Imagen de Portada

Spatio-temporal Decoupled Knowledge Compensator for Few-Shot Action Recognition

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Qu, Hongyu, Shu, Xiangbo, Yan, Rui, Gao, Hailiang, Wang, Wenguan, Tang, Jinhui
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

MVP-Shot: Multi-Velocity Progressive-Alignment Framework for Few-Shot Action Recognition
por: Qu, Hongyu, et al.
Publicado: (2024)

OmniGaze: Reward-inspired Generalizable Gaze Estimation In The Wild
por: Qu, Hongyu, et al.
Publicado: (2025)

Learning Clustering-based Prototypes for Compositional Zero-shot Learning
por: Qu, Hongyu, et al.
Publicado: (2025)

Locality-aware Cross-modal Correspondence Learning for Dense Audio-Visual Events Localization
por: Xing, Ling, et al.
Publicado: (2024)

EventCrab: Harnessing Frame and Point Synergy for Event-based Action Recognition and Beyond
por: Cao, Meiqi, et al.
Publicado: (2024)

GPT4Ego: Unleashing the Potential of Pre-trained Models for Zero-Shot Egocentric Action Recognition
por: Dai, Guangzhao, et al.
Publicado: (2024)

An Information Compensation Framework for Zero-Shot Skeleton-based Action Recognition
por: Xu, Haojun, et al.
Publicado: (2024)

Vision-centric Token Compression in Large Language Model
por: Xing, Ling, et al.
Publicado: (2025)

Kernel-Aware Graph Prompt Learning for Few-Shot Anomaly Detection
por: Tao, Fenfang, et al.
Publicado: (2024)

Spatiotemporal-Untrammelled Mixture of Experts for Multi-Person Motion Prediction
por: Yin, Zheng, et al.
Publicado: (2025)

Enabling Validation for Robust Few-Shot Recognition
por: Wang, Hanxin, et al.
Publicado: (2025)

SOAP: Enhancing Spatio-Temporal Relation and Motion Information Capturing for Few-Shot Action Recognition
por: Huang, Wenbo, et al.
Publicado: (2024)

Video-to-Task Learning via Motion-Guided Attention for Few-Shot Action Recognition
por: Guo, Hanyu, et al.
Publicado: (2024)

TAMT: Temporal-Aware Model Tuning for Cross-Domain Few-Shot Action Recognition
por: Wang, Yilong, et al.
Publicado: (2024)

ASTRA: Let Arbitrary Subjects Transform in Video Editing
por: Shen, Fei, et al.
Publicado: (2025)

MA-FSAR: Multimodal Adaptation of CLIP for Few-Shot Action Recognition
por: Xing, Jiazheng, et al.
Publicado: (2023)

Learning 3D Representations for Spatial Intelligence from Unposed Multi-View Images
por: Zhou, Bo, et al.
Publicado: (2026)

FTMoMamba: Motion Generation with Frequency and Text State Space Models
por: Li, Chengjian, et al.
Publicado: (2024)

Multimodal Cross-Domain Few-Shot Learning for Egocentric Action Recognition
por: Hatano, Masashi, et al.
Publicado: (2024)

Task-Specific Distance Correlation Matching for Few-Shot Action Recognition
por: Long, Fei, et al.
Publicado: (2025)

Manta: Enhancing Mamba for Few-Shot Action Recognition of Long Sub-Sequence
por: Huang, Wenbo, et al.
Publicado: (2024)

3D Gaussian Map with Open-Set Semantic Grouping for Vision-Language Navigation
por: Gao, Jianzhe, et al.
Publicado: (2026)

UnityGraph: Unified Learning of Spatio-temporal features for Multi-person Motion Prediction
por: Qu, Kehua, et al.
Publicado: (2024)

TEST-V: TEst-time Support-set Tuning for Zero-shot Video Classification
por: Yan, Rui, et al.
Publicado: (2025)

Trokens: Semantic-Aware Relational Trajectory Tokens for Few-Shot Action Recognition
por: Kumar, Pulkit, et al.
Publicado: (2025)

Learning Causal Domain-Invariant Temporal Dynamics for Few-Shot Action Recognition
por: Li, Yuke, et al.
Publicado: (2024)

Frame Order Matters: A Temporal Sequence-Aware Model for Few-Shot Action Recognition
por: Li, Bozheng, et al.
Publicado: (2024)

Multimodal Prototype-Enhanced Network for Few-Shot Action Recognition
por: Ni, Xinzhe, et al.
Publicado: (2022)

AdaFPP: Adapt-Focused Bi-Propagating Prototype Learning for Panoramic Activity Recognition
por: Cao, Meiqi, et al.
Publicado: (2024)

D$^2$ST-Adapter: Disentangled-and-Deformable Spatio-Temporal Adapter for Few-shot Action Recognition
por: Pei, Wenjie, et al.
Publicado: (2023)

Understanding the Cross-Domain Capabilities of Video-Based Few-Shot Action Recognition Models
por: Markham, Georgia, et al.
Publicado: (2024)

STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognition
por: Liu, Hongli, et al.
Publicado: (2026)

CLIP-guided Prototype Modulating for Few-shot Action Recognition
por: Wang, Xiang, et al.
Publicado: (2023)

Knowledge is Power: Advancing Few-shot Action Recognition with Multimodal Semantics from MLLMs
por: Xing, Jiazheng, et al.
Publicado: (2026)

Divide-and-Conquer Decoupled Network for Cross-Domain Few-Shot Segmentation
por: Cong, Runmin, et al.
Publicado: (2025)

Decoupling Spatio-Temporal Adapter for Fine-Grained Badminton Action Localization
por: Wang, Tianyu, et al.
Publicado: (2026)

Dynamic in Static: Hybrid Visual Correspondence for Self-Supervised Video Object Segmentation
por: Pei, Gensheng, et al.
Publicado: (2024)

Path-Decoupled Hyperbolic Flow Matching for Few-Shot Adaptation
por: Li, Lin, et al.
Publicado: (2026)

Embedding Generalized Semantic Knowledge into Few-Shot Remote Sensing Segmentation
por: Jia, Yuyu, et al.
Publicado: (2024)

Transformer-based Fusion of 2D-pose and Spatio-temporal Embeddings for Distracted Driver Action Recognition
por: Akdag, Erkut, et al.
Publicado: (2024)