180 citations · 420 across the 29 of their papers we have counts for
29 papers
D-Separation for Causal Self-Explanation
Wei Liu, Jun Wang, Haozhao Wang +4
Rationalization is a self-explaining framework for NLP models. Conventional work typically uses the maximum mutual information (MMI) criterion to find the rationale that is most in…
The Robust Semantic Segmentation UNCV2023 Challenge Results
Xuanlong Yu, Yi Zuo, Zitao Wang +34
This paper outlines the winning solutions employed in addressing the MUAD uncertainty quantification challenge held at ICCV 2023. The challenge was centered around semantic segment…
OFVL-MS: Once for Visual Localization across Multiple Indoor Scenes
Tao Xie, Kun Dai, Siyi Lu +7
In this work, we seek to predict camera poses across scenes with a multi-task learning manner, where we view the localization of each scene as a new task. We propose OFVL-MS, a uni…
Decoupled Rationalization with Asymmetric Learning Rates: A Flexible Lipschitz Restraint
Wei Liu, Jun Wang, Haozhao Wang +5
A self-explaining rationalization model is generally constructed by a cooperative game where a generator selects the most human-intelligible pieces from the input text as rationale…
Sharp upper bounds for the capacity in the hyperbolic and Euclidean spaces
Haizhong Li, Ruixuan Li, Changwei Xiong
We derive various sharp upper bounds for the -capacity of a smooth compact set in the hyperbolic space and the Euclidean space . Firstly, using…
Dual-modality Smart Shoes for Quantitative Assessment of Hemiplegic Patients' Lower Limbs' Muscle Strength
Huajun Long, Jie Li, Rui Li +2
Stroke can lead to the impaired motor ability of the patient's lower limbs and hemiplegia. Accurate assessment of the lower limbs' motor ability is important for diagnosis and reha…
CSGCL: Community-Strength-Enhanced Graph Contrastive Learning
Han Chen, Ziwen Zhao, Yuhua Li +3
Graph Contrastive Learning (GCL) is an effective way to learn generalized graph representations in a self-supervised manner, and has grown rapidly in recent years. However, the und…
MGR: Multi-generator Based Rationalization
Wei Liu, Haozhao Wang, Jun Wang +4
Rationalization is to employ a generator and a predictor to construct a self-explaining NLP model in which the generator selects a subset of human-intelligible pieces of the input…
LSwinSR: UAV Imagery Super-Resolution based on Linear Swin Transformer
Rui Li, Xiaowei Zhao
Super-resolution, which aims to reconstruct high-resolution images from low-resolution images, has drawn considerable attention and has been intensively studied in computer vision…
Structural phase transitions and superconductivity in the Heusler intermetallics PdSn ( = Ti, Zr, Hf)
Hang Su, Feng Du, Rui Li +7
We report the discovery of structural phase transitions and superconductivity in the full Heusler compounds PdSn ( = Ti, Zr, Hf), by means of electrical transport, magnet…
Pillar R-CNN for Point Cloud 3D Object Detection
Guangsheng Shi, Ruifeng Li, Chao Ma
The performance of point cloud 3D object detection hinges on effectively representing raw points, grid-based voxels or pillars. Recent two-stage 3D detectors typically take the poi…
Adaptive Low-Precision Training for Embeddings in Click-Through Rate Prediction
Shiwei Li, Huifeng Guo, Lu Hou +5
Embedding tables are usually huge in click-through rate (CTR) prediction models. To train and deploy the CTR models efficiently and economically, it is necessary to compress their…
Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigation
Yixiong Zou, Shanghang Zhang, Yuhua Li +1
Few-shot class-incremental learning (FSCIL) is designed to incrementally recognize novel classes with only few training samples after the (pre-)training on base classes with suffic…
Two-band description of the strong `spin'-orbit coupled one-dimensional hole gas in a cylindrical Ge nanowire
Rui Li, Xin-Yu Qi
The low-energy effective Hamiltonian of the strong `spin'-orbit coupled one-dimensional hole gas in a cylindrical Ge nanowire in the presence of a strong magnetic field is studied…
FR: Folded Rationalization with a Unified Encoder
Wei Liu, Haozhao Wang, Jun Wang +3
Conventional works generally employ a two-phase model in which a generator selects the most important pieces, followed by a predictor that makes predictions based on the selected p…
Hierarchical Local-Global Transformer for Temporal Sentence Grounding
Xiang Fang, Daizong Liu, Pan Zhou +2
This paper studies the multimedia problem of temporal sentence grounding (TSG), which aims to accurately determine the specific video segment in an untrimmed video according to a g…
A Family of Lanthanide Noncentrosymmetric Superconductors La ( = Ru, Rh, Ir; = Al, In)
Hang Su, Feng Du, Shuaishuai Luo +10
We report the discovery of superconductivity in a series of noncentrosymmetric compounds La ( = Ru, Rh, Ir; = Al, In), which have a cubic crystal structure with spac…
Trend and forecasting of the COVID-19 outbreak in China
Qiang Li, Wei Feng
By using the public data from Jan. 20 to Feb. 11, 2020, we perform data-driven analysis and forecasting on the COVID-19 epidemic in mainland China, especially Hubei province. Our r…
Fast Rigid 3D Registration Solution: A Simple Method Free of SVD and Eigen-Decomposition
Jin Wu, Ming Liu, Zebo Zhou +1
A novel solution is obtained to solve the rigid 3D registration problem, motivated by previous eigen-decomposition approaches. Different from existing solvers, the proposed algorit…
Spin-orbit coupling and electric-dipole spin resonance in a nanowire double quantum dot
Zhi-Hai Liu, Rui Li, Xuedong Hu +1
We study the electric-dipole transitions for a single electron in a double quantum dot located in a semiconductor nanowire. Enabled by spin-orbit coupling (SOC), electric-dipole sp…
Fast Symbolic 3D Registration Solution
Jin Wu, Ming Liu, Zebo Zhou +1
3D registration has always been performed invoking singular value decomposition (SVD) or eigenvalue decomposition (EIG) in real engineering practices. However, these numerical algo…
Structural and magnetic properties of CeZnAl single crystals
Qian Liu, Bin Shen, Michael Smidman +6
We have synthesized single crystals of CeZnAl, which is a new member of the family of the Ce-based intermetallics Ce ( = transition metal, = Si, Ge, Al), crystalliz…
A parabolic-hyperbolic system modeling the growth of a tumor
Rui Li, Bei Hu
In this paper, we consider a model with tumor microenvironment involving nutrient density, extracellular matrix and matrix-degrading enzymes, which satisfy a coupled system of PDEs…
Very Low-Mass Stellar and Substellar Companions to Solar-like Stars From MARVELS VI: A Giant Planet and a Brown Dwarf Candidate in a Close Binary System HD 87646
Bo Ma, Jian Ge, Alex Wolszczan +34
We report the detections of a giant planet (MARVELS-7b) and a brown dwarf candidate (MARVELS-7c) around the primary star in the close binary system, HD 87646. It is the first close…