Once Detected, Never Lost: Surpassing Human Performance in Offline LiDAR based 3D Object Detection

Kavli Affiliate: Feng Wang | First 5 Authors: Lue Fan, Yuxue Yang, Yiming Mao, Feng Wang, Yuntao Chen | Summary: This paper aims for high-performance offline LiDAR-based 3D object detection. We first observe that experienced human annotators annotate objects from a track-centric perspective. They first label the objects with clear shapes in a track, and […]


Continue.. Once Detected, Never Lost: Surpassing Human Performance in Offline LiDAR based 3D Object Detection

Non-linear optics at twist interfaces in h-BN/SiC heterostructures

Kavli Affiliate: Xiang Zhang | First 5 Authors: Abhijit Biswas, Rui Xu, Gustavo A. Alvarez, Jin Zhang, Joyce Christiansen-Salameh | Summary: Understanding the emergent electronic structure in twisted atomically thin layers has led to the exciting field of twistronics. However, practical applications of such systems are challenging since the specific angular correlations between the layers […]


Continue.. Non-linear optics at twist interfaces in h-BN/SiC heterostructures

Imaging 3D Chemistry at 1 nm Resolution with Fused Multi-Modal Electron Tomography

Kavli Affiliate: Ting Xu | First 5 Authors: Jonathan Schwartz, Zichao Wendy Di, Yi Jiang, Jason Manassa, Jacob Pietryga | Summary: Measuring the three-dimensional (3D) distribution of chemistry in nanoscale matter is a longstanding challenge for metrological science. The inelastic scattering events required for 3D chemical imaging are too rare, requiring high beam exposure that […]


Continue.. Imaging 3D Chemistry at 1 nm Resolution with Fused Multi-Modal Electron Tomography

TTIDA: Controllable Generative Data Augmentation via Text-to-Text and Text-to-Image Models

Kavli Affiliate: Xiang Zhang | First 5 Authors: Yuwei Yin, Jean Kaddour, Xiang Zhang, Yixin Nie, Zhenguang Liu | Summary: Data augmentation has been established as an efficacious approach to supplement useful information for low-resource datasets. Traditional augmentation techniques such as noise injection and image transformations have been widely used. In addition, generative data augmentation […]


Continue.. TTIDA: Controllable Generative Data Augmentation via Text-to-Text and Text-to-Image Models

Self-Supervised Scene Dynamic Recovery from Rolling Shutter Images and Events

Kavli Affiliate: Xiang Zhang | First 5 Authors: Yangguang Wang, Xiang Zhang, Mingyuan Lin, Lei Yu, Boxin Shi | Summary: Scene Dynamic Recovery (SDR) by inverting distorted Rolling Shutter (RS) images to an undistorted high frame-rate Global Shutter (GS) video is a severely ill-posed problem, particularly when prior knowledge about camera/object motions is unavailable. Commonly […]


Continue.. Self-Supervised Scene Dynamic Recovery from Rolling Shutter Images and Events

Hamiltonian Switching Control of Noisy Bipartite Qubit Systems

Kavli Affiliate: K. Birgitta Whaley | First 5 Authors: Zhibo Yang, Robert L. Kosut, K. Birgitta Whaley, , | Summary: We develop a Hamiltonian switching ansatz for bipartite control that is inspired by the Quantum Approximate Optimization Algorithm (QAOA), to mitigate environmental noise on qubits. We illustrate the approach with application to the protection of […]


Continue.. Hamiltonian Switching Control of Noisy Bipartite Qubit Systems

Enhancing Clinical Evidence Recommendation with Multi-Channel Heterogeneous Learning on Evidence Graphs

Kavli Affiliate: Xiang Zhang | Authors: Maolin Luo, Xiang Zhang | Summary: Clinical evidence encompasses the associations and impacts between patients, interventions (such as drugs or physiotherapy), problems, and outcomes. The goal of recommending clinical evidence is to provide medical practitioners with relevant information to support their decision-making processes and to generate new evidence. Our […]


Continue.. Enhancing Clinical Evidence Recommendation with Multi-Channel Heterogeneous Learning on Evidence Graphs

Action Pick-up in Dynamic Action Space Reinforcement Learning

Kavli Affiliate: Feng Wang | Authors: Jiaqi Ye, Xiaodong Li, Pangjing Wu, Feng Wang | Summary: Most reinforcement learning algorithms are based on a key assumption that Markov decision processes (MDPs) are stationary. However, non-stationary MDPs with dynamic action space are omnipresent in real-world scenarios. Yet problems of dynamic action space reinforcement learning have been […]


Continue.. Action Pick-up in Dynamic Action Space Reinforcement Learning

A Hierarchical Multi-Vehicle Coordinated Motion Planning Method based on Interactive Spatio-Temporal Corridors

Kavli Affiliate: Xiang Zhang | Authors: Xiang Zhang, Boyang Wang, Yaomin Lu, Haiou Liu, Jianwei Gong, Huiyan Chen | Summary: Multi-vehicle coordinated motion planning has always been challenged to safely and efficiently resolve conflicts under non-holonomic dynamic constraints. Constructing spatial-temporal corridors for multi-vehicle can decouple the high-dimensional conflicts and further reduce the difficulty of obtaining […]


Continue.. A Hierarchical Multi-Vehicle Coordinated Motion Planning Method based on Interactive Spatio-Temporal Corridors

Weakly-Supervised Text-driven Contrastive Learning for Facial Behavior Understanding

Kavli Affiliate: Xiang Zhang | First 5 Authors: Xiang Zhang, Taoyue Wang, Xiaotian Li, Huiyuan Yang, Lijun Yin | Summary: Contrastive learning has shown promising potential for learning robust representations by utilizing unlabeled data. However, constructing effective positive-negative pairs for contrastive learning on facial behavior datasets remains challenging. This is because such pairs inevitably encode […]


Continue.. Weakly-Supervised Text-driven Contrastive Learning for Facial Behavior Understanding