Generalizable Multi-modal Adversarial Imitation Learning for Non-stationary Dynamics [0.03%]
面向非平稳环境的泛化多模态对抗模仿学习
Yi-Chen Li,Ningjing Chao,Zongzhang Zhang et al.
Yi-Chen Li et al.
Imitation Learning (IL) learns from experts, on which most existing studies assume that the imitator will be deployed in stationary environments. However, real-world scenarios commonly involve perturbations, necessitating robust imitators f...
Yichen Li,Haozhao Wang,Yining Qi et al.
Yichen Li et al.
Federated learning (FL) has emerged as a significant distributed machine learning paradigm. It allows the training of a global model through user collaboration without the necessity of sharing their original data. Traditional FL generally a...
Deformable Graph Transformer [0.03%]
可变形图变换器
Jinyoung Park,Seongjun Yun,Hyeonjin Park et al.
Jinyoung Park et al.
Transformer-based models have recently shown success in representation learning on graph-structured data beyond natural language processing and computer vision. However, the success is limited to small-scale graphs due to the drawbacks of f...
Instant Gaussian Splatting Generation for High-Quality and Real-Time Facial Asset Rendering [0.03%]
即时高斯图元生成用于高质量和实时面部资产渲染
Dafei Qin,Hongyang Lin,Qixuan Zhang et al.
Dafei Qin et al.
Traditional and AI-driven modeling techniques enable high-fidelity 3D asset generation from scans, videos, or text prompts. However, editing and rendering these assets often involves a trade-off between quality and speed. In this paper, we ...
BackMix: Regularizing Open Set Recognition by Removing Underlying Fore-Background Priors [0.03%]
BackMix：通过去除潜在的前景背景先验来规范开放集识别
Yu Wang,Junxian Mu,Hongzhi Huang et al.
Yu Wang et al.
Open set recognition (OSR) requires models to classify known samples while detecting unknown samples for real-world applications. Existing studies show impressive progress using unknown samples from auxiliary datasets to regularize OSR mode...
Huaiwen Zhang,Yang Yang,Fan Qi et al.
Huaiwen Zhang et al.
Supervised Cross-Modal Retrieval (SCMR) achieves significant performance with the supervision provided by substantial label annotations of multi-modal data. However, the requirement for large annotated multi-modal datasets restricts the use...
LMP-GAN: Out-Of-Distribution Detection For Non-Control Data Malware Attacks [0.03%]
LMP-GAN：针对非控制数据恶意软件攻击的分布外检测
David Wood,David Kapp,Temesgen Kebede et al.
David Wood et al.
Anomaly detection is a common application of machine learning. Out-of-distribution (OOD) detection in particular is a semi-supervised anomaly detection technique where the detection method is trained only on the inlier (in-distribution) sam...
The NeRF Signature: Codebook-Aided Watermarking for Neural Radiance Fields [0.03%]
NeRF签名：用于神经辐射场的代码本辅助水印技术
Ziyuan Luo,Anderson Rocha,Boxin Shi et al.
Ziyuan Luo et al.
Neural Radiance Fields (NeRF) have been gaining attention as a significant form of 3D content representation. With the proliferation of NeRF-based creations, the need for copyright protection has emerged as a critical issue. Although some a...
Video4DGen: Enhancing Video and 4D Generation through Mutual Optimization [0.03%]
Video4DGen：通过相互优化增强视频和4D生成
Yikai Wang,Guangce Liu,Xinzhou Wang et al.
Yikai Wang et al.
The advancement of 4D (i.e., sequential 3D) generation opens up new possibilities for lifelike experiences in various applications, where users can explore dynamic objects or characters from any viewpoint. Meanwhile, video generative models...
Lei Yang,Tao Tang,Jun Li et al.
Lei Yang et al.
While most recent autonomous driving system focuses on developing perception methods on ego-vehicle sensors, people tend to overlook an alternative approach to leverage intelligent roadside cameras to extend the perception ability beyond th...