The lack of occlusion data in commonly used action recognition video datasets limits model robustness and impedes sustained performance improvements. We construct OccludeNet, a large-scale occluded video dataset that includes both real-world and synthetic occlusion scene videos under various natural environments. OccludeNet features dynamic tracking occlusion, static scene occlusion, and multi-view interactive occlusion, addressing existing gaps in data. Our analysis reveals that occlusion impacts action classes differently, with actions involving low scene relevance and partial body visibility experiencing greater accuracy degradation. To overcome the limitations of current occlusion-focused approaches, we propose a structural causal model for occluded scenes and introduce the Causal Action Recognition (CAR) framework, which employs backdoor adjustment and counterfactual reasoning. This framework enhances key actor information, improving model robustness to occlusion. We anticipate that the challenges posed by OccludeNet will stimulate further exploration of causal relations in occlusion scenarios and encourage a reevaluation of class correlations, ultimately promoting sustainable performance improvements. The code and full dataset will be released soon.
Vision-language models (VLMs) are capable of recognizing unseen actions. However, existing VLMs lack intrinsic understanding of procedural action concepts. Hence, they overfit to fixed labels and are not invariant to unseen action synonyms. To address this, we propose a simple fine-tuning technique, Action Concept Enhancement (ACE), to improve the robustness and concept understanding of VLMs in procedural action classification. ACE continually incorporates augmented action synonyms and negatives in an auxiliary classification loss by stochastically replacing fixed labels during training. This creates new combinations of action labels over the course of fine-tuning and prevents overfitting to fixed action representations. We show the enhanced concept understanding of our VLM, by visualizing the alignment of encoded embeddings of unseen action synonyms in the embedding space. Our experiments on the ATA, IKEA and GTEA datasets demonstrate the efficacy of ACE in domains of cooking and assembly leading to significant improvements in zero-shot action classification while maintaining competitive performance on seen actions.
Falls among seniors due to difficulties with tasks such as picking up objects pose significant health and safety risks, impacting quality of life and independence. Reliable, accessible assessment tools are critical for early intervention but often require costly clinic-based equipment and trained personnel, limiting their use in daily life. Existing wearable-based pickup measurement solutions address some needs but face limitations in generalizability. We present IMUVIE, a wearable system that uses motion movies and a machine-learning model to automatically detect and measure pickup events, providing a practical solution for frequent monitoring. IMUVIE's design principles-data normalization, occlusion handling, and streamlined visuals-enhance model performance and are adaptable to tasks beyond pickup classification. In rigorous leave one subject out cross validation evaluations, IMUVIE achieves exceptional window level localization accuracy of 91-92% for pickup action classification on 256,291 motion movie frame candidates while maintaining an event level recall of 97% when evaluated on 129 pickup events. IMUVIE has strong generalization and performs well on unseen subjects. In an interview survey, IMUVIE demonstrated strong user interest and trust, with ease of use identified as the most critical factor for adoption. IMUVIE offers a practical, at-home solution for fall risk assessment, facilitating early detection of movement deterioration, and supporting safer, independent living for seniors.
Robots need to perceive persons in their surroundings for safety and to interact with them. In this paper, we present a person segmentation and action classification approach that operates on 3D scans of hemisphere field of view LiDAR sensors. We recorded a data set with an Ouster OSDome-64 sensor consisting of scenes where persons perform three different actions and annotated it. We propose a method based on a MaskDINO model to detect and segment persons and to recognize their actions from combined spherical projected multi-channel representations of the LiDAR data with an additional positional encoding. Our approach demonstrates good performance for the person segmentation task and further performs well for the estimation of the person action states walking, waving, and sitting. An ablation study provides insights about the individual channel contributions for the person segmentation task. The trained models, code and dataset are made publicly available.
Extracting multiscale contextual information and higher-order correlations among skeleton sequences using Graph Convolutional Networks (GCNs) alone is inadequate for effective action classification. Hypergraph convolution addresses the above issues but cannot harness the long-range dependencies. Transformer proves to be effective in capturing these dependencies and making complex contextual features accessible. We propose an Autoregressive Adaptive HyperGraph Transformer (AutoregAd-HGformer) model for in-phase (autoregressive and discrete) and out-phase (adaptive) hypergraph generation. The vector quantized in-phase hypergraph equipped with powerful autoregressive learned priors produces a more robust and informative representation suitable for hyperedge formation. The out-phase hypergraph generator provides a model-agnostic hyperedge learning technique to align the attributes with input skeleton embedding. The hybrid (supervised and unsupervised) learning in AutoregAd-HGformer explores the action-dependent feature along spatial, temporal, and channel dimensions. The extensive experimental results and ablation study indicate the superiority of our model over state-of-the-art hypergraph architectures on NTU RGB+D, NTU RGB+D 120, and NW-UCLA datasets.
Deep learning models, in particular \textit{image} models, have recently gained generalisability and robustness. %are becoming more general and robust by the day. In this work, we propose to exploit such advances in the realm of \textit{video} classification. Video foundation models suffer from the requirement of extensive pretraining and a large training time. Towards mitigating such limitations, we propose "\textit{Attention Map (AM) Flow}" for image models, a method for identifying pixels relevant to motion in each input video frame. In this context, we propose two methods to compute AM flow, depending on camera motion. AM flow allows the separation of spatial and temporal processing, while providing improved results over combined spatio-temporal processing (as in video models). Adapters, one of the popular techniques in parameter efficient transfer learning, facilitate the incorporation of AM flow into pretrained image models, mitigating the need for full-finetuning. We extend adapters to "\textit{temporal processing adapters}" by incorporating a temporal processing unit into the adapters. Our work achieves faster convergence, therefore reducing the number of epochs needed for training. Moreover, we endow an image model with the ability to achieve state-of-the-art results on popular action recognition datasets. This reduces training time and simplifies pretraining. We present experiments on Kinetics-400, Something-Something v2, and Toyota Smarthome datasets, showcasing state-of-the-art or comparable results.
We show that useful video representations can be learned from synthetic videos and natural images, without incorporating natural videos in the training. We propose a progression of video datasets synthesized by simple generative processes, that model a growing set of natural video properties (e.g., motion, acceleration, and shape transformations). The downstream performance of video models pre-trained on these generated datasets gradually increases with the dataset progression. A VideoMAE model pre-trained on our synthetic videos closes 97.2\% of the performance gap on UCF101 action classification between training from scratch and self-supervised pre-training from natural videos, and outperforms the pre-trained model on HMDB51. Introducing crops of static images to the pre-training stage results in similar performance to UCF101 pre-training and outperforms the UCF101 pre-trained model on 11 out of 14 out-of-distribution datasets of UCF101-P. Analyzing the low-level properties of the datasets, we identify correlations between frame diversity, frame similarity to natural data, and downstream performance. Our approach provides a more controllable and transparent alternative to video data curation processes for pre-training.
Combining sports and machine learning involves leveraging ML algorithms and techniques to extract insight from sports-related data such as player statistics, game footage, and other relevant information. However, datasets related to figure skating in the literature focus primarily on element classification and are currently unavailable or exhibit only limited access, which greatly raise the entry barrier to developing visual sports technology for it. Moreover, when using such data to help athletes improve their skills, we find they are very coarse-grained: they work for learning what an element is, but they are poorly suited to learning whether the element is good or bad. Here we propose air time detection, a novel motion analysis task, the goal of which is to accurately detect the duration of the air time of a jump. We present YourSkatingCoach, a large, novel figure skating dataset which contains 454 videos of jump elements, the detected skater skeletons in each video, along with the gold labels of the start and ending frames of each jump, together as a video benchmark for figure skating. In addition, although this type of task is often viewed as classification, we cast it as a sequential labeling problem and propose a Transformer-based model to calculate the duration. Experimental results show that the proposed model yields a favorable results for a strong baseline. To further verify the generalizability of the fine-grained labels, we apply the same process to other sports as cross-sports tasks but for coarse-grained task action classification. Here we fine-tune the classification to demonstrate that figure skating, as it contains the essential body movements, constitutes a strong foundation for adaptation to other sports.
Current vision-language foundation models, such as CLIP, have recently shown significant improvement in performance across various downstream tasks. However, whether such foundation models significantly improve more complex fine-grained action recognition tasks is still an open question. To answer this question and better find out the future research direction on human behavior analysis in-the-wild, this paper provides a large-scale study and insight on current state-of-the-art vision foundation models by comparing their transfer ability onto zero-shot and frame-wise action recognition tasks. Extensive experiments are conducted on recent fine-grained, human-centric action recognition datasets (e.g., Toyota Smarthome, Penn Action, UAV-Human, TSU, Charades) including action classification and segmentation.
As Artificial Intelligence models, such as Large Video-Language models (VLMs), grow in size, their deployment in real-world applications becomes increasingly challenging due to hardware limitations and computational costs. To address this, we design a hybrid edge-cloud solution that leverages the efficiency of smaller models for local processing while deferring to larger, more accurate cloud-based models when necessary. Specifically, we propose a novel unsupervised data generation method, Dual-Model Distillation (DMD), to train a lightweight switcher model that can predict when the edge model's output is uncertain and selectively offload inference to the large model in the cloud. Experimental results on the action classification task show that our framework not only requires less computational overhead, but also improves accuracy compared to using a large model alone. Our framework provides a scalable and adaptable solution for action classification in resource-constrained environments, with potential applications beyond healthcare. Noteworthy, while DMD-generated data is used for optimizing performance and resource usage in our pipeline, we expect the concept of DMD to further support future research on knowledge alignment across multiple models.
Human action recognition has been a topic of interest across multiple fields ranging from security to entertainment systems. Tracking the motion and identifying the action being performed on a real time basis is necessary for critical security systems. In entertainment, especially gaming, the need for immediate responses for actions and gestures are paramount for the success of that system. We show that Motion History image has been a well established framework to capture the temporal and activity information in multi dimensional detail enabling various usecases including classification. We utilize MHI to produce sample data to train a classifier and demonstrate its effectiveness for action classification across six different activities in a single multi-action video. We analyze the classifier performance and identify usecases where MHI struggles to generate the appropriate activity image and discuss mechanisms and future work to overcome those limitations.
Skeleton-based Temporal Action Segmentation involves the dense action classification of variable-length skeleton sequences. Current approaches primarily apply graph-based networks to extract framewise, whole-body-level motion representations, and use one-hot encoded labels for model optimization. However, whole-body motion representations do not capture fine-grained part-level motion representations and the one-hot encoded labels neglect the intrinsic semantic relationships within the language-based action definitions. To address these limitations, we propose a novel method named Language-assisted Human Part Motion Representation Learning (LPL), which contains a Disentangled Part Motion Encoder (DPE) to extract dual-level (i.e., part and whole-body) motion representations and a Language-assisted Distribution Alignment (LDA) strategy for optimizing spatial relations within representations. Specifically, after part-aware skeleton encoding via DPE, LDA generates dual-level action descriptions to construct a textual embedding space with the help of a large-scale language model. Then, LDA motivates the alignment of the embedding space between text descriptions and motions. This alignment allows LDA not only to enhance intra-class compactness but also to transfer the language-encoded semantic correlations among actions to skeleton-based motion learning. Moreover, we propose a simple yet efficient Semantic Offset Adapter to smooth the cross-domain misalignment. Our experiments indicate that LPL achieves state-of-the-art performance across various datasets (e.g., +4.4\% Accuracy, +5.6\% F1 on the PKU-MMD dataset). Moreover, LDA is compatible with existing methods and improves their performance (e.g., +4.8\% Accuracy, +4.3\% F1 on the LARa dataset) without additional inference costs.
In recent years, Wi-Fi sensing has garnered significant attention due to its numerous benefits, such as privacy protection, low cost, and penetration ability. Extensive research has been conducted in this field, focusing on areas such as gesture recognition, people identification, and fall detection. However, many data-driven methods encounter challenges related to domain shift, where the model fails to perform well in environments different from the training data. One major factor contributing to this issue is the limited availability of Wi-Fi sensing datasets, which makes models learn excessive irrelevant information and over-fit to the training set. Unfortunately, collecting large-scale Wi-Fi sensing datasets across diverse scenarios is a challenging task. To address this problem, we propose CrossFi, a siamese network-based approach that excels in both in-domain scenario and cross-domain scenario, including few-shot, zero-shot scenarios, and even works in few-shot new-class scenario where testing set contains new categories. The core component of CrossFi is a sample-similarity calculation network called CSi-Net, which improves the structure of the siamese network by using an attention mechanism to capture similarity information, instead of simply calculating the distance or cosine similarity. Based on it, we develop an extra Weight-Net that can generate a template for each class, so that our CrossFi can work in different scenarios. Experimental results demonstrate that our CrossFi achieves state-of-the-art performance across various scenarios. In gesture recognition task, our CrossFi achieves an accuracy of 98.17% in in-domain scenario, 91.72% in one-shot cross-domain scenario, 64.81% in zero-shot cross-domain scenario, and 84.75% in one-shot new-class scenario. The code for our model is publicly available at https://github.com/RS2002/CrossFi.
Weakly supervised temporal action localization (WTAL) aims to detect action instances in untrimmed videos using only video-level annotations. Since many existing works optimize WTAL models based on action classification labels, they encounter the task discrepancy problem (i.e., localization-by-classification). To tackle this issue, recent studies have attempted to utilize action category names as auxiliary semantic knowledge through vision-language pre-training (VLP). However, there are still areas where existing research falls short. Previous approaches primarily focused on leveraging textual information from language models but overlooked the alignment of dynamic human action and VLP knowledge in a joint space. Furthermore, the deterministic representation employed in previous studies struggles to capture fine-grained human motions. To address these problems, we propose a novel framework that aligns human action knowledge and VLP knowledge in a probabilistic embedding space. Moreover, we propose intra- and inter-distribution contrastive learning to enhance the probabilistic embedding space based on statistical similarities. Extensive experiments and ablation studies reveal that our method significantly outperforms all previous state-of-the-art methods. Code is available at https://github.com/sejong-rcv/PVLR.
Existing multimodal-based human action recognition approaches are either computationally expensive, which limits their applicability in real-time scenarios, or fail to exploit the spatial temporal information of multiple data modalities. In this work, we present an efficient pose-driven attention-guided multimodal network (EPAM-Net) for action recognition in videos. Specifically, we adapted X3D networks for both RGB and pose streams to capture spatio-temporal features from RGB videos and their skeleton sequences. Then skeleton features are utilized to help the visual network stream focusing on key frames and their salient spatial regions using a spatial temporal attention block. Finally, the scores of the two streams of the proposed network are fused for final classification. The experimental results show that our method achieves competitive performance on NTU-D 60 and NTU RGB-D 120 benchmark datasets. Moreover, our model provides a 6.2--9.9x reduction in FLOPs (floating-point operation, in number of multiply-adds) and a 9--9.6x reduction in the number of network parameters. The code will be available at https://github.com/ahmed-nady/Multimodal-Action-Recognition.
Recognizing distractions on the road is crucial to reduce traffic accidents. Video-based networks are typically used, but are limited by their computational cost and are vulnerable to viewpoint changes. In this paper, we propose a novel approach for pose-based driver action classification using speech recognition networks, which is lighter and more viewpoint invariant that video-based one. We leverage the similarity in the encoding of information between audio and pose data, representing poses as key points over time. Our architecture is based on Squeezeformer, an efficient attentionbased speech recognition network. We introduce a selection of data augmentation techniques to enhance generalization. Experiments on the Drive&Act dataset demonstrate superior performance compared to state-of-the-art methods. Additionally, we explore the integration of object information and the impact of viewpoint changes. Our results highlight the effectiveness and robustness of speech recognition networks in pose-based action classification.
Video contrastive learning (v-CL) has gained prominence as a leading framework for unsupervised video representation learning, showcasing impressive performance across various tasks such as action classification and detection. In the field of video representation learning, a feature extractor should ideally capture both static and dynamic semantics. However, our series of experiments reveals that existing v-CL methods predominantly capture static semantics, with limited capturing of dynamic semantics. Through causal analysis, we identify the root cause: the v-CL objective lacks explicit modeling of dynamic features and the measurement of dynamic similarity is confounded by static semantics, while the measurement of static similarity is confounded by dynamic semantics. In response, we propose "Bi-level Optimization of Learning Dynamic with Decoupling and Intervention" (BOLD-DI) to capture both static and dynamic semantics in a decoupled manner. Our method can be seamlessly integrated into the existing v-CL methods and experimental results highlight the significant improvements.
Recognizing human actions in adverse lighting conditions presents significant challenges in computer vision, with wide-ranging applications in visual surveillance and nighttime driving. Existing methods tackle action recognition and dark enhancement separately, limiting the potential for end-to-end learning of spatiotemporal representations for video action classification. This paper introduces Dark Transformer, a novel video transformer-based approach for action recognition in low-light environments. Dark Transformer leverages spatiotemporal self-attention mechanisms in cross-domain settings to enhance cross-domain action recognition. By extending video transformers to learn cross-domain knowledge, Dark Transformer achieves state-of-the-art performance on benchmark action recognition datasets, including InFAR, XD145, and ARID. The proposed approach demonstrates significant promise in addressing the challenges of action recognition in adverse lighting conditions, offering practical implications for real-world applications.
Pre-trained vision-language models (VLMs) have enabled significant progress in open vocabulary computer vision tasks such as image classification, object detection and image segmentation. Some recent works have focused on extending VLMs to open vocabulary single label action classification in videos. However, previous methods fall short in holistic video understanding which requires the ability to simultaneously recognize multiple actions and entities e.g., objects in the video in an open vocabulary setting. We formulate this problem as open vocabulary multilabel video classification and propose a method to adapt a pre-trained VLM such as CLIP to solve this task. We leverage large language models (LLMs) to provide semantic guidance to the VLM about class labels to improve its open vocabulary performance with two key contributions. First, we propose an end-to-end trainable architecture that learns to prompt an LLM to generate soft attributes for the CLIP text-encoder to enable it to recognize novel classes. Second, we integrate a temporal modeling module into CLIP's vision encoder to effectively model the spatio-temporal dynamics of video concepts as well as propose a novel regularized finetuning technique to ensure strong open vocabulary classification performance in the video domain. Our extensive experimentation showcases the efficacy of our approach on multiple benchmark datasets.
We present EgoExo-Fitness, a new full-body action understanding dataset, featuring fitness sequence videos recorded from synchronized egocentric and fixed exocentric (third-person) cameras. Compared with existing full-body action understanding datasets, EgoExo-Fitness not only contains videos from first-person perspectives, but also provides rich annotations. Specifically, two-level temporal boundaries are provided to localize single action videos along with sub-steps of each action. More importantly, EgoExo-Fitness introduces innovative annotations for interpretable action judgement--including technical keypoint verification, natural language comments on action execution, and action quality scores. Combining all of these, EgoExo-Fitness provides new resources to study egocentric and exocentric full-body action understanding across dimensions of "what", "when", and "how well". To facilitate research on egocentric and exocentric full-body action understanding, we construct benchmarks on a suite of tasks (i.e., action classification, action localization, cross-view sequence verification, cross-view skill determination, and a newly proposed task of guidance-based execution verification), together with detailed analysis. Code and data will be available at https://github.com/iSEE-Laboratory/EgoExo-Fitness/tree/main.