Explanipedia

NAIPv2: Debiased Pairwise Learning for Efficient Paper Quality Estimation Open

Penghai Zhao, Jinyu Tian, Qinghua Xing, Xin Zhang, Zhizhong Li , et al. · 2025

The ability to estimate the quality of scientific papers is central to how both humans and AI systems will advance scientific knowledge in the future. However, existing LLM-based estimation methods suffer from high inference cost, whereas …

AGSwap: Overcoming Category Boundaries in Object Fusion via Adaptive Group Swapping Open

Zedong Zhang, Ying Tai, Jianjun Qian, Jian Yang, Jun Li · 2025

Fusing cross-category objects to a single coherent object has gained increasing attention in text-to-image (T2I) generation due to its broad applications in virtual reality, digital media, film, and gaming. However, existing methods often …

NaviFormer: A Spatio-Temporal Context-Aware Transformer for Object Navigation Open

Wei Xie, Hai Jiang, Yun Zhu, Jianjun Qian, Jin Xie · 2025

Learning discriminative state representations of agents, encompassing the spatial layout and temporal pose trajectory, is essential for effective navigation decisions. However, existing approaches often rely on simplistic plain networks fo…

Learning Generalized Residual Exchange-Correlation-Uncertain Functional for Density Functional Theory Open

Shuanggen Jin, Shuo Chen, Jianjun Qian, Ying Tai, Jun Li · 2025

Density Functional Theory (DFT) stands as a widely used and efficient approach for addressing the many-electron Schrödinger equation across various domains such as physics, chemistry, and biology. However, a core challenge that persists ov…

Innovative applications of visualized thermosensitive color-changing personalized boluses in post-mastectomy radiotherapy: a dosimetric analysis Open

Yong Wang, Fujing Huang, Wei Han, Jianjun Qian, Peifeng Zhao , et al. · 2025

Robust style injection for person image synthesis Open

Yan Huang, Jianjun Qian, Shumin Zhu, Jun Li, Jian Yang · 2025

Person Image Synthesis has been widely used in fashion with extensive application scenarios. The point of this task is how to synthesise person image from a single source image under arbitrary poses. Prior methods generate the person image…

Fd-Avatar: Faster and Detailed 3d Head Avatars Reconstruction Open

Haijie Yang, Zhenyu Zhang, Jianjun Qian, Jian Yang · 2025

Learning Generalized Residual Exchange-Correlation-Uncertain Functional for Density Functional Theory Open

Shuanggen Jin, Shuo Chen, Jianjun Qian, Ying Tai, Jun Li · 2024

Density Functional Theory (DFT) stands as a widely used and efficient approach for addressing the many-electron Schrödinger equation across various domains such as physics, chemistry, and biology. However, a core challenge that persists ov…

ConsistentAvatar: Learning to Diffuse Fully Consistent Talking Head Avatar with Temporal Guidance Open

Haijie Yang, Zhenyu Zhang, Hao Tang, Jianjun Qian, Jian Yang · 2024

Diffusion models have shown impressive potential on talking head generation. While plausible appearance and talking effect are achieved, these methods still suffer from temporal, 3D or expression inconsistency due to the error accumulation…

Text2LiDAR: Text-guided LiDAR Point Cloud Generation via Equirectangular Transformer Open

Yang Wu, Kaihua Zhang, Jianjun Qian, Jin Xie, Jian Yang · 2024

The complex traffic environment and various weather conditions make the collection of LiDAR data expensive and challenging. Achieving high-quality and controllable LiDAR data generation is urgently needed, controlling with text is a common…

MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space Open

Jiangwei Weng, Zhiqiang Yan, Ying Tai, Jianjun Qian, Jian Yang , et al. · 2024

Recent advances in low light image enhancement have been dominated by Retinex-based learning framework, leveraging convolutional neural networks (CNNs) and Transformers. However, the vanilla Retinex theory primarily addresses global illumi…

Driving-Video Dehazing with Non-Aligned Regularization for Safety Assistance Open

Junkai Fan, Jiangwei Weng, Kun Wang, Yi-Jun Yang, Jianjun Qian , et al. · 2024

Real driving-video dehazing poses a significant challenge due to the inherent difficulty in acquiring precisely aligned hazy/clear video pairs for effective model training, especially in dynamic driving scenarios with unpredictable weather…

The relationship between splenic dose and radiation-induced lymphopenia Open

Yifu Ma, Yuehong Kong, Shuying Zhang, Yong Peng, Meiling Xu , et al. · 2024

Lymphocytes, which are highly sensitive to radiation, play a crucial role in the body’s defense against tumors. Radiation-induced lymphopenia has been associated with poorer outcomes in different cancer types. Despite being the largest sec…

Contrastive Subspace Distribution Learning for Novel Category Discovery in High-Dimensional Visual Data Open

Shuai Wei, Shuo Chen, Guangyu Li, Jianjun Qian, Jian Yang , et al. · 2024

Ragnet3d: Learning Distinguishable Representation for Pooled Grids in 3d Object Detection Open

Jiaxin Chen, Yuehui Han, Zhiqiang Yan, Jianjun Qian, Jun Li , et al. · 2024

Recurrent Structure Attention Guidance for Depth Super-resolution Open

Jiayi Yuan, Haobo Jiang, Xiang Li, Jianjun Qian, Jun Li , et al. · 2023

Image guidance is an effective strategy for depth super-resolution. Generally, most existing methods employ hand-crafted operators to decompose the high-frequency (HF) and low-frequency (LF) ingredients from low-resolution depth maps and g…

Structure Flow-Guided Network for Real Depth Super-resolution Open

Jiayi Yuan, Haobo Jiang, Xiang Li, Jianjun Qian, Jun Li , et al. · 2023

Real depth super-resolution (DSR), unlike synthetic settings, is a challenging task due to the structural distortion and the edge noise caused by the natural degradation in real-world low-resolution (LR) depth maps. These defeats result in…

Non-aligned supervision for Real Image Dehazing Open

Junkai Fan, Fei Guo, Jianjun Qian, Xiang Li, Jun Li , et al. · 2023

Removing haze from real-world images is challenging due to unpredictable weather conditions, resulting in the misalignment of hazy and clear image pairs. In this paper, we propose an innovative dehazing framework that operates under non-al…

Recurrent Structure Attention Guidance for Depth Super-Resolution Open

Jiayi Yuan, Haobo Jiang, Xiang Li, Jianjun Qian, Jun Li , et al. · 2023

Image guidance is an effective strategy for depth super-resolution. Generally, most existing methods employ hand-crafted operators to decompose the high-frequency (HF) and low-frequency (LF) ingredients from low-resolution depth maps and g…

Structure Flow-Guided Network for Real Depth Super-Resolution Open

Jiayi Yuan, Haobo Jiang, Xiang Li, Jianjun Qian, Jun Li , et al. · 2023

Real depth super-resolution (DSR), unlike synthetic settings, is a challenging task due to the structural distortion and the edge noise caused by the natural degradation in real-world low-resolution (LR) depth maps. These defeats result in…

Dual Feature Disentanglement for Face Anti-Spoofing Open

Yimei Ma, Jianjun Qian, Jun Li, Jian Yang · 2023

Cascading Enhancement Representation for Face Anti-Spoofing Open

Yimei Ma, Yangwei Dong, Jianjun Qian, Wai Keung Wong, Jian Yang · 2023

An extensive bioinformatics study on the role of mitochondrial solute carrier family 25 in PC and its mechanism behind affecting immune infiltration and tumor energy metabolism Open

Qiang Zhang, Yubao Tang, Shuai Sun, Qiuyi Xie, Jie Yao , et al. · 2022

RecNet: A Resource-Constraint Aware Neural Network for Used Car Recommendation Open

Haihua Shi, Jianjun Qian, Nengjun Zhu, Tong Zhang, Zhen Cui , et al. · 2022

Resource constraints, e.g., limited product inventory or financial strength, may affect consumers’ choices or preferences in some recommendation tasks but are usually ignored in previous recommendation methods. In this paper, we aim to min…

Unsupervised Domain Adaptation for Point Cloud Semantic Segmentation via Graph Matching Open

Yikai Bian, Le Hui, Jianjun Qian, Jin Xie · 2022

Unsupervised domain adaptation for point cloud semantic segmentation has attracted great attention due to its effectiveness in learning with unlabeled data. Most of existing methods use global-level feature alignment to transfer the knowle…

Generative Subgraph Contrast for Self-Supervised Graph Representation Learning Open

Yuehui Han, Le Hui, Haobo Jiang, Jianjun Qian, Jin Xie · 2022

Contrastive learning has shown great promise in the field of graph representation learning. By manually constructing positive/negative samples, most graph contrastive learning methods rely on the vector inner product based similarity metri…

Cross-view panorama image synthesis with progressive attention GANs Open

Songsong Wu, Hao Tang, Xiao‐Yuan Jing, Jianjun Qian, Nicu Sebe , et al. · 2022

Linearity-Aware Subspace Clustering Open

Yesong Xu, Shuo Chen, Jun Li, Jianjun Qian · 2022

Obtaining a good similarity matrix is extremely important in subspace clustering. Current state-of-the-art methods learn the similarity matrix through self-expressive strategy. However, these methods directly adopt original samples as a se…

OTFace: Hard Samples Guided Optimal Transport Loss for Deep Face Representation Open

Jianjun Qian, Shumin Zhu, Chaoyu Zhao, Jian Yang, Wai Keung Wong · 2022

Face representation in the wild is extremely hard due to the large scale face variations. To this end, some deep convolutional neural networks (CNNs) have been developed to learn discriminative feature by designing properly margin-based lo…

Cross-View Panorama Image Synthesis Open

Songsong Wu, Hao Tang, Xiao‐Yuan Jing, Haifeng Zhao, Jianjun Qian , et al. · 2022

In this paper, we tackle the problem of synthesizing a ground-view panorama image conditioned on a top-view aerial image, which is a challenging problem due to the large gap between the two image domains with different view-points. Instead…

Jianjun Qian YOU? Author Swipe