68 citations · 166 across the 13 of their papers we have counts for
14 papers
Learning Skills from Historical Action Trajectories: Action Experience Dictionary for World Action Models
Qi Lyu, Jiahua Dong, Hao Shen +9
World Action Models (WAMs) couple visual dynamics prediction with action generation, yet they do not explicitly support the reuse of action experience across manipulation tasks. Fu…
JANUS: Online Jacobian-Aligned Infill for Black-Box Optimization
Hongyuan Yu, Pufan Xu, Jiaojiao Yi +4
Population optimizers such as CMA-ES, DE, and multi-objective evolutionary algorithms drive search mainly through selection signals that are scalar or rank based: such a signal ind…
GuardianBench: A Same-Scene Instruction-Contrastive Benchmark for Latent Contextual Risk in Embodied AI
Zhesheng Zhang, Jiahao Lu, Wei Liu +8
In embodied AI, safety risk can be latent: a benign instruction and a safe scene become hazardous only when composed. Prior work has advanced embodied safety by varying visual cont…
UESF-Bench: Benchmarking and Probing for Unified Embodied Seeking and Following
Kun Yu, Jianhua Yang, Yixiang Chen +7
Language-guided human following is an important capability for embodied agents, but existing benchmarks typically assume that the target person is visible at the start of an episod…
SliceMamba with Neural Architecture Search for Medical Image Segmentation
Chao Fan, Hongyuan Yu, Yan Huang +3
Despite the progress made in Mamba-based medical image segmentation models, existing methods utilizing unidirectional or multi-directional feature scanning mechanisms struggle to e…
CNTN: Cyclic Noise-tolerant Network for Gait Recognition
Weichen Yu, Hongyuan Yu, Yan Huang +2
Gait recognition aims to identify individuals by recognizing their walking patterns. However, an observation is made that most of the previous gait recognition methods degenerate s…
Generalized Inter-class Loss for Gait Recognition
Weichen Yu, Hongyuan Yu, Yan Huang +1
Gait recognition is a unique biometric technique that can be performed at a long distance non-cooperatively and has broad applications in public safety and intelligent traffic syst…
Regularized Graph Structure Learning with Semantic Knowledge for Multi-variates Time-Series Forecasting
Hongyuan Yu, Ting Li, Weichen Yu +4
Multivariate time-series forecasting is a critical task for many applications, and graph time-series network is widely studied due to its capability to capture the spatial-temporal…
Consecutive Knowledge Meta-Adaptation Learning for Unsupervised Medical Diagnosis
Yumin Zhang, Yawen Hou, Xiuyi Chen +2
Deep learning-based Computer-Aided Diagnosis (CAD) has attracted appealing attention in academic researches and clinical applications. Nevertheless, the Convolutional Neural Networ…
Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Search
Houwen Peng, Hao Du, Hongyuan Yu +3
One-shot weight sharing methods have recently drawn great attention in neural architecture search due to high efficiency and competitive performance. However, weight sharing across…
Recurrent Deconvolutional Generative Adversarial Networks with Application to Text Guided Video Generation
Hongyuan Yu, Yan Huang, Lihong Pi +1
This paper proposes a novel model for video generation and especially makes the attempt to deal with the problem of video generation from text descriptions, i.e., synthesizing real…
Cyclic Differentiable Architecture Search
Hongyuan Yu, Houwen Peng, Yan Huang +4
Differentiable ARchiTecture Search, i.e., DARTS, has drawn great attention in neural architecture search. It tries to find the optimal architecture in a shallow search network and…
An End-to-end Video Text Detector with Online Tracking
Hongyuan Yu, Chengquan Zhang, Xuan Li +3
Video text detection is considered as one of the most difficult tasks in document analysis due to the following two challenges: 1) the difficulties caused by video scenes, i.e., mo…
Identity-Enhanced Network for Facial Expression Recognition
Yanwei Li, Xingang Wang, Shilei Zhang +4
Facial expression recognition is a challenging task, arguably because of large intra-class variations and high inter-class similarities. The core drawback of the existing approache…