Video Action Recognition

Follow this topic Ask about this topic

Video action recognition studies how to identify activities from sequences of frames, where timing and interactions can distinguish actions that look similar in a single image. Common approaches include 3D convolutional networks and video transformers, RGB and optical-flow streams, pose or skeleton models, and pretrained vision-language models adapted through prompts or limited fine-tuning. Research also addresses few-shot and open-vocabulary recognition, temporal localization, and transfer across domains such as egocentric, medical, sports, and surveillance video. A central challenge is improving temporal understanding and generalization under viewpoint changes, occlusion, scarce labels, and background shortcuts while keeping models efficient and reliable in real-world settings.

Latest papers

112 papers13 papers in the last four weeks, up 86% on the four weeks before. 0.1% of all new papers.

Apr 10, 2026

Learnable Motion-Focused Tokenization for Effective and Efficient Video Unsupervised Domain Adaptation

Video Unsupervised Domain Adaptation (VUDA) poses a significant challenge in action recognition, requiring the adaptation of a model from a labeled source domain to an unlabeled target domain. Despite recent advances, existing VUDA methods often fall short of fully supervised performance, a key reason being the prevalence of static and uninformative backgrounds that exacerbate domain shifts. Additionally, prior approaches largely overlook computational efficiency, limiting real-world adoption. To address these issues, we propose Learnable Motion-Focused Tokenization (LMFT) for VUDA. LMFT tokenizes video frames into patch tokens and learns to discard low-motion, redundant tokens, primarily corresponding to background regions, while retaining motion-rich, action-relevant tokens for adaptation. Extensive experiments on three standard VUDA benchmarks across 21 domain adaptation settings show that our VUDA framework with LMFT achieves state-of-the-art performance while significantly reducing computational overhead. LMFT thus enables VUDA that is both effective and computationally efficient.

Tzu Ling Liu, Ian Stavness, Mrigank Rochan

University of Saskatchewan, Canada

Unsupervised Domain Adaptation Video Action Recognition Video Token Compression

Apr 10, 2026

Fine-Grained Action Segmentation for Renorrhaphy in Robot-Assisted Partial Nephrectomy

Fine-grained action segmentation during renorrhaphy in robot-assisted partial nephrectomy requires frame-level recognition of visually similar suturing gestures with variable duration and substantial class imbalance. The SIA-RAPN benchmark defines this problem on 50 clinical videos acquired with the da Vinci Xi system and annotated with 12 frame-level labels. The benchmark compares four temporal models built on I3D features: MS-TCN++, AsFormer, TUT, and DiffAct. Evaluation uses balanced accuracy, edit score, segmental F1 at overlap thresholds of 10, 25, and 50, frame-wise accuracy, and frame-wise mean average precision. In addition to the primary evaluation across five released split configurations on SIA-RAPN, the benchmark reports cross-domain results on a separate single-port RAPN dataset. Across the strongest reported values over those five runs on the primary dataset, DiffAct achieves the highest F1, frame-wise accuracy, edit score, and frame mAP, while MS-TCN++ attains the highest balanced accuracy.

Jiaheng Dai, Huanrong Liu, Tailai Zhou +7

Fudan University, Shanghai, China · University of Macau, Macau, China · The Chinese PLA General Hospital, Beijing, China +1

Temporal Action Segmentation Surgical Video Understanding Video Action Recognition Surgical Robotics

Apr 8, 2026

Insights from Visual Cognition: Understanding Human Action Dynamics with Overall Glance and Refined Gaze Transformer

Recently, Transformer has made significant progress in various vision tasks. To balance computation and efficiency in video tasks, recent works heavily rely on factorized or window-based self-attention. However, these approaches split spatiotemporal correlations between regions of interest in videos, limiting the models' ability to capture motion and long-range dependencies. In this paper, we argue that, similar to the human visual system, the importance of temporal and spatial information varies across different time scales, and attention is allocated sparsely over time through glance and gaze behavior. Is equal consideration of time and space crucial for success in video tasks? Motivated by this understanding, we propose a dual-path network called the Overall Glance and Refined Gaze (OG-ReG) Transformer. The Glance path extracts coarse-grained overall spatiotemporal information, while the Gaze path supplements the Glance path by providing local details. Our model achieves state-of-the-art results on the Kinetics-400, Something-Something v2, and Diving-48, demonstrating its competitive performance. The code will be available at https://github.com/linuxsino/OG-ReG.

Bohao Xing, Deng Li, Rong Gao +2

Department of Computational Engineering, Lappeenranta-Lahti University of Technology LUT, Finland · Faculty of Information Technology, Brno University of Technology, Czech Republic

Video Action Recognition Spatiotemporal Transformers 3D ViTs Temporal Attention

Apr 4, 2026

SBF: An Effective Representation to Augment Skeleton for Video-based Human Action Recognition

Many modern video-based human action recognition (HAR) approaches use 2D skeleton as the intermediate representation in their prediction pipelines. Despite overall encouraging results, these approaches still struggle in many common scenes, mainly because the skeleton does not capture critical action-related information pertaining to the depth of the joints, contour of the human body, and interaction between the human and objects. To address this, we propose an effective approach to augment skeleton with a representation capturing action-related information in the pipeline of HAR. The representation, termed Scale-Body-Flow (SBF), consists of three distinct components, namely a scale map volume given by the scale (and hence depth information) of each joint, a body map outlining the human subject, and a flow map indicating human-object interaction given by pixel-wise optical flow values. To predict SBF, we further present SFSNet, a novel segmentation network supervised by the skeleton and optical flow without extra annotation overhead beyond the existing skeleton extraction. Extensive experiments across different datasets demonstrate that our pipeline based on SBF and SFSNet achieves significantly higher HAR accuracy with similar compactness and efficiency as compared with the state-of-the-art skeleton-only approaches.

Zhuoxuan Peng, Yiyi Ding, Yang Lin +1

The Hong Kong University of Science and Technology · The Hong Kong University of Science and Technology (Guangzhou)

Video Action Recognition Skeleton-Based Action Recognition Motion Representation Learning Flow Map Learning

Apr 1, 2026

ViTs for Action Classification in Videos: An Approach to Risky Tackle Detection in American Football Practice Videos

Early identification of hazardous actions in contact sports enables timely intervention and improves player safety. We present a method for detecting risky tackles in American football practice videos and introduce a substantially expanded dataset for this task. Our work contains 733 single-athlete-dummy tackle clips, each temporally localized around first point contact and labeled with a strike zone component of the standardized Assessment for Tackling Technique (SATT-3), extending prior work that reported 178 annotated videos. Using a Vision transformer-based model with imbalance-aware training, we obtain risky recall of 0.67 and Risky F1 of 0.59 under crossvalidation. Relative to the previous baseline in a smaller subset (risky recall of 0.58; Risky F1 0.56 ), our approach improves risky recall by more than 8% points on a much larger dataset. These results indicate that the vision transformer-based video analysis, coupled with careful handling of class imbalance, can reliably detect rare but safety-critical tackling patterns, offering a practical pathway toward coach-centered injury prevention tools.

Syed Ahsan Masud Zaidi, William Hsu, Scott Dietrich

Kansas State University, Manhattan , KS ,66506, USA · Albright College, Athletics/Athletic training, Reading, PA,1962, USA

Sports Video Analysis Video Action Recognition

Apr 1, 2026

PrivHAR-Bench: A Graduated Privacy Benchmark Dataset for Video-Based Action Recognition

Existing research on privacy-preserving Human Activity Recognition (HAR) typically evaluates methods against a binary paradigm: clear video versus a single privacy transformation. This limits cross-method comparability and obscures the nuanced relationship between privacy strength and recognition utility. We introduce PrivHAR-Bench, a multi-tier benchmark dataset designed to standardize the evaluation of the Privacy-Utility Trade-off in video-based action recognition. PrivHAR-Bench applies a graduated spectrum of visual privacy transformations: from lightweight spatial obfuscation to cryptographic block permutation, to a curated subset of 15 activity classes selected for human articulation diversity. Each of the 1,932 source videos is distributed across 9 parallel tiers of increasing privacy strength, with additional background-removed variants to isolate the contribution of human motion features from contextual scene bias. We provide lossless frame sequences, per-frame bounding boxes, estimated pose keypoints with joint-level confidence scores, standardized group-based train/test splits, and an evaluation toolkit computing recognition accuracy and privacy metrics. Empirical validation using R3D-18 demonstrates a measurable and interpretable degradation curve across tiers, with within-tier accuracy declining from 88.8% (clear) to 53.5% (encrypted, background-removed) and cross-domain accuracy collapsing to 4.8%, establishing PrivHAR-Bench as a controlled benchmark for comparing privacy-preserving HAR methods under standardized conditions. The dataset, generation pipeline, and evaluation code are publicly available.

Samar Ansari

School of Computer and Engineering Sciences University of Chester Chester, CH1 4BJ, United Kingdom

Privacy-Utility Tradeoff Human Activity Recognition Privacy-Preserving ML Video Action Recognition

Mar 27, 2026

From Pixels to Privacy: Temporally Consistent Video Anonymization via Token Pruning for Privacy Preserving Action Recognition

Recent advances in large-scale video models have significantly improved video understanding across domains such as surveillance, healthcare, and entertainment. However, these models also amplify privacy risks by encoding sensitive attributes, including facial identity, race, and gender. While image anonymization has been extensively studied, video anonymization remains relatively underexplored, even though modern video models can leverage spatiotemporal motion patterns as biometric identifiers. To address this challenge, we propose a novel attention-driven spatiotemporal video anonymization framework based on systematic disentanglement of utility and privacy features. Our key insight is that attention mechanisms in Vision Transformers (ViTs) can be explicitly structured to separate action-relevant information from privacy-sensitive content. Building on this insight, we introduce two task-specific classification tokens, an action CLS token and a privacy CLS token, that learn complementary representations within a shared Transformer backbone. We contrast their attention distributions to compute a utility-privacy score for each spatiotemporal tubelet, and keep the top-k tubelets with the highest scores. This selectively prunes tubelets dominated by privacy cues while preserving those most critical for action recognition. Extensive experiments demonstrate that our approach maintains action recognition performance comparable to models trained on raw videos, while substantially reducing privacy leakage. These results indicate that attention-driven spatiotemporal pruning offers an effective and principled solution for privacy-preserving video analytics.

Nazia Aslam, Abhisek Ray, Joakim Bruslund Haurum +2

Aalborg University, Denmark · Aarhus University, Denmark · Poineer Centre for AI, Denmark +2

Privacy-Preserving ML Visual Token Pruning Video Action Recognition

Mar 26, 2026

SurgPhase: Time efficient pituitary tumor surgery phase recognition via an interactive web platform

Accurate surgical phase recognition is essential for analyzing procedural workflows, supporting intraoperative decision-making, and enabling data-driven improvements in surgical education and performance evaluation. In this work, we present a comprehensive framework for phase recognition in pituitary tumor surgery (PTS) videos, combining self-supervised representation learning, robust temporal modeling, and scalable data annotation strategies. Our method achieves 90% accuracy on a held-out test set, outperforming current state-of-the-art approaches and demonstrating strong generalization across variable surgical cases. A central contribution of this work is the integration of a collaborative online platform designed for surgeons to upload surgical videos, receive automated phase analysis, and contribute to a growing dataset. This platform not only facilitates large-scale data collection but also fosters knowledge sharing and continuous model improvement. To address the challenge of limited labeled data, we pretrain a ResNet-50 model using the self-supervised framework on 251 unlabeled PTS videos, enabling the extraction of high-quality feature representations. Fine-tuning is performed on a labeled dataset of 81 procedures using a modified training regime that incorporates focal loss, gradual layer unfreezing, and dynamic sampling to address class imbalance and procedural variability.

Yan Meng, Jack Cook, X. Y. Han +12

Children’s National Hospital, 111 Michigan Ave NW, Washington, 20010, DC, USA · Surgical Data Science Collective, 2000 Pennsylvania Ave. NW, Suite 7000, Washington, 20006, DC, USA · Booth School of Business, University of Chicago, 5807 S Woodlawn Ave, Chicago, 60637, IL, USA +7

Surgical Video Understanding Video Action Recognition Temporal Video Understanding

Mar 25, 2026

B-MoE: A Body-Part-Aware Mixture-of-Experts "All Parts Matter" Approach to Micro-Action Recognition

Micro-actions, fleeting and low-amplitude motions, such as glances, nods, or minor posture shifts, carry rich social meaning but remain difficult for current action recognition models to recognize due to their subtlety, short duration, and high inter-class ambiguity. In this paper, we introduce B-MoE, a Body-part-aware Mixture-of-Experts framework designed to explicitly model the structured nature of human motion. In B-MoE, each expert specializes in a distinct body region (head, body, upper limbs, lower limbs), and is based on the lightweight Macro-Micro Motion Encoder (M3E) that captures long-range contextual structure and fine-grained local motion. A cross-attention routing mechanism learns inter-region relationships and dynamically selects the most informative regions for each micro-action. B-MoE uses a dual-stream encoder that fuses these region-specific semantic cues with global motion features to jointly capture spatially localized cues and temporally subtle variations that characterize micro-actions. Experiments on three challenging benchmarks (MA-52, SocialGesture, and MPII-GroupInteraction) show consistent state-of-theart gains, with improvements in ambiguous, underrepresented, and low amplitude classes.

Nishit Poddar, Aglind Reka, Diana-Laura Borza +4

INRIA · Birla Institute of Technology & Science, Hyderabad · Université Côte d’Azur

Video Action Recognition Mixture-of-Experts Models

Mar 22, 2026

Privacy-Preserving Federated Action Recognition via Differentially Private Selective Tuning and Efficient Communication

Federated video action recognition enables collaborative model training without sharing raw video data, yet remains vulnerable to two key challenges: model exposure and communication overhead. Gradients exchanged between clients and the server can leak private motion patterns, while full-model synchronization of high-dimensional video networks causes significant bandwidth and communication costs. To address these issues, we propose Federated Differential Privacy with Selective Tuning and Efficient Communication for Action Recognition, namely FedDP-STECAR. Our FedDP-STECAR framework selectively fine-tunes and perturbs only a small subset of task-relevant layers under Differential Privacy (DP), reducing the surface of information leakage while preserving temporal coherence in video features. By transmitting only the tuned layers during aggregation, communication traffic is reduced by over 99% compared to full-model updates. Experiments on the UCF-101 dataset using the MViT-B-16x4 transformer show that FedDP-STECAR achieves up to 70.2% higher accuracy under strict privacy (

ε=0.65

) in centralized settings and 48% faster training with 73.1% accuracy in federated setups, enabling scalable and privacy-preserving video action recognition. Code available at https://github.com/izakariyya/mvit-federated-videodp

Idris Zakariyya, Pai Chet Ng, Kaushik Bhargav Sivangi +3

School of Computing Science, University of Glasgow, G12 8QQ, Glasgow, UK · Infocomm Technology Cluster, Singapore Institute of Technology, Singapore · The Edward S. Rogers Sr. Dept. of Electrical and Computer Engineering, University of Toronto, Canada

Differentially Private Federated Learning Video Action Recognition Communication-Efficient Distributed Training Selective Fine-Tuning

Mar 13, 2026

Generalized Recognition of Basic Surgical Actions Enables Skill Assessment and Vision-Language-Model-based Surgical Planning

Artificial intelligence, imaging, and large language models have the potential to transform surgical practice, training, and automation. Understanding and modeling of basic surgical actions (BSA), the fundamental unit of operation in any surgery, is important to drive the evolution of this field. In this paper, we present a BSA dataset comprising 10 basic actions across 6 surgical specialties with over 11,000 video clips, which is the largest to date. Based on the BSA dataset, we developed a new foundation model that conducts general-purpose recognition of basic actions. Our approach demonstrates robust cross-specialist performance in experiments validated on datasets from different procedural types and various body parts. Furthermore, we demonstrate downstream applications enabled by the BAS foundation model through surgical skill assessment in prostatectomy using domain-specific knowledge, and action planning in cholecystectomy and nephrectomy using large vision-language models. Multinational surgeons' evaluation of the language model's output of the action planning explainable texts demonstrated clinical relevance. These findings indicate that basic surgical actions can be robustly recognized across scenarios, and an accurate BSA understanding model can essentially facilitate complex applications and speed up the realization of surgical superintelligence.

Mengya Xu, Daiyun Shen, Jie Zhang +19

Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China · Department of Biomedical Engineering, National University of Singapore, Singapore · Department of Surgery, The Chinese University of Hong Kong, Hong Kong, China +13

Surgical Video Understanding Video Action Recognition

Mar 9, 2026

Human-AI Divergence in Ego-centric Action Recognition under Spatial and Spatiotemporal Manipulations

Humans consistently outperform state-of-the-art AI models in action recognition, particularly in challenging real-world conditions involving low resolution, occlusion, and visual clutter. Understanding the sources of this performance gap is essential for developing more robust and human-aligned models. In this paper, we present a large-scale human-AI comparative study of egocentric action recognition using Minimal Identifiable Recognition Crops (MIRCs), defined as the smallest spatial or spatiotemporal regions sufficient for reliable human recognition. We used our previously introduced, Epic ReduAct, a systematically spatially reduced and temporally scrambled dataset derived from 36 EPIC KITCHENS videos, spanning multiple spatial reduction levels and temporal conditions. Recognition performance is evaluated using over 3,000 human participants and the Side4Video model. Our analysis combines quantitative metrics, Average Reduction Rate and Recognition Gap, with qualitative analyses of spatial (high-, mid-, and low-level visual features) and spatiotemporal factors, including a categorisation of actions into Low Temporal Actions (LTA) and High Temporal Actions (HTA). Results show that human performance exhibits sharp declines when transitioning from MIRCs to subMIRCs, reflecting a strong reliance on sparse, semantically critical cues such as hand-object interactions. In contrast, the model degrades more gradually and often relies on contextual and mid- to low-level features, sometimes even exhibiting increased confidence under spatial reduction. Temporally, humans remain robust to scrambling when key spatial cues are preserved, whereas the model often shows insensitivity to temporal disruption, revealing class-dependent temporal sensitivities.

Sadegh Rahmaniboldaji, Filip Rybansky, Quoc C. Vuong +3

University of Surrey, Guildford, UK · Newcastle University, Newcastle upon Tyne, UK

Video Action Recognition Human Activity Recognition Egocentric Video Understanding Temporal Video Understanding

Mar 9, 2026

Novel Semantic Prompting for Zero-Shot Action Recognition

Zero-shot action recognition relies on transferring knowledge from vision-language models to unseen actions using semantic descriptions. While recent methods focus on temporal modeling or architectural adaptations to handle video data, we argue that semantic prompting alone provides a strong and underexplored signal for zero-shot action understanding. We introduce SP-CLIP, a lightweight framework that augments frozen vision-language models with structured semantic prompts describing actions at multiple levels of abstraction, such as intent, motion, and object interaction. Without modifying the visual encoder or learning additional parameters, SP-CLIP aligns video representations with enriched textual semantics through prompt aggregation and consistency scoring. Experiments across standard benchmarks show that semantic prompting substantially improves zero-shot action recognition, particularly for fine-grained and compositional actions, while preserving the efficiency and generalization of pretrained models.

Salman Iqbal, Waheed Rehman

Zero-Shot Action Recognition Video Action Recognition Zero-Shot Learning Vision-Language Models LLM Prompting

Mar 4, 2026

A Baseline Study and Benchmark for Few-Shot Open-Set Action Recognition with Feature Residual Discrimination

Few-Shot Action Recognition (FS-AR) has shown promising results but is often limited by a closed-set assumption that fails in real-world open-set scenarios. While Few-Shot Open-Set (FSOS) recognition is well-established for images, its extension to spatio-temporal video data remains underexplored. To address this, we propose an architectural extension based on a Feature-Residual Discriminator (FR-Disc), adapting previous work on skeletal data to the more complex video domain. Extensive experiments on five datasets demonstrate that while common open-set techniques provide only marginal gains, our FR-Disc significantly enhances unknown rejection capabilities without compromising closed-set accuracy, setting a new state-of-the-art for FSOS-AR. The project website, code, and benchmark are available at: https://hsp-iit.github.io/fsosar/.

Stefano Berti, Giulia Pasquale, Lorenzo Natale

Humanoid Sensing and Perception, Istituto Italiano di Tecnologia, Genoa, Italy

Open-Set Recognition Few-Shot Learning Video Action Recognition

Mar 2, 2026

OpenMarcie: Dataset for Multimodal Action Recognition in Industrial Environments

Smart factories use advanced technologies to optimize production and increase efficiency. To this end, the recognition of worker activity allows for accurate quantification of performance metrics, improving efficiency holistically while contributing to worker safety. OpenMarcie is, to the best of our knowledge, the biggest multimodal dataset designed for human action monitoring in manufacturing environments. It includes data from wearables sensing modalities and cameras distributed in the surroundings. The dataset is structured around two experimental settings, involving a total of 36 participants. In the first setting, twelve participants perform a bicycle assembly and disassembly task under semi-realistic conditions without a fixed protocol, promoting divergent and goal-oriented problem-solving. The second experiment involves twenty-five volunteers (24 valid data) engaged in a 3D printer assembly task, with the 3D printer manufacturer's instructions provided to guide the volunteers in acquiring procedural knowledge. This setting also includes sequential collaborative assembly, where participants assess and correct each other's progress, reflecting real-world manufacturing dynamics. OpenMarcie includes over 37 hours of egocentric and exocentric, multimodal, and multipositional data, featuring eight distinct data types and more than 200 independent information channels. The dataset is benchmarked across three human activity recognition tasks: activity classification, open vocabulary captioning, and cross-modal alignment.

Hymalai Bello, Lala Ray, Joanna Sorysz +2

DFKI Kaiserslautern · RPTU Kaiserslautern-Landau · Korea University

Human Activity Recognition Video Action Recognition Multimodal Learning Cross-Modal Alignment

Feb 23, 2026

BigMaQ: A Big Macaque Motion and Animation Dataset Bridging Image and 3D Pose Representations

The recognition of dynamic and social behavior in animals is fundamental for advancing ethology, ecology, medicine and neuroscience. Recent progress in deep learning has enabled automated behavior recognition from video, yet an accurate reconstruction of the three-dimensional (3D) pose and shape has not been integrated into this process. Especially for non-human primates, mesh-based tracking efforts lag behind those for other species, leaving pose descriptions restricted to sparse keypoints that are unable to fully capture the richness of action dynamics. To address this gap, we introduce the

\textbf{Big Ma}

ca

\textbf{Q}

ue 3D Motion and Animation Dataset (

\texttt{BigMaQ}

), a large-scale dataset comprising more than 750 scenes of interacting rhesus macaques with detailed 3D pose descriptions. Extending previous surface-based animal tracking methods, we construct subject-specific textured avatars by adapting a high-quality macaque template mesh to individual monkeys. This allows us to provide pose descriptions that are more accurate than previous state-of-the-art surface-based animal tracking methods. From the original dataset, we derive BigMaQ500, an action recognition benchmark that links surface-based pose vectors to single frames across multiple individual monkeys. By pairing features extracted from established image and video encoders with and without our pose descriptors, we demonstrate substantial improvements in mean average precision (mAP) when pose information is included. With these contributions,

\texttt{BigMaQ}

establishes the first dataset that both integrates dynamic 3D pose-shape representations into the learning task of animal action recognition and provides a rich resource to advance the study of visual appearance, posture, and social interaction in non-human primates. The code and data are publicly available at https://martinivis.github.io/BigMaQ/ .

Lucas Martini, Alexander Lappe, Anna Bognár +2

Hertie Institute, University of Tübingen · IMPRS-IS · KU Leuven

Video Action Recognition Markerless Motion Capture 3D Mesh Reconstruction

Feb 21, 2026

Frame2Freq: Spectral Adapters for Fine-Grained Video Understanding

Adapting image-pretrained backbones to video typically relies on time-domain adapters tuned to a single temporal scale. Our experiments show that these modules pick up static image cues and very fast flicker changes, while overlooking medium-speed motion. Capturing dynamics across multiple time-scales is, however, crucial for fine-grained temporal analysis (i.e., opening vs. closing bottle). To address this, we introduce Frame2Freq -- a family of frequency-aware adapters that perform spectral encoding during image-to-video adaptation of pretrained Vision Foundation Models (VFMs), improving fine-grained action recognition. Frame2Freq uses Fast Fourier Transform (FFT) along time and learns frequency-band specific embeddings that adaptively highlight the most discriminative frequency ranges. Across five fine-grained activity recognition datasets, Frame2Freq outperforms prior PEFT methods and even surpasses fully fine-tuned models on four of them. These results provide encouraging evidence that frequency analysis methods are a powerful tool for modeling temporal dynamics in image-to-video transfer. Code is available at https://github.com/th-nesh/Frame2Freq.

Thinesh Thiyakesan Ponbagavathi, Constantin Seibold, Alina Roitberg

Institute for Artificial Intelligence, University of Stuttgart, Germany · Intelligent Assistive Systems Lab, University of Hildesheim · University Hospital Heidelberg, Diagnostic and Interventional Radiology

Video Action Recognition Vision Foundation Model Adaptation Frequency-Domain Feature Learning Parameter-Efficient Fine-Tuning

Feb 20, 2026

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

Few-Shot Action Recognition (FSAR) is a challenging task that requires recognizing novel action categories with a few labeled videos. Recent works typically apply semantically coarse category names as auxiliary contexts to guide the learning of discriminative visual features. However, such context provided by the action names is too limited to provide sufficient background knowledge for capturing novel spatial and temporal concepts in actions. In this paper, we propose DiST, an innovative Decomposition-incorporation framework for FSAR that makes use of decoupled Spatial and Temporal knowledge provided by large language models to learn expressive multi-granularity prototypes. In the decomposition stage, we decouple vanilla action names into diverse spatio-temporal attribute descriptions (action-related knowledge). Such commonsense knowledge complements semantic contexts from spatial and temporal perspectives. In the incorporation stage, we propose Spatial/Temporal Knowledge Compensators (SKC/TKC) to discover discriminative object-level and frame-level prototypes, respectively. In SKC, object-level prototypes adaptively aggregate important patch tokens under the guidance of spatial knowledge. Moreover, in TKC, frame-level prototypes utilize temporal attributes to assist in inter-frame temporal relation modeling. These learned prototypes thus provide transparency in capturing fine-grained spatial details and diverse temporal patterns. Experimental results show DiST achieves state-of-the-art results on five standard FSAR datasets.

Hongyu Qu, Xiangbo Shu, Rui Yan +3

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.

Video Action Recognition Few-Shot Learning Prototype Learning

Jan 22, 2026

Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition

Zero-Shot Compositional Action Recognition (ZS-CAR) requires recognizing novel verb-object combinations composed of previously observed primitives. In this work, we tackle a key failure mode: models predict verbs via object-driven shortcuts (i.e., relying on the labeled object class) rather than temporal evidence. We argue that sparse compositional supervision and verb-object learning asymmetry can promote object-driven shortcut learning. Our analysis with proposed diagnostic metrics shows that existing methods overfit to training co-occurrence patterns and underuse temporal verb cues, resulting in weak generalization to unseen compositions. To address object-driven shortcuts, we propose Robust COmpositional REpresentations (RCORE) with two components. Co-occurrence Prior Regularization (CPR) adds explicit supervision for unseen compositions and regularizes the model against frequent co-occurrence priors by treating them as hard negatives. Temporal Order Regularization for Composition (TORC) enforces temporal-order sensitivity to learn temporally grounded verb representations. Across Sth-com and EK100-com, RCORE reduces shortcut diagnostics and consequently improves compositional generalization.

Geo Ahn, Inwoong Lee, Taeoh Kim +3

1Kyung Hee University · ∗This work was done during an internship at NAVER Cloud. · 2NAVER Cloud

Zero-Shot Learning Video Action Recognition Shortcut Learning Compositional Representation Learning Compositional Generalization Zero-Shot Action Recognition

Nov 17, 2025

MGCA-Net: Multi-Grained Category-Aware Network for Open-Vocabulary Temporal Action Localization

Open-Vocabulary Temporal Action Localization (OV-TAL) aims to recognize and localize instances of any desired action categories in videos without explicitly curating training data for all categories. Existing methods mostly recognize action categories at a single granularity, which degrades the recognition accuracy of both base and novel action categories. To address these issues, we propose a Multi-Grained Category-Aware Network (MGCA-Net) comprising a localizer, an action presence predictor, a conventional classifier, and a coarse-to-fine classifier. Specifically, the localizer localizes category-agnostic action proposals. For these action proposals, the action presence predictor estimates the probability that they belong to an action instance. At the same time, the conventional classifier predicts the probability of each action proposal over base action categories at the snippet granularity. Novel action categories are recognized by the coarse-to-fine classifier, which first identifies action presence at the video granularity. Finally, it assigns each action proposal to one category from the coarse categories at the proposal granularity. Through coarse-to-fine category awareness for novel actions and the conventional classifier's awareness of base actions, multi-grained category awareness is achieved, effectively enhancing localization performance. Comprehensive evaluations on the THUMOS'14 and ActivityNet-1.3 benchmarks demonstrate that our method achieves state-of-the-art performance. Furthermore, our MGCA-Net achieves state-of-the-art results under the Zero-Shot Temporal Action Localization setting.

Zhenying Fang, Richang Hong

School of Computer Science and Information Engineering, Hefei University of Technology, 188065, China

Video Action Recognition Temporal Action Detection Temporal Video Understanding Temporal Action Localization

Apr 14, 2025

Hierarchical Relation-augmented Representation Generalization for Few-shot Action Recognition

Few-shot action recognition (FSAR) aims to recognize novel action categories with few exemplars. Existing methods typically learn frame-level representations for each video by designing inter-frame temporal modeling strategies or inter-video interaction at the coarse video-level granularity. However, they treat each episode task in isolation and neglect fine-grained temporal relation modeling between videos, thus failing to capture shared fine-grained temporal patterns across videos and reuse temporal knowledge from historical tasks. In light of this, we propose HR2G-shot, a Hierarchical Relation-augmented Representation Generalization framework for FSAR, which unifies three types of relation modeling (inter-frame, inter-video, and inter-task) to learn task-specific temporal patterns from a holistic view. Going beyond conducting inter-frame temporal interactions, we further devise two components to respectively explore inter-video and inter-task relationships: i) Inter-video Semantic Correlation (ISC) performs cross-video frame-level interactions in a fine-grained manner, thereby capturing task-specific query features and enhancing both intra-class consistency and inter-class separability; ii) Inter-task Knowledge Transfer (IKT) retrieves and aggregates relevant temporal knowledge from the bank, which stores diverse temporal patterns from historical episode tasks. Extensive experiments on five benchmarks show that HR2G-shot outperforms current top-leading FSAR methods.

Hongyu Qu, Ling Xing, Jiachao Zhang +3

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

Temporal Reasoning Hierarchical Representation Learning Few-Shot Learning Video Action Recognition

Mar 3, 2024

XOV-Action: Towards Generalizable Open-Vocabulary Action Recognition

Inspired by the impressive success of image-text foundation models, recent works have proposed to adapt these foundation models to video data, leading to efficient and effective video models for open-vocabulary action recognition. However, through a comprehensive evaluation, our work finds that state-of-the-art open-vocabulary action recognition models still struggle with generalization to video domains that they have not encountered. To address this limitation, we introduce generalizable open-vocabulary action recognition, which aims to develop action recognition models capable of generalizing to both novel action categories and unseen video domains. Our work contributes a novel model named XOV-Action to overcome two critical challenges: (1) understanding novel action concepts of open-set categories, and (2) mitigating the scenario discrepancy between training and test datasets. Specifically, XOV-Action first proposes to capture diverse action-related concepts by learning diversified elaboration representations, which enables better generalization to open-set action categories. Second, XOV-Action learns scene-agnostic video representations to overcome the scene bias, which improves the generalization in unseen video domains. Additionally, to evaluate models in generalizable open-vocabulary action recognition, we contribute a new cross-domain action benchmark named XOVABench, which covers multiple video domains with varying degrees of gaps and consists of both closed-set and open-set action categories. Extensive quantitative and qualitative experiments demonstrate that our proposed XOV-Action can effectively improve action recognition performance for both closed-set and open-set categories across video domains. The benchmark is available at https://github.com/KunyuLin/XOV-Action/.

Kun-Yu Lin, Henghui Ding, Jia-Run Du +6

School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou 510275, China · Institute of Big Data, Fudan University, Shanghai 200433, China · AI Thrust, Hong Kong University of Science and Technology (Guangzhou), Guangzhou 511400, China +1

Open-Set Recognition Cross-Domain Generalization Video Action Recognition