Maintaining a consistent identity across video frames while estimating pose is crucial for downstream tasks such as behavior analysis and action recognition, yet existing pipelines largely decouple tracking and pose estimation. Top-down methods rely on per-frame detections followed by identity association, leading to increased computational cost and error propagation, whereas bottom-up approaches often struggle to preserve identity reliably in multi-instance settings. To address these limitations, we introduce DeepSTEP (STEP), a Transformer-based framework for joint tracking and pose estimation across diverse animal species and humans. STEP unifies localization, identity maintenance, and keypoint estimation into a single model, eliminating the need for per-frame detections or post hoc matching. Our approach leverages discriminative model weight prediction to propagate target identity across frames while predicting anatomically meaningful keypoints. Discriminative model prediction typically requires predefined target states. In contrast, STEP assumes only an initial bounding box in the first frame, removing the need for explicit keypoint initialization. This is enabled by two components: Gaussian Map Soft Prediction (GMSP) and Offset Map Regression Adapter (OMRA), which allow direct keypoint prediction and simplify inference. Starting from the initial bounding box, STEP tracks the subject and estimates its pose in subsequent frames. We train and evaluate STEP on datasets spanning multiple species, demonstrating strong performance and greater efficiency than existing methods. By jointly modeling tracking and pose, STEP provides an effective and scalable solution.
Zero-shot skeleton-based action recognition aims to classify unseen skeleton-based human actions without prior exposure to such categories during training. This task is extremely challenging due to the difficulty in generalizing from known to unknown actions. Previous studies typically use two-stage training: pre-training skeleton encoders on seen action categories using cross-entropy loss and then aligning pre-extracted skeleton and text features, enabling knowledge transfer to unseen classes through skeleton-text alignment and language models' generalization. However, their efficacy is hindered by 1) insufficient discrimination for skeleton features, as the fixed skeleton encoder fails to capture necessary alignment information for effective skeleton-text alignment; 2) the neglect of alignment bias between skeleton and unseen text features during testing. To this end, we propose a prototype-guided feature alignment paradigm for zero-shot skeleton-based action recognition, termed PGFA. Specifically, we develop an end-to-end cross-modal contrastive training framework to improve skeleton-text alignment, ensuring sufficient discrimination for skeleton features. Additionally, we introduce a prototype-guided text feature alignment strategy to mitigate the adverse impact of the distribution discrepancy during testing. We provide a theoretical analysis to support our prototype-guided text feature alignment strategy and empirically evaluate our overall PGFA on three well-known datasets. Compared with the top competitor SMIE method, our PGFA achieves absolute accuracy improvements of 22.96%, 12.53%, and 18.54% on the NTU-60, NTU-120, and PKU-MMD datasets, respectively.
Understanding behavior requires datasets that capture humans while carrying out complex tasks. The kitchen is an excellent environment for assessing human motor and cognitive function, as many complex actions are naturally exhibited in kitchens from chopping to cleaning. Here, we introduce the EPFL-Smart-Kitchen-30 dataset, collected in a noninvasive motion capture platform inside a kitchen environment. Nine static RGB-D cameras, inertial measurement units (IMUs) and one head-mounted HoloLens~2 headset were used to capture 3D hand, body, and eye movements. The EPFL-Smart-Kitchen-30 dataset is a multi-view action dataset with synchronized exocentric, egocentric, depth, IMUs, eye gaze, body and hand kinematics spanning 29.7 hours of 16 subjects cooking four different recipes. Action sequences were densely annotated with 33.78 action segments per minute. Leveraging this multi-modal dataset, we propose four benchmarks to advance behavior understanding and modeling through 1) a vision-language benchmark, 2) a semantic text-to-motion generation benchmark, 3) a multi-modal action recognition benchmark, 4) a pose-based action segmentation benchmark. We expect the EPFL-Smart-Kitchen-30 dataset to pave the way for better methods as well as insights to understand the nature of ecologically-valid human behavior. Code and data are available at https://github.com/amathislab/EPFL-Smart-Kitchen
Action segmentation is a core challenge in high-level video understanding, aiming to partition untrimmed videos into segments and assign each a label from a predefined action set. Existing methods primarily address single-person activities with fixed action sequences, overlooking multi-person scenarios. In this work, we pioneer textual reference-guided human action segmentation in multi-person settings, where a textual description specifies the target person for segmentation. We introduce the first dataset for Referring Human Action Segmentation, i.e., RHAS133, built from 133 movies and annotated with 137 fine-grained actions with 33h video data, together with textual descriptions for this new task. Benchmarking existing action recognition methods on RHAS133 using VLM-based feature extractors reveals limited performance and poor aggregation of visual cues for the target person. To address this, we propose a holistic-partial aware Fourier-conditioned diffusion framework, i.e., HopaDIFF, leveraging a novel cross-input gate attentional xLSTM to enhance holistic-partial long-range reasoning and a novel Fourier condition to introduce more fine-grained control to improve the action segmentation generation. HopaDIFF achieves state-of-the-art results on RHAS133 in diverse evaluation settings. The code is available at https://github.com/KPeng9510/HopaDIFF.git.
Few-Shot Action Recognition (FSAR) aims to train a model with only a few labeled video instances. A key challenge in FSAR is handling divergent narrative trajectories for precise video matching. While the frame- and tuple-level alignment approaches have been promising, their methods heavily rely on pre-defined and length-dependent alignment units (e.g., frames or tuples), which limits flexibility for actions of varying lengths and speeds. In this work, we introduce a novel TEmporal Alignment-free Matching (TEAM) approach, which eliminates the need for temporal units in action representation and brute-force alignment during matching. Specifically, TEAM represents each video with a fixed set of pattern tokens that capture globally discriminative clues within the video instance regardless of action length or speed, ensuring its flexibility. Furthermore, TEAM is inherently efficient, using token-wise comparisons to measure similarity between videos, unlike existing methods that rely on pairwise comparisons for temporal alignment. Additionally, we propose an adaptation process that identifies and removes common information across classes, establishing clear boundaries even between novel categories. Extensive experiments demonstrate the effectiveness of TEAM. Codes are available at github.com/leesb7426/TEAM.
Operating rooms (ORs) demand precise coordination among surgeons, nurses, and equipment in a fast-paced, occlusion-heavy environment, necessitating advanced perception models to enhance safety and efficiency. Existing datasets either provide partial egocentric views or sparse exocentric multi-view context, but do not explore the comprehensive combination of both. We introduce EgoExOR, the first OR dataset and accompanying benchmark to fuse first-person and third-person perspectives. Spanning 94 minutes (84,553 frames at 15 FPS) of two emulated spine procedures, Ultrasound-Guided Needle Insertion and Minimally Invasive Spine Surgery, EgoExOR integrates egocentric data (RGB, gaze, hand tracking, audio) from wearable glasses, exocentric RGB and depth from RGB-D cameras, and ultrasound imagery. Its detailed scene graph annotations, covering 36 entities and 22 relations (568,235 triplets), enable robust modeling of clinical interactions, supporting tasks like action recognition and human-centric perception. We evaluate the surgical scene graph generation performance of two adapted state-of-the-art models and offer a new baseline that explicitly leverages EgoExOR's multimodal and multi-perspective signals. This new dataset and benchmark set a new foundation for OR perception, offering a rich, multimodal resource for next-generation clinical perception.
Traditional approaches in unsupervised or self supervised learning for skeleton-based action classification have concentrated predominantly on the dynamic aspects of skeletal sequences. Yet, the intricate interaction between the moving and static elements of the skeleton presents a rarely tapped discriminative potential for action classification. This paper introduces a novel measurement, referred to as spatial-temporal joint density (STJD), to quantify such interaction. Tracking the evolution of this density throughout an action can effectively identify a subset of discriminative moving and/or static joints termed "prime joints" to steer self-supervised learning. A new contrastive learning strategy named STJD-CL is proposed to align the representation of a skeleton sequence with that of its prime joints while simultaneously contrasting the representations of prime and nonprime joints. In addition, a method called STJD-MP is developed by integrating it with a reconstruction-based framework for more effective learning. Experimental evaluations on the NTU RGB+D 60, NTU RGB+D 120, and PKUMMD datasets in various downstream tasks demonstrate that the proposed STJD-CL and STJD-MP improved performance, particularly by 3.5 and 3.6 percentage points over the state-of-the-art contrastive methods on the NTU RGB+D 120 dataset using X-sub and X-set evaluations, respectively.
Action recognition models using deep learning are vulnerable to adversarial examples, which are transferable across other models trained on the same data modality. Existing transferable attack methods face two major challenges: 1) they heavily rely on the assumption that the decision boundaries of the surrogate (a.k.a., source) model and the target model are similar, which limits the adversarial transferability; and 2) their decision boundary difference makes the attack direction uncertain, which may result in the gradient oscillation, weakening the adversarial attack. This motivates us to propose a Background Mixup-induced Temporal Consistency (BMTC) attack method for action recognition. From the input transformation perspective, we design a model-agnostic background adversarial mixup module to reduce the surrogate-target model dependency. In particular, we randomly sample one video from each category and make its background frame, while selecting the background frame with the top attack ability for mixup with the clean frame by reinforcement learning. Moreover, to ensure an explicit attack direction, we leverage the background category as guidance for updating the gradient of adversarial example, and design a temporal gradient consistency loss, which strengthens the stability of the attack direction on subsequent frames. Empirical studies on two video datasets, i.e., UCF101 and Kinetics-400, and one image dataset, i.e., ImageNet, demonstrate that our method significantly boosts the transferability of adversarial examples across several action/image recognition models. Our code is available at https://github.com/mlvccn/BMTC_TransferAttackVid.
Long-term Action Quality Assessment (AQA) aims to evaluate the quantitative performance of actions in long videos. However, existing methods face challenges due to domain shifts between the pre-trained large-scale action recognition backbones and the specific AQA task, thereby hindering their performance. This arises since fine-tuning resource-intensive backbones on small AQA datasets is impractical. We address this by identifying two levels of domain shift: task-level, regarding differences in task objectives, and feature-level, regarding differences in important features. For feature-level shifts, which are more detrimental, we propose Progressive Hierarchical Instruction (PHI) with two strategies. First, Gap Minimization Flow (GMF) leverages flow matching to progressively learn a fast flow path that reduces the domain gap between initial and desired features across shallow to deep layers. Additionally, a temporally-enhanced attention module captures long-range dependencies essential for AQA. Second, List-wise Contrastive Regularization (LCR) facilitates coarse-to-fine alignment by comprehensively comparing batch pairs to learn fine-grained cues while mitigating domain shift. Integrating these modules, PHI offers an effective solution. Experiments demonstrate that PHI achieves state-of-the-art performance on three representative long-term AQA datasets, proving its superiority in addressing the domain shift for long-term AQA.
This paper presents a novel inertial localization framework named Egocentric Action-aware Inertial Localization (EAIL), which leverages egocentric action cues from head-mounted IMU signals to localize the target individual within a 3D point cloud. Human inertial localization is challenging due to IMU sensor noise that causes trajectory drift over time. The diversity of human actions further complicates IMU signal processing by introducing various motion patterns. Nevertheless, we observe that some actions observed through the head-mounted IMU correlate with spatial environmental structures (e.g., bending down to look inside an oven, washing dishes next to a sink), thereby serving as spatial anchors to compensate for the localization drift. The proposed EAIL framework learns such correlations via hierarchical multi-modal alignment. By assuming that the 3D point cloud of the environment is available, it contrastively learns modality encoders that align short-term egocentric action cues in IMU signals with local environmental features in the point cloud. These encoders are then used in reasoning the IMU data and the point cloud over time and space to perform inertial localization. Interestingly, these encoders can further be utilized to recognize the corresponding sequence of actions as a by-product. Extensive experiments demonstrate the effectiveness of the proposed framework over state-of-the-art inertial localization and inertial action recognition baselines.
Spatial-temporal graph convolutional networks (ST-GCNs) showcase impressive performance in skeleton-based human action recognition (HAR). However, despite the development of numerous models, their recognition performance does not differ significantly after aligning the input settings. With this observation, we hypothesize that ST-GCNs are over-parameterized for HAR, a conjecture subsequently confirmed through experiments employing the lottery ticket hypothesis. Additionally, a novel sparse ST-GCNs generator is proposed, which trains a sparse architecture from a randomly initialized dense network while maintaining comparable performance levels to the dense components. Moreover, we generate multi-level sparsity ST-GCNs by integrating sparse structures at various sparsity levels and demonstrate that the assembled model yields a significant enhancement in HAR performance. Thorough experiments on four datasets, including NTU-RGB+D 60(120), Kinetics-400, and FineGYM, demonstrate that the proposed sparse ST-GCNs can achieve comparable performance to their dense components. Even with 95% fewer parameters, the sparse ST-GCNs exhibit a degradation of <1% in top-1 accuracy. Meanwhile, the multi-level sparsity ST-GCNs, which require only 66% of the parameters of the dense ST-GCNs, demonstrate an improvement of >1% in top-1 accuracy. The code is available at https://github.com/davelailai/Sparse-ST-GCN.
Computer-assisted interventions can improve intra-operative guidance, particularly through deep learning methods that harness the spatiotemporal information in surgical videos. However, the severe data imbalance often found in surgical video datasets hinders the development of high-performing models. In this work, we aim to overcome the data imbalance by synthesizing surgical videos. We propose a unique two-stage, text-conditioned diffusion-based method to generate high-fidelity surgical videos for under-represented classes. Our approach conditions the generation process on text prompts and decouples spatial and temporal modeling by utilizing a 2D latent diffusion model to capture spatial content and then integrating temporal attention layers to ensure temporal consistency. Furthermore, we introduce a rejection sampling strategy to select the most suitable synthetic samples, effectively augmenting existing datasets to address class imbalance. We evaluate our method on two downstream tasks-surgical action recognition and intra-operative event prediction-demonstrating that incorporating synthetic videos from our approach substantially enhances model performance. We open-source our implementation at https://gitlab.com/nct_tso_public/surgvgen.
Large-scale pre-trained models have achieved remarkable success in language and image tasks, leading an increasing number of studies to explore the application of pre-trained image models, such as CLIP, in the domain of few-shot action recognition (FSAR). However, current methods generally suffer from several problems: 1) Direct fine-tuning often undermines the generalization capability of the pre-trained model; 2) The exploration of task-specific information is insufficient in the visual tasks; 3) The semantic order information is typically overlooked during text modeling; 4) Existing cross-modal alignment techniques ignore the temporal coupling of multimodal information. To address these, we propose Task-Adapter++, a parameter-efficient dual adaptation method for both image and text encoders. Specifically, to make full use of the variations across different few-shot learning tasks, we design a task-specific adaptation for the image encoder so that the most discriminative information can be well noticed during feature extraction. Furthermore, we leverage large language models (LLMs) to generate detailed sequential sub-action descriptions for each action class, and introduce semantic order adapters into the text encoder to effectively model the sequential relationships between these sub-actions. Finally, we develop an innovative fine-grained cross-modal alignment strategy that actively maps visual features to reside in the same temporal stage as semantic descriptions. Extensive experiments fully demonstrate the effectiveness and superiority of the proposed method, which achieves state-of-the-art performance on 5 benchmarks consistently. The code is open-sourced at https://github.com/Jaulin-Bage/Task-Adapter-pp.
Wireless signal-based human sensing technologies, such as WiFi, millimeter-wave (mmWave) radar, and Radio Frequency Identification (RFID), enable the detection and interpretation of human presence, posture, and activities, thereby providing critical support for applications in public security, healthcare, and smart environments. These technologies exhibit notable advantages due to their non-contact operation and environmental adaptability; however, existing systems often fail to leverage the textual information inherent in datasets. To address this, we propose an innovative text-enhanced wireless sensing framework, WiTalk, that seamlessly integrates semantic knowledge through three hierarchical prompt strategies-label-only, brief description, and detailed action description-without requiring architectural modifications or incurring additional data costs. We rigorously validate this framework across three public benchmark datasets: XRF55 for human action recognition (HAR), and WiFiTAL and XRFV2 for WiFi temporal action localization (TAL). Experimental results demonstrate significant performance improvements: on XRF55, accuracy for WiFi, RFID, and mmWave increases by 3.9%, 2.59%, and 0.46%, respectively; on WiFiTAL, the average performance of WiFiTAD improves by 4.98%; and on XRFV2, the mean average precision gains across various methods range from 4.02% to 13.68%. Our codes have been included in https://github.com/yangzhenkui/WiTalk.
While current skeleton action recognition models demonstrate impressive performance on large-scale datasets, their adaptation to new application scenarios remains challenging. These challenges are particularly pronounced when facing new action categories, diverse performers, and varied skeleton layouts, leading to significant performance degeneration. Additionally, the high cost and difficulty of collecting skeleton data make large-scale data collection impractical. This paper studies one-shot and limited-scale learning settings to enable efficient adaptation with minimal data. Existing approaches often overlook the rich mutual information between labeled samples, resulting in sub-optimal performance in low-data scenarios. To boost the utility of labeled data, we identify the variability among performers and the commonality within each action as two key attributes. We present SkeletonX, a lightweight training pipeline that integrates seamlessly with existing GCN-based skeleton action recognizers, promoting effective training under limited labeled data. First, we propose a tailored sample pair construction strategy on two key attributes to form and aggregate sample pairs. Next, we develop a concise and effective feature aggregation module to process these pairs. Extensive experiments are conducted on NTU RGB+D, NTU RGB+D 120, and PKU-MMD with various GCN backbones, demonstrating that the pipeline effectively improves performance when trained from scratch with limited data. Moreover, it surpasses previous state-of-the-art methods in the one-shot setting, with only 1/10 of the parameters and much fewer FLOPs. The code and data are available at: https://github.com/zzysteve/SkeletonX
In this paper, we propose H-MoRe, a novel pipeline for learning precise human-centric motion representation. Our approach dynamically preserves relevant human motion while filtering out background movement. Notably, unlike previous methods relying on fully supervised learning from synthetic data, H-MoRe learns directly from real-world scenarios in a self-supervised manner, incorporating both human pose and body shape information. Inspired by kinematics, H-MoRe represents absolute and relative movements of each body point in a matrix format that captures nuanced motion details, termed world-local flows. H-MoRe offers refined insights into human motion, which can be integrated seamlessly into various action-related applications. Experimental results demonstrate that H-MoRe brings substantial improvements across various downstream tasks, including gait recognition(CL@R1: +16.01%), action recognition(Acc@1: +8.92%), and video generation(FVD: -67.07%). Additionally, H-MoRe exhibits high inference efficiency (34 fps), making it suitable for most real-time scenarios. Models and code will be released upon publication.
Multi-modal multi-view action recognition is a rapidly growing field in computer vision, offering significant potential for applications in surveillance. However, current datasets often fail to address real-world challenges such as wide-area distributed settings, asynchronous data streams, and the lack of frame-level annotations. Furthermore, existing methods face difficulties in effectively modeling inter-view relationships and enhancing spatial feature learning. In this paper, we introduce the MultiSensor-Home dataset, a novel benchmark designed for comprehensive action recognition in home environments, and also propose the Multi-modal Multi-view Transformer-based Sensor Fusion (MultiTSF) method. The proposed MultiSensor-Home dataset features untrimmed videos captured by distributed sensors, providing high-resolution RGB and audio data along with detailed multi-view frame-level action labels. The proposed MultiTSF method leverages a Transformer-based fusion mechanism to dynamically model inter-view relationships. Furthermore, the proposed method integrates a human detection module to enhance spatial feature learning, guiding the model to prioritize frames with human activity to enhance action the recognition accuracy. Experiments on the proposed MultiSensor-Home and the existing MM-Office datasets demonstrate the superiority of MultiTSF over the state-of-the-art methods. Quantitative and qualitative results highlight the effectiveness of the proposed method in advancing real-world multi-modal multi-view action recognition. The source code is available at https://github.com/thanhhff/MultiTSF.
The growing ageing population and their preference to maintain independence by living in their own homes require proactive strategies to ensure safety and support. Ambient Assisted Living (AAL) technologies have emerged to facilitate ageing in place by offering continuous monitoring and assistance within the home. Within AAL technologies, action recognition plays a crucial role in interpreting human activities and detecting incidents like falls, mobility decline, or unusual behaviours that may signal worsening health conditions. However, action recognition in practical AAL applications presents challenges, including occlusions, noisy data, and the need for real-time performance. While advancements have been made in accuracy, robustness to noise, and computation efficiency, achieving a balance among them all remains a challenge. To address this challenge, this paper introduces the Robust and Efficient Temporal Convolution network (RE-TCN), which comprises three main elements: Adaptive Temporal Weighting (ATW), Depthwise Separable Convolutions (DSC), and data augmentation techniques. These elements aim to enhance the model's accuracy, robustness against noise and occlusion, and computational efficiency within real-world AAL contexts. RE-TCN outperforms existing models in terms of accuracy, noise and occlusion robustness, and has been validated on four benchmark datasets: NTU RGB+D 60, Northwestern-UCLA, SHREC'17, and DHG-14/28. The code is publicly available at: https://github.com/Gbouna/RE-TCN
Advancements in computer-assisted surgical procedures heavily rely on accurate visual data interpretation from camera systems used during surgeries. Traditional open-access datasets focusing on surgical procedures are often limited by their small size, typically consisting of fewer than 100 videos with less than 100K images. To address these constraints, a new dataset called Surg-3M has been compiled using a novel aggregation pipeline that collects high-resolution videos from online sources. Featuring an extensive collection of over 4K surgical videos and more than 3 million high-quality images from multiple procedure types, Surg-3M offers a comprehensive resource surpassing existing alternatives in size and scope, including two novel tasks. To demonstrate the effectiveness of this dataset, we present SurgFM, a self-supervised foundation model pretrained on Surg-3M that achieves impressive results in downstream tasks such as surgical phase recognition, action recognition, and tool presence detection. Combining key components from ConvNeXt, DINO, and an innovative augmented distillation method, SurgFM exhibits exceptional performance compared to specialist architectures across various benchmarks. Our experimental results show that SurgFM outperforms state-of-the-art models in multiple downstream tasks, including significant gains in surgical phase recognition (+8.9pp, +4.7pp, and +3.9pp of Jaccard in AutoLaparo, M2CAI16, and Cholec80), action recognition (+3.1pp of mAP in CholecT50) and tool presence detection (+4.6pp of mAP in Cholec80). Moreover, even when using only half of the data, SurgFM outperforms state-of-the-art models in AutoLaparo and achieves state-of-the-art performance in Cholec80. Both Surg-3M and SurgFM have significant potential to accelerate progress towards developing autonomous robotic surgery systems.
Understanding human behavior requires measuring behavioral actions. Due to its complexity, behavior is best mapped onto a rich, semantic structure such as language. The recent development of multi-modal large language models (MLLMs) is a promising candidate for a wide range of action understanding tasks. In this work, we focus on evaluating and then improving MLLMs to perform action recognition. We reformulate EPIC-KITCHENS-100, one of the largest and most challenging egocentric action datasets, to the form of video multiple question answering (EPIC-KITCHENS-100-MQA). We show that when we sample difficult incorrect answers as distractors, leading MLLMs struggle to recognize the correct actions. We propose a series of methods that greatly improve the MLLMs' ability to perform action recognition, achieving state-of-the-art on both the EPIC-KITCHENS-100 validation set, as well as outperforming GPT-4o by 21 points in accuracy on EPIC-KITCHENS-100-MQA. Lastly, we show improvements on other action-related video benchmarks such as EgoSchema, PerceptionTest, LongVideoBench, VideoMME and MVBench, suggesting that MLLMs are a promising path forward for complex action tasks. Code and models are available at: https://github.com/AdaptiveMotorControlLab/LLaVAction.