Hongsong Wang

CoRR, May, 2026

When Policy Entropy Constraint Fails: Preserving Diversity in Flow-based RLHF via Perceptual Entropy.

[BibT_eX]

[DOI]

CoRR, May, 2026

OZ-TAL: Online Zero-Shot Temporal Action Localization.

[BibT_eX]

[DOI]

CoRR, May, 2026

Marrying Text-to-Motion Generation with Skeleton-Based Action Recognition.

[BibT_eX]

[DOI]

Jidong Kuang

CoRR, April, 2026

Towards Universal Skeleton-Based Action Recognition.

[BibT_eX]

[DOI]

Jidong Kuang

CoRR, April, 2026

Bilingual Text-to-Motion Generation: A New Benchmark and Baselines.

[BibT_eX]

[DOI]

CoRR, March, 2026

Attribution as Retrieval: Model-Agnostic AI-Generated Image Attribution.

[BibT_eX]

[DOI]

CoRR, March, 2026

EasyTune: Efficient Step-Aware Fine-Tuning for Diffusion-Based Motion Generation.

[BibT_eX]

[DOI]

CoRR, February, 2026

ConsistentRFT: Reducing Visual Hallucinations in Flow-based Reinforcement Fine-Tuning.

[BibT_eX]

[DOI]

CoRR, February, 2026

Foundation Model for Skeleton-Based Human Action Understanding.

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., January, 2026

Temporal consistency-aware text-to-motion generation.

[BibT_eX]

[DOI]

Vis. Intell., 2026

Data-Free Class-Incremental Gesture Recognition With Prototype-Guided Pseudo-Feature Replay.

[BibT_eX]

[DOI]

IEEE Trans. Image Process., 2026

Efficient Neural Architecture Search for brain-inspired spiking neural network.

[BibT_eX]

[DOI]

Pattern Recognit., 2026

Zero-shot skeleton-based action recognition with dual visual-text alignment.

[BibT_eX]

[DOI]

Pattern Recognit., 2026

ReAlign: Text-to-Motion Generation via Step-Aware Reward-Guided Alignment.

[BibT_eX]

[DOI]

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025

Fast Inference of Visual Autoregressive Model with Adjacency-Adaptive Dynamical Draft Trees.

[BibT_eX]

[DOI]

CoRR, December, 2025

Multimodal Skeleton-Based Action Representation Learning via Decomposition and Composition.

[BibT_eX]

[DOI]

CoRR, December, 2025

Dragging with Geometry: From Pixels to Geometry-Guided Image Editing.

[BibT_eX]

[DOI]

CoRR, September, 2025

Efficient Diffusion-Based 3D Human Pose Estimation with Hierarchical Temporal Pruning.

[BibT_eX]

[DOI]

CoRR, August, 2025

HQ-OV3D: A High Box Quality Open-World 3D Detection Framework based on Diffision Model.

[BibT_eX]

[DOI]

CoRR, August, 2025

DreamCS: Geometry-Aware Text-to-3D Generation with Unpaired 3D Reward Supervision.

[BibT_eX]

[DOI]

CoRR, June, 2025

Addressing Skewed Heterogeneity via Federated Prototype Rectification With Personalization.

[BibT_eX]

[DOI]

IEEE Trans. Neural Networks Learn. Syst., May, 2025

PAMD: Plausibility-Aware Motion Diffusion Model for Long Dance Generation.

[BibT_eX]

[DOI]

CoRR, May, 2025

Training-Free Zero-Shot Temporal Action Detection with Vision-Language Models.

[BibT_eX]

[DOI]

CoRR, January, 2025

STHFL: Spatio-Temporal Heterogeneous Federated Learning.

[BibT_eX]

[DOI]

CoRR, January, 2025

DSACap: Enhancing Visual-Semantic Alignment with Diffusion-based Framework for Image Captioning.

[BibT_eX]

[DOI]

Proceedings of the 33rd ACM International Conference on Multimedia, 2025

MirrorDiff: Learning Mirror Diffusion for Image Captioning via Regeneration.

[BibT_eX]

[DOI]

Proceedings of the 2025 International Conference on Multimedia Retrieval, 2025

PTSR: A Unified Patch Tokenization, Selection and Representation Framework for Efficient Micro-expression Recognition.

[BibT_eX]

[DOI]

Proceedings of the 2025 International Conference on Multimedia Retrieval, 2025

LOTA: Bit-Planes Guided AI-Generated Image Detection.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

Heterogeneous Skeleton-Based Action Representation Learning.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

Action-Agnostic Pose-Based Gait Recognition.

[BibT_eX]

[DOI]

Yingjie Cheng

Proceedings of the Biometric Recognition - 19th Chinese Conference, 2025

USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelation.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025

Dual Conditioned Motion Diffusion for Pose-Based Video Anomaly Detection.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025

SAM-Aware Graph Prompt Reasoning Network for Cross-Domain Few-Shot Segmentation.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025

2024

Graph Convolution Based Efficient Re-Ranking for Visual Retrieval.

[BibT_eX]

[DOI]

IEEE Trans. Multim., 2024

Dynamic heterogeneous federated learning with multi-level prototypes.

[BibT_eX]

[DOI]

Shunxin Guo

Xin Geng

Pattern Recognit., 2024

Region-aware image-based human action retrieval with transformers.

[BibT_eX]

[DOI]

Jianhua Zhao

Comput. Vis. Image Underst., 2024

SoPo: Text-to-Motion Generation Using Semi-Online Preference Optimization.

[BibT_eX]

[DOI]

CoRR, 2024

Frequency-Guided Diffusion Model with Perturbation Training for Skeleton-Based Video Anomaly Detection.

[BibT_eX]

[DOI]

Xiaofeng Tan

Xin Geng

CoRR, 2024

Zero-Shot Skeleton-based Action Recognition with Dual Visual-Text Alignment.

[BibT_eX]

[DOI]

CoRR, 2024

Flexible Music-Conditioned Dance Generation with Style Description Prompts.

[BibT_eX]

[DOI]

Yin Zhu

Xin Geng

CoRR, 2024

Robust 3D Face Alignment with Multi-Path Neural Architecture Search.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Multimedia and Expo, 2024

2023

Efficient Token-Guided Image-Text Retrieval With Consistent Multimodal Contrastive Training.

[BibT_eX]

[DOI]

IEEE Trans. Image Process., 2023

Learning Efficient Representations for Image-Based Patent Retrieval.

[BibT_eX]

[DOI]

Yuqi Zhang

Proceedings of the Pattern Recognition and Computer Vision - 6th Chinese Conference, 2023

Occluded Skeleton-Based Human Action Recognition with Dual Inhibition Training.

[BibT_eX]

[DOI]

Zhenjie Chen

Proceedings of the 31st ACM International Conference on Multimedia, 2023

2022

Velocity-to-velocity human motion forecasting.

[BibT_eX]

[DOI]

Pattern Recognit., 2022

2021

AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detection.

[BibT_eX]

[DOI]

Shengcai Liao

Ling Shao

IEEE Trans. Image Process., 2021

PVRED: A Position-Velocity Recurrent Encoder-Decoder for Human Motion Prediction.

[BibT_eX]

[DOI]

IEEE Trans. Image Process., 2021

2019

VRED: A Position-Velocity Recurrent Encoder-Decoder for Human Motion Prediction.

[BibT_eX]

[DOI]

Jiashi Feng

CoRR, 2019

2018

Beyond Joints: Learning Representations From Primitive Geometries for Skeleton-Based Action Recognition and Detection.

[BibT_eX]

[DOI]

IEEE Trans. Image Process., 2018

Cross-Agent Action Recognition.

[BibT_eX]

[DOI]

IEEE Trans. Circuits Syst. Video Technol., 2018

Learning content and style: Joint action recognition and person identification from human skeletons.

[BibT_eX]

[DOI]

Pattern Recognit., 2018

2017

Learning robust representations using recurrent neural networks for skeleton based action classification and detection.

[BibT_eX]

[DOI]

Proceedings of the 2017 IEEE International Conference on Multimedia & Expo Workshops, 2017

Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017

2016

How scenes imply actions in realistic videos?

[BibT_eX]

[DOI]

Wei Wang

Proceedings of the 2016 IEEE International Conference on Image Processing, 2016

2015

Hierarchical motion evolution for action recognition.

[BibT_eX]

[DOI]

Wei Wang