Few-Shot Action Recognition

Latest papers

10 papers2 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Geometry-Aware Trajectory State Modeling for Few-Shot Action Recognition
Oct 28, 2026Zhiqi Miao, Marko Haralović, Stanislav Levendeev +5Few-Shot Action Recognition Video Action Recognition
University of Groningen · University of Twente · Faculty of Electrical Engineering and Computing, University of Zagreb
Closing the Estimation Gap: Training-Free Transductive Inference for Cross-Domain Few-Shot Action Recognition
Oct 13, 2026Changyi Li, Zeyu Yang, Yu XiaoFew-Shot Action Recognition Few-Shot Learning
Dept. of Information and Communications Engineering, Aalto University, 02150 Espoo, Finland
Few-Shot Video Recognition via Hierarchical Metric Learning
Sep 4, 2026Jiaxin Zhang, Haoran Gao, Xizhan Gao +3Few-Shot Action Recognition Few-Shot Learning
School of Information Science and Engineering, University of Jinan, Shandong, China
SkelHCC: A Hyperbolic CLIP-Driven Cache Adaptation Framework for Skeleton-based One-Shot Action Recognition
Jun 2, 2026Yanan Liu, Anqi Zhu, Jingmin Zhu +6Skeleton-Based Action Recognition Cross-Modal Representation Learning
Yunnan University, Kunming, China · Monash University · Lancaster University +1
AI-Assisted Competency Assessment from Egocentric Video in Simulation-Based Nursing Education
May 16, 2026Hanchen David Wang, Yilin Liu, Madison J. Lee +4Educational Assessment Few-Shot Action Recognition
Vanderbilt University
STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognition
May 13, 2026Hongli Liu, Yu Wang, Shengjie ZhaoCross-Modal Representation Learning Few-Shot Action Recognition
School of Computer Science and Technology, Tongji University, Shanghai, China · Engineering Research Center of Key Software Technologies for Smart City Perception and Planning, Ministry of Education
Knowledge is Power: Advancing Few-shot Action Recognition with Multimodal Semantics from MLLMs
Mar 27, 2026Jiazheng Xing, Chao Xu, Hangjie Yuan +4Few-Shot Action Recognition Few-Shot Learning
College of Control Science and Engineering, Zhejiang University, Hangzhou, 310027, Zhejiang, China. · College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, 310023, Zhejiang, China. · College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, 310027, Zhejiang, China. +1
A Baseline Study and Benchmark for Few-Shot Open-Set Action Recognition with Feature Residual Discrimination
Mar 4, 2026Stefano Berti, Giulia Pasquale, Lorenzo NataleFew-Shot Action Recognition Open-Set Recognition
Humanoid Sensing and Perception, Istituto Italiano di Tecnologia, Genoa, Italy
Spatio-temporal Decoupled Knowledge Compensator for Few-Shot Action Recognition
Feb 20, 2026Hongyu Qu, Xiangbo Shu, Rui Yan +3Few-Shot Action Recognition Video Action Recognition
School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China. · State Key Lab of Brain-Machine Intelligence, Zhejiang University, China.
Hierarchical Relation-augmented Representation Generalization for Few-shot Action Recognition
Apr 14, 2025Hongyu Qu, Ling Xing, Jiachao Zhang +3Few-Shot Action Recognition Temporal Reasoning
School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China · Artificial Intelligence Industrial Technology Research Institute, Nanjing Institute of Technology, Nanjing 211167, China

Oct 28, 2026J/K move · Enter open · S save

Geometry-Aware Trajectory State Modeling for Few-Shot Action Recognition

Zhiqi Miao, Marko Haralović, Stanislav Levendeev, Sarvesh Angadi+4

University of Groningen · University of Twente · Faculty of Electrical Engineering and Computing, University of Zagreb

Few-Shot Action Recognition Video Action Recognition Few-Shot Learning Motion Representation Learning Geometric Representation Learning

Open paper AskPDF arXiv

Few-shot action recognition (FSAR) requires representations that expose discriminative motion dynamics from only a few labeled videos. Recent trajectory-based methods leverage long-term point tracks for explicit temporal correspondence, but often treat trajectories as carriers of sampled visual features or summarize their motion with compact 2D displacement-based descriptors. We instead view an action as the ordered evolution of 2.5D trajectory states and their local geometric interactions. Based on this view, we introduce GeoTRAM, a geometry-aware trajectory state modeling framework for FSAR. GeoTRAM lifts sparse tracks into 2.5D trajectories, where StateMotion models ordered intra-trajectory state evolution and RelMotion captures state-conditioned local interactions through time-varying relative geometry and motion. Quality-filtered spectral sampling provides more reliable trajectory initialization; complementary semantic, motion, and depth cues are separately refined and preserved for joint spatio-temporal modeling; action-guided reweighting and top-

ρ

trajectory selection support complementary frame- and trajectory-level matching. Experiments on five FSAR benchmarks demonstrate strong gains on the motion-centric Something-Something benchmarks while maintaining competitive performance on more appearance-driven benchmarks and a favorable accuracy--efficiency trade-off.