Hongsong Wang - RankMe

67 papers A* 8A 1B 3Journal 51Unranked 4

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Attribution as Retrieval: Model-Agnostic AI-Generated Image Attribution. CoRR Hongsong Wang, Renxi Cheng, Chaolei Han, Jie Gui
2026	J	`jnl`	Bilingual Text-to-Motion Generation: A New Benchmark and Baselines. CoRR Wanjiang Weng, Xiaofeng Tan, Xiangbo Shu, Guo-Sen Xie, Pan Zhou, Hongsong Wang
2026	J	`jnl`	ConsistentRFT: Reducing Visual Hallucinations in Flow-based Reinforcement Fine-Tuning. CoRR Xiaofeng Tan, Jun Liu, Yuanting Fan, Bin-Bin Gao, Xi Jiang, Xiaochen Chen, Jinlong Peng, Chengjie Wang, Hongsong Wang, Feng Zheng
2026	J	`jnl`	Data-Free Class-Incremental Gesture Recognition With Prototype-Guided Pseudo-Feature Replay. IEEE Trans. Image Process. Hongsong Wang, Ao Sun, Jie Gui, Liang Wang
2026	J	`jnl`	EasyTune: Efficient Step-Aware Fine-Tuning for Diffusion-Based Motion Generation. CoRR Xiaofeng Tan, Wanjiang Weng, Haodong Lei, Hongsong Wang
2026	J	`jnl`	Foundation Model for Skeleton-Based Human Action Understanding. IEEE Trans. Pattern Anal. Mach. Intell. Hongsong Wang, Wanjiang Weng, Junbo Wang, Fang Zhao, Guo-Sen Xie, Xin Geng, Liang Wang
2026	A*	`conf`	ReAlign: Text-to-Motion Generation via Step-Aware Reward-Guided Alignment. AAAI Wanjiang Weng, Xiaofeng Tan, Junbo Wang, Guo-Sen Xie, Pan Zhou, Hongsong Wang
2026	J	`jnl`	Temporal Consistency-Aware Text-to-Motion Generation. CoRR Hongsong Wang, Wenjing Yan, Qiuxia Lai, Xin Geng
2026	J	`jnl`	Temporal consistency-aware text-to-motion generation. Vis. Intell. Hongsong Wang, Wenjing Yan, Qiuxia Lai, Xin Geng
2026	J	`jnl`	Zero-shot skeleton-based action recognition with dual visual-text alignment. Pattern Recognit. Jidong Kuang, Hongsong Wang, Chaolei Han, Yang Zhang, Jie Gui
2025	—	`conf`	Action-Agnostic Pose-Based Gait Recognition. CCBR Hongsong Wang, Yingjie Cheng, Jie Gui
2025	J	`jnl`	Addressing Skewed Heterogeneity via Federated Prototype Rectification With Personalization. IEEE Trans. Neural Networks Learn. Syst. Shunxin Guo, Hongsong Wang, Shuxia Lin, Zhiqiang Kou, Xin Geng
2025	A*	`conf`	DSACap: Enhancing Visual-Semantic Alignment with Diffusion-based Framework for Image Captioning. ACM Multimedia Liangyu Fu, Junbo Wang, Yuke Li, Qiangguo Jin, Hongsong Wang, Jing Ya, Linjiang Huang, Liang Yao, Jiangbin Zheng, Xuecheng Wu, Zhiyong Wang
2025	J	`jnl`	Data-Free Class-Incremental Gesture Recognition with Prototype-Guided Pseudo Feature Replay. CoRR Hongsong Wang, Ao Sun, Jie Gui, Liang Wang
2025	J	`jnl`	Dragging with Geometry: From Pixels to Geometry-Guided Image Editing. CoRR Xinyu Pu, Hongsong Wang, Jie Gui, Pan Zhou
2025	J	`jnl`	DreamCS: Geometry-Aware Text-to-3D Generation with Unpaired 3D Reward Supervision. CoRR Xiandong Zou, Ruihao Xia, Hongsong Wang, Pan Zhou
2025	A*	`conf`	Dual Conditioned Motion Diffusion for Pose-Based Video Anomaly Detection. AAAI Hongsong Wang, Andi Xu, Pinle Ding, Jie Gui
2025	J	`jnl`	Efficient Diffusion-Based 3D Human Pose Estimation with Hierarchical Temporal Pruning. CoRR Yuquan Bi, Hongsong Wang, Xinli Shi, Zhipeng Gui, Jie Gui, Yuan Yan Tang
2025	J	`jnl`	Fast Inference of Visual Autoregressive Model with Adjacency-Adaptive Dynamical Draft Trees. CoRR Haodong Lei, Hongsong Wang, Xin Geng, Liang Wang, Pan Zhou
2025	J	`jnl`	Foundation Model for Skeleton-Based Human Action Understanding. CoRR Hongsong Wang, Wanjiang Weng, Junbo Wang, Fang Zhao, Guo-Sen Xie, Xin Geng, Liang Wang
2025	J	`jnl`	HQ-OV3D: A High Box Quality Open-World 3D Detection Framework based on Diffision Model. CoRR Qi Liu, Yabei Li, Hongsong Wang, Lei He
2025	A*	`conf`	Heterogeneous Skeleton-Based Action Representation Learning. CVPR Hongsong Wang, Xiaoyan Ma, Jidong Kuang, Jie Gui
2025	J	`jnl`	Heterogeneous Skeleton-Based Action Representation Learning. CoRR Hongsong Wang, Xiaoyan Ma, Jidong Kuang, Jie Gui
2025	J	`jnl`	LOTA: Bit-Planes Guided AI-Generated Image Detection. CoRR Hongsong Wang, Renxi Cheng, Yang Zhang, Chaolei Han, Jie Gui
2025	B	`conf`	MirrorDiff: Learning Mirror Diffusion for Image Captioning via Regeneration. ICMR Junbo Wang, Liangyu Fu, Yining Zhu, Qiangguo Jin, Hongsong Wang, Yuke Li, Xuecheng Wu, Kun Hu
2025	J	`jnl`	Multimodal Skeleton-Based Action Representation Learning via Decomposition and Composition. CoRR Hongsong Wang, Heng Fei, Bingxuan Dai, Jie Gui
2025	J	`jnl`	PAMD: Plausibility-Aware Motion Diffusion Model for Long Dance Generation. CoRR Hongsong Wang, Yin Zhu, Qiuxia Lai, Yang Zhang, Guo-Sen Xie, Xin Geng
2025	B	`conf`	PTSR: A Unified Patch Tokenization, Selection and Representation Framework for Efficient Micro-expression Recognition. ICMR Liangyu Fu, Junbo Wang, Qiangguo Jin, Yining Zhu, Hongsong Wang, Yuke Li, Xuecheng Wu, Kun Hu
2025	J	`jnl`	ReAlign: Text-to-Motion Generation via Step-Aware Reward-Guided Alignment. CoRR Wanjiang Weng, Xiaofeng Tan, Junbo Wang, Guo-Sen Xie, Pan Zhou, Hongsong Wang
2025	A*	`conf`	SAM-Aware Graph Prompt Reasoning Network for Cross-Domain Few-Shot Segmentation. AAAI Shi-Feng Peng, Guolei Sun, Yong Li, Hongsong Wang, Guo-Sen Xie
2025	J	`jnl`	SAM-Aware Graph Prompt Reasoning Network for Cross-Domain Few-Shot Segmentation. CoRR Shi-Feng Peng, Guolei Sun, Yong Li, Hongsong Wang, Guo-Sen Xie
2025	J	`jnl`	STHFL: Spatio-Temporal Heterogeneous Federated Learning. CoRR Shunxin Guo, Hongsong Wang, Shuxia Lin, Xu Yang, Xin Geng
2025	J	`jnl`	Training-Free Zero-Shot Temporal Action Detection with Vision-Language Models. CoRR Chaolei Han, Hongsong Wang, Jidong Kuang, Lei Zhang, Jie Gui
2025	A*	`conf`	USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelation. AAAI Wanjiang Weng, Hongsong Wang, Junbo Wang, Lei He, Guo-Sen Xie
2024	J	`jnl`	Addressing Skewed Heterogeneity via Federated Prototype Rectification with Personalization. CoRR Shunxin Guo, Hongsong Wang, Shuxia Lin, Zhiqiang Kou, Xin Geng
2024	J	`jnl`	Dual Conditioned Motion Diffusion for Pose-Based Video Anomaly Detection. CoRR Andi Xu, Hongsong Wang, Pinle Ding, Jie Gui
2024	J	`jnl`	Dynamic heterogeneous federated learning with multi-level prototypes. Pattern Recognit. Shunxin Guo, Hongsong Wang, Xin Geng
2024	J	`jnl`	Flexible Music-Conditioned Dance Generation with Style Description Prompts. CoRR Hongsong Wang, Yin Zhu, Xin Geng
2024	J	`jnl`	Frequency-Guided Diffusion Model with Perturbation Training for Skeleton-Based Video Anomaly Detection. CoRR Xiaofeng Tan, Hongsong Wang, Xin Geng
2024	J	`jnl`	Graph Convolution Based Efficient Re-Ranking for Visual Retrieval. IEEE Trans. Multim. Yuqi Zhang, Qi Qian, Hongsong Wang, Chong Liu, Weihua Chen, Fan Wang
2024	J	`jnl`	Region-aware Image-based Human Action Retrieval with Transformers. CoRR Hongsong Wang, Jianhua Zhao, Jie Gui
2024	J	`jnl`	Region-aware image-based human action retrieval with transformers. Comput. Vis. Image Underst. Hongsong Wang, Jianhua Zhao, Jie Gui
2024	A	`conf`	Robust 3D Face Alignment with Multi-Path Neural Architecture Search. ICME Zhichao Jiang, Hongsong Wang, Xi Teng, Baopu Li
2024	J	`jnl`	Robust 3D Face Alignment with Multi-Path Neural Architecture Search. CoRR Zhichao Jiang, Hongsong Wang, Xi Teng, Baopu Li
2024	J	`jnl`	SoPo: Text-to-Motion Generation Using Semi-Online Preference Optimization. CoRR Xiaofeng Tan, Hongsong Wang, Xin Geng, Pan Zhou
2024	J	`jnl`	USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelation. CoRR Wanjiang Weng, Hongsong Wang, Junbo Wang, Lei He, Guosen Xie
2024	J	`jnl`	Zero-Shot Skeleton-based Action Recognition with Dual Visual-Text Alignment. CoRR Jidong Kuang, Hongsong Wang, Chaolei Han, Jie Gui
2023	J	`jnl`	Dynamic Heterogeneous Federated Learning with Multi-Level Prototypes. CoRR Shunxin Guo, Hongsong Wang, Xin Geng
2023	J	`jnl`	Efficient Token-Guided Image-Text Retrieval With Consistent Multimodal Contrastive Training. IEEE Trans. Image Process. Chong Liu, Yuqi Zhang, Hongsong Wang, Weihua Chen, Fan Wang, Yan Huang, Yi-Dong Shen, Liang Wang
2023	J	`jnl`	Efficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training. CoRR Chong Liu, Yuqi Zhang, Hongsong Wang, Weihua Chen, Fan Wang, Yan Huang, Yi-Dong Shen, Liang Wang
2023	J	`jnl`	Graph Convolution Based Efficient Re-Ranking for Visual Retrieval. CoRR Yuqi Zhang, Qi Qian, Hongsong Wang, Chong Liu, Weihua Chen, Fan Wang
2023	—	`conf`	Learning Efficient Representations for Image-Based Patent Retrieval. PRCV (7) Hongsong Wang, Yuqi Zhang
2023	J	`jnl`	Learning Efficient Representations for Image-Based Patent Retrieval. CoRR Hongsong Wang, Yuqi Zhang
2023	A*	`conf`	Occluded Skeleton-Based Human Action Recognition with Dual Inhibition Training. ACM Multimedia Zhenjie Chen, Hongsong Wang, Jie Gui
2022	J	`jnl`	Velocity-to-velocity human motion forecasting. Pattern Recognit. Hongsong Wang, Liang Wang, Jiashi Feng, Daquan Zhou
2021	J	`jnl`	AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detection. CoRR Hongsong Wang, Shengcai Liao, Ling Shao
2021	J	`jnl`	AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detection. IEEE Trans. Image Process. Hongsong Wang, Shengcai Liao, Ling Shao
2021	J	`jnl`	PVRED: A Position-Velocity Recurrent Encoder-Decoder for Human Motion Prediction. IEEE Trans. Image Process. Hongsong Wang, Jian Dong, Bin Cheng, Jiashi Feng
2019	J	`jnl`	VRED: A Position-Velocity Recurrent Encoder-Decoder for Human Motion Prediction. CoRR Hongsong Wang, Jiashi Feng
2018	J	`jnl`	Beyond Joints: Learning Representations From Primitive Geometries for Skeleton-Based Action Recognition and Detection. IEEE Trans. Image Process. Hongsong Wang, Liang Wang
2018	J	`jnl`	Cross-Agent Action Recognition. IEEE Trans. Circuits Syst. Video Technol. Hongsong Wang, Liang Wang
2018	J	`jnl`	Learning content and style: Joint action recognition and person identification from human skeletons. Pattern Recognit. Hongsong Wang, Liang Wang
2017	—	`conf`	Learning robust representations using recurrent neural networks for skeleton based action classification and detection. ICME Workshops Hongsong Wang, Liang Wang
2017	A*	`conf`	Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks. CVPR Hongsong Wang, Liang Wang
2017	J	`jnl`	Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks. CoRR Hongsong Wang, Liang Wang
2016	B	`conf`	How scenes imply actions in realistic videos? ICIP Hongsong Wang, Wei Wang, Liang Wang
2015	—	`conf`	Hierarchical motion evolution for action recognition. ACPR Hongsong Wang, Wei Wang, Liang Wang