Zero-Shot Action Recognition

Latest papers

20 papers2 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

PRIMA: Pose Refined Inductive Motion Adapter for Zero Shot Social Bodily Behavior Recognition
Oct 18, 2026Mingcong Ding, Babette Bühler, Tim Fütterer +2VLM Adaptation Zero-Shot Action Recognition
Technical University of Munich Munich, Germany · Munich Center for Machine Learning (MCML) Munich, Germany · University of Tübingen Tübingen, Germany
More Features Are Not More Evidence: Limits of Training-Free Human Activity Recognition with Jev
Sep 28, 2026Orhan KonakHuman Activity Recognition Zero-Shot Action Recognition
Hasso Plattner Institute, University of Potsdam Potsdam, Germany
Skeleton-based Zero-Shot Spatio-Temporal Action Localization via Weakly-Supervised Pretraining
Aug 26, 2026Koshiro Nagano, Fumiaki Sato, Ryo Hachiuma +2Temporal Action Localization Zero-Shot Learning
Konica Minolta, Inc. · Keio University · CyberAgent +1
Visual Anchoring in Diffusion: Multimodal Zero-Shot Skeleton Action Recognition
Aug 5, 2026Zehao Bao, Shujun Guo, Bruce X. B. YuSkeleton-Based Action Recognition Diffusion Transformer
The University of Hong Kong Hong Kong SAR, China · Zhejiang University Hangzhou, China
GenPrior: Unleashing Text-to-Motion Generative Priors for Zero-Shot Skeleton-based Action Recognition
Aug 3, 2026Jidong Kuang, Hongsong Wang, Jie GuiSkeleton-Based Action Recognition Zero-Shot Learning
School of Cyber Science and Engineering, Southeast University Nanjing, China · School of Computer Science and Engineering, Southeast University Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Nanjing, China · School of Cyber Science and Engineering, Southeast University Purple Mountain Laboratories Engineering Research Center of Blockchain Application, Supervision and Management Nanjing, China
Zero-Fi: Zero-Shot Wi-Fi-Based Human Activity Recognition via Contrastive Signal-Language Alignment
Jul 29, 2026Yitong Shen, Cheng Guo, Peiliang Wang +5Human Activity Recognition Zero-Shot Action Recognition
University of South Florida · University of North Carolina at Charlotte
Robust Zero-Shot Generalization for Open-Vocabulary Action Recognition via Task Arithmetic
Jun 17, 2026Francesca Morandi, Omayma Moussadek, Federico Venturini +5Zero-Shot Learning OOD Generalization
University of Modena and Reggio Emilia · University of Pisa · Eni S.p.A.
Divide, Deliberate, Decide: A Multi-Agent Framework for Fine-Grained Egocentric Action Recognition
Jun 16, 2026Alessandro Sottovia, Alessandro Torcinovich, Oswald LanzZero-Shot Learning Multi-Agent Debate
Faculty of Engineering, Free University of Bozen-Bolzano, Bolzano, Italy
Closing the Modality Gap in Zero-Shot HAR: Contrastive Training and Separability-Optimized Prototypes on IMU Data
Jun 9, 2026Anik GhoshPrototype-Based Learning Contrastive Learning
Cross-Domain Human Action Recognition from Multiview Motion and Textual Descriptions
May 21, 2026Yannick Porto, Renato Martins, Thomas Chalumeau +1Zero-Shot Learning Human Activity Recognition
Université Bourgogne Europe, CNRS – France · TEB Group, Prynel SAS – France
Zero-Shot Temporal Action Localization Through Textual Guidance
May 21, 2026Benedetta Liberatori, Alessandro Conti, Lorenzo Vaquero +3Zero-Shot Learning Temporal Action Detection
University of Trento, Trento, Italy · Fondazione Bruno Kessler, Trento, Italy
PoseBridge: Bridging the Skeletonization Gap for Zero-Shot Skeleton-Based Action Recognition
May 12, 2026Sanghyeon Lee, Jinwoo Kim, Jong Taek LeeSkeleton-Based Action Recognition Human Activity Recognition
School of Computer Science and Engineering Kyungpook National University, Daegu, South Korea
CEZSAR: A Contrastive Embedding Method for Zero-Shot Action Recognition
May 1, 2026Valter Estevam, Rayson Laroca, Helio Pedrini +1Contrastive Learning Zero-Shot Learning
Federal Institute of Paraná, Irati, Brasil · Federal University of Paraná, Curitiba, Brasil · Pontifical Catholic University of Paraná, Curitiba, Brasil +1
High-Speed Vision Improves Zero-Shot Semantic Understanding of Human Actions
May 1, 2026Yongpeng Cao, Yuji YamakawaVideo Understanding Zero-Shot Learning
Institute of Industrial Science, The University of Tokyo, Japan · Interfaculty Initiative in Information Studies, Graduate School of Interdisciplinary Information Studies, The University of Tokyo, Japan
Motion-Guided Semantic Alignment with Negative Prompts for Zero-Shot Video Action Recognition
Apr 18, 2026Yiming Wang, Frederick W. B. Li, Jingyun WangRepresentation Learning Video Action Recognition
Department of Computer Science, Durham University
Appearance-free Action Recognition: Zero-shot Generalization in Humans and a Two-Pathway Model
Apr 17, 2026Prerana Kumar, Martin A. GieseZero-Shot Learning Zero-Shot Action Recognition
Hertie Institute, University of Tuebingen · IMPRS-IS · Hertie Institute, University of Tübingen
Frequency-Enhanced Diffusion Models: Curriculum-Guided Semantic Alignment for Zero-Shot Skeleton Action Recognition
Apr 10, 2026Yuxi Zhou, Zhengbo Zhang, Jingyu Pan +2Skeleton-Based Action Recognition Zero-Shot Action Recognition
State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China. · Information Systems Technology and Design Pillar, Singapore University of Technology and Design, Singapore, Singapore. · School of Geodesy and Geomatics, Wuhan University, Wuhan, China. +2
SCALE: Semantic- and Confidence-Aware Conditional Variational Autoencoder for Zero-shot Skeleton-based Action Recognition
Apr 2, 2026Soroush Oraki, Feng Ding, Jie LiangSkeleton-Based Action Recognition Zero-Shot Action Recognition
School of Engineering Science, Simon Fraser University, Burnaby, BC, Canada · School of Information Science and Technology, Eastern Institute of Technology, Ningbo, China
Novel Semantic Prompting for Zero-Shot Action Recognition
Mar 9, 2026Salman Iqbal, Waheed RehmanZero-Shot Action Recognition Video Action Recognition
Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition
Jan 22, 2026Geo Ahn, Inwoong Lee, Taeoh Kim +3Zero-Shot Learning Video Action Recognition
1Kyung Hee University · ∗This work was done during an internship at NAVER Cloud. · 2NAVER Cloud

Oct 18, 2026J/K move · Enter open · S save

PRIMA: Pose Refined Inductive Motion Adapter for Zero Shot Social Bodily Behavior Recognition

Mingcong Ding, Babette Bühler, Tim Fütterer, Ulrich Trautwein+1

Technical University of Munich Munich, Germany · Munich Center for Machine Learning (MCML) Munich, Germany · University of Tübingen Tübingen, Germany

VLM Adaptation Zero-Shot Action Recognition Motion Representation Learning PEFT of VLMs

Open paper AskPDF arXiv

Recognizing fine-grained bodily behaviors, such as self-grooming, postural shifts, and backchanneling, is a useful intermediate step for computational social signal analysis. But the behaviors that matter vary across social contexts, and retraining a model for each new taxonomy is expensive. Vision-language models (VLMs) can adapt to new categories through text prompts, yet they lack sensitivity to body structure and often confuse subtle postural distinctions. We propose PRIMA (Pose Refined Inductive Motion Adapter), a lightweight module that injects a body-structure prior into frozen VLMs using human pose as a training-time supervisory signal, requiring no pose input at inference. PRIMA separates a model-specific projection head from a shared core that encodes transferable body-configuration knowledge; adapting to a new VLM requires retraining only the head. We train PRIMA on a micro-action dataset and evaluate entirely through zero-shot prompting. The adapter improves recognition on its training domain, transfers to additional VLM backbones at different scales with the core frozen, and generalizes to two unseen target datasets from social psychology and daily activity recognition. In a supporting downstream study, the improved behavior predictions also yield higher correlations with human ratings of rapport and dominance in a collaboration context. Within the scope of the tested models and indoor datasets, the results indicate that pose-guided training can produce body-structure priors that generalize across unseen behavior vocabularies and can be partially reused across VLM backbones while preserving RGB-only inference.