object detection layer are introduced to enhance small object detection accuracy.
- 5
- Rapid detection and social media supervision of runway incursion based on deep learning5
The experimental result shows that the airport target detection based on optimised YOLO has excellent fastness and accuracy.
- 4
- 4
- 4
- Dedark+Detection: A Hybrid Scheme for Object Detection under Low-light Surveillance4
A hybrid method that jointly use enhancement and object detection for the above challenge, namely Dedark+Detection is proposed, and superior performance can be found when comparing to state-of-the-arts.
- From Semantics, Scene to Instance-awareness: Distilling Foundation Model for Open-vocabulary Grounded Situation Recognition3
This paper proposes Multimodal Interactive Prompt Distillation (MIPD), a novel framework that distills enriched multimodal knowledge from the foundation model, enabling the student Ov-GSR model to recognize unseen situations and be better aware of rare situations.
- An improved personal protective equipment detection method based on YOLOv43
An enhanced face mask detection method based on YOLOv4 is presented and a modified face mask detection model called MaskYOLO is introduced, which includes improvements in the original YOLOv4 network structure.
- WaRENet: A Novel Urban Waterlogging Risk Evaluation Network3
A novel urban waterlogging risk evaluation network (WaRENet) is proposed to evaluate the risk of waterlogging and incorporates switchable atrous convolution (SAC) into YOLOv5 to solve occlusions and varying scales problems in complex waterlogging scenes.
- 3
- 3
- 2
- Design of Multimedia Education and Teaching Management System based on Artificial Intelligence and Computational Technology2
The analysis shows that the IMTTS can change educational management by providing reliable solutions that address present issues and meet evolving educational needs, and highlights the system’s capacity to handle compute needs that scale.
- HACRNet: hierarchical attention compression for high-speed fine-grained ship recognition2
A novel Hierarchical Attention Compression Network (HACRNet) is proposed that introduces a Spatial-Reduction Multi-Head Attention (SR-MSA) module that progressively reduces feature resolution, significantly lowering computational complexity and enhancing recognition efficiency.
- 2
- 1
- From Semantics, Scene to Instance-awareness: Distilling Foundation Model for Grounded Open-vocabulary Situation Recognition1
This paper proposes Multimodal Interactive Prompt Distillation (MIPD), a novel framework that distills enriched multimodal knowledge from the foundation model, enabling the student Ov-GSR model to recognize unseen situations and be better aware of rare situations.
- 1
- Risk factors for corneal nerve fiber loss in Chinese patients with type 2 diabetes mellitus1
HbA1c, CV, and LDL-C levels are independently associated with CNFL in T2DM patients and these may accordingly serve as intervention targets for the early DPN prevention and treatment.
- 1
- 1
- Target-aware pooling combining global contexts for aerial tracking1
This paper designs a tracker called TAP-GC that utilizes a weight-sharing deep CNN network to extract the multi-scale template and test features, and constructs a target-aware pooling module in the template branch, allowing the tracker to pay more attention to the target-related information.
- Video sentence grounding with temporally global textual knowledge1
A Pseudo-query Intermediary Network (PIN) is proposed to achieve an improved alignment of visual and comprehensive pseudo-query features within the feature space through contrastive learning and enhances the feature alignment between visual and language for better temporal grounding.
- Dynamic texture segmentation using spectral clustering based on CHMMs1
The spectral clustering method based on Continuous Hidden Markov Model (CHMM) into dynamic texture (DT) segmentation is introduced and results on artificially synthesized DT samples of DynTex dataset demonstrate the effectiveness of the proposed method.
- –
- –
- Extending Depth of Field for Varifocal Multiview Images–
This work proposes an end-to-end method for the EDoF of varifocal multiview images, including image alignment, image optimization and image fusion, and results demonstrate the efficiency of the proposed method.
- Convex hull regression strategy for people detection on top-view fisheye images–
This work proposes a Convex Hull Regression Strategy for people detection on top-view fisheye images that replaces the instance with its convex hull to solve the above challenging issue and can be pre-trained on regular datasets without additional processing.
- –
- –
- –
- –
Publication data from OpenAlex; 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.