RealLiFe: Real-Time Light Field Reconstruction via Hierarchical Sparse Gradient Descent [0.03%]
基于分层稀疏梯度下降的实时光场重建方法
Yijie Deng,Lei Han,Tianpeng Lin et al.
Yijie Deng et al.
With the rise of Extended Reality (XR) technology, there is a growing need for real-time light field reconstruction from sparse view inputs. Existing methods can be classified into offline techniques, which can generate high-quality novel v...
Task-Specific Directions: Definition, Exploration, and Utilization in Parameter Efficient Fine-Tuning [0.03%]
任务特定方向：定义、探索和参数高效微调中的应用
Chongjie Si,Zhiyi Shi,Shifan Zhang et al.
Chongjie Si et al.
Large language models demonstrate impressive performance on downstream tasks, yet requiring extensive resource consumption when fully fine-tuning all parameters. To mitigate this, Parameter Efficient Fine-Tuning (PEFT) strategies, such as L...
Tackling Ill-Posedness of Reversible Image Conversion With Well-Posed Invertible Network [0.03%]
用适定可逆网络解决可逆图像转换的不适定问题
Yuanfei Huang,Hua Huang
Yuanfei Huang
Reversible image conversion (RIC) suffers from ill-posedness issues due to its forward conversion process being considered an underdetermined system. Despite employing invertible neural networks (INN), existing RIC methods intrinsically rem...
Liang Chen,Xianquan Zhang,Chunqiang Yu et al.
Liang Chen et al.
Secure and high-capacity secret information transmission is an important task of the image hiding research. The existing image hiding methods face some critical issues: cover-based methods offer high capacity but introduce image distortion ...
Privacy-Preserving Model Transcription With Differentially Private Synthetic Distillation [0.03%]
具有差异隐私合成蒸馏的保密模型转写
Bochao Liu,Shiming Ge,Pengju Wang et al.
Bochao Liu et al.
While many deep learning models trained on private datasets have been deployed in various practical tasks, they may pose a privacy leakage risk as attackers could recover informative data or label knowledge from models. In this work, we pre...
Fine-Grained Alignment Supervision Matters in Vision-and-Language Navigation [0.03%]
细粒度的对齐监督在视觉和语言导航中起重要作用
Keji He,Yan Huang,Ya Jing et al.
Keji He et al.
The Vision-and-Language Navigation (VLN) task involves an agent navigating within 3D indoor environments based on provided instructions. Achieving cross-modal alignment presents one of the most critical challenges in VLN, as the predicted t...
SEGA: A Transferable Signed Ensemble Gaussian Black-Box Attack Against No-Reference Image Quality Assessment Models [0.03%]
针对无参考图像质量评估模型的转移式有符号 ensemble 高斯黑盒攻击算法
Yujia Liu,Dingquan Li,Zhixuan Li et al.
Yujia Liu et al.
No-Reference Image Quality Assessment (NR-IQA) models play an important role in various real-world applications. Recently, adversarial attacks against NR-IQA models have attracted increasing attention, as they provide valuable insights for ...
Robust Matrix Completion With Deterministic Sampling Via Convex Optimization [0.03%]
基于凸优化的确定性取样稳健矩阵填充方法
Yinjian Wang,Wei Li,James E Fowler et al.
Yinjian Wang et al.
The problem of robust matrix completion-the recovery of a low-rank matrix and a sparse matrix from a sampling of their superposition-has been addressed extensively in prior literature. Yet, much of this work has focused exclusively on the c...
Yunfeng Ma,Min Liu,Shuai Jiang et al.
Yunfeng Ma et al.
Multimodal anomaly detection (MAD) aims to exploit both texture and spatial attributes to identify deviations from normal patterns in complex scenarios. However, zero-shot (ZS) settings arising from privacy concerns or confidentiality const...
Deeply Learned Robust Matrix Completion for Large-scale Low-rank Data Recovery [0.03%]
基于深度学习的大规模低秩数据恢复算法
HanQin Cai,Chandra Kundu,Jialin Liu et al.
HanQin Cai et al.
Robust matrix completion (RMC) is a widely used machine learning tool that simultaneously tackles two critical issues in low-rank data analysis: missing data entries and extreme outliers. This paper proposes a novel scalable and learnable n...