Multimodal human action recognition based on RGB and skeleton data fusion, while effective, is constrained by significant limitations such as high computational complexity, excessive memory consumption, and substantial energy demands, particularly when implemented with Artificial Neural Networks (ANN). These limitations restrict its applicability in resource-constrained scenarios. To address these challenges, we propose a novel Spiking Neural Network (SNN)-driven framework for multimodal human action recognition, utilizing event camera and skeleton data. Our framework is centered on two key innovations: (1) a novel multimodal SNN architecture that employs distinct backbone networks for each modality-an SNN-based Mamba for event camera data and a Spiking Graph Convolutional Network (SGN) for skeleton data-combined with a spiking semantic extraction module to capture deep semantic representations; and (2) a pioneering SNN-based discretized information bottleneck mechanism for modality fusion, which effectively balances the preservation of modality-specific semantics with efficient information compression. To validate our approach, we propose a novel method for constructing a multimodal dataset that integrates event camera and skeleton data, enabling comprehensive evaluation. Extensive experiments demonstrate that our method achieves superior performance in both recognition accuracy and energy efficiency, offering a promising solution for practical applications.
This paper introduces ViNet-S, a 36MB model based on the ViNet architecture with a U-Net design, featuring a lightweight decoder that significantly reduces model size and parameters without compromising performance. Additionally, ViNet-A (148MB) incorporates spatio-temporal action localization (STAL) features, differing from traditional video saliency models that use action classification backbones. Our studies show that an ensemble of ViNet-S and ViNet-A, by averaging predicted saliency maps, achieves state-of-the-art performance on three visual-only and six audio-visual saliency datasets, outperforming transformer-based models in both parameter efficiency and real-time performance, with ViNet-S reaching over 1000fps.
Human Action Recognition (HAR) plays a crucial role in applications such as health monitoring, smart home automation, and human-computer interaction. While HAR has been extensively studied, action summarization, which involves identifying and summarizing continuous actions, remains an emerging task. This paper introduces the novel XRF V2 dataset, designed for indoor daily activity Temporal Action Localization (TAL) and action summarization. XRF V2 integrates multimodal data from Wi-Fi signals, IMU sensors (smartphones, smartwatches, headphones, and smart glasses), and synchronized video recordings, offering a diverse collection of indoor activities from 16 volunteers across three distinct environments. To tackle TAL and action summarization, we propose the XRFMamba neural network, which excels at capturing long-term dependencies in untrimmed sensory sequences and outperforms state-of-the-art methods, such as ActionFormer and WiFiTAD. We envision XRF V2 as a valuable resource for advancing research in human action localization, action forecasting, pose estimation, multimodal foundation models pre-training, synthetic data generation, and more.
Human Action Recognition (HAR) is a challenging domain in computer vision, involving recognizing complex patterns by analyzing the spatiotemporal dynamics of individuals' movements in videos. These patterns arise in sequential data, such as video frames, which are often essential to accurately distinguish actions that would be ambiguous in a single image. HAR has garnered considerable interest due to its broad applicability, ranging from robotics and surveillance systems to sports motion analysis, healthcare, and the burgeoning field of autonomous vehicles. While several taxonomies have been proposed to categorize HAR approaches in surveys, they often overlook hybrid methodologies and fail to demonstrate how different models incorporate various architectures and modalities. In this comprehensive survey, we present the novel SMART-Vision taxonomy, which illustrates how innovations in deep learning for HAR complement one another, leading to hybrid approaches beyond traditional categories. Our survey provides a clear roadmap from foundational HAR works to current state-of-the-art systems, highlighting emerging research directions and addressing unresolved challenges in discussion sections for architectures within the HAR domain. We provide details of the research datasets that various approaches used to measure and compare goodness HAR approaches. We also explore the rapidly emerging field of Open-HAR systems, which challenges HAR systems by presenting samples from unknown, novel classes during test time.
Pseudo-label learning methods have been widely applied in weakly-supervised temporal action localization. Existing works directly utilize weakly-supervised base model to generate instance-level pseudo-labels for training the fully-supervised detection head. We argue that the noise in pseudo-labels would interfere with the learning of fully-supervised detection head, leading to significant performance leakage. Issues with noisy labels include:(1) inaccurate boundary localization; (2) undetected short action clips; (3) multiple adjacent segments incorrectly detected as one segment. To target these issues, we introduce a two-stage noisy label learning strategy to harness every potential useful signal in noisy labels. First, we propose a frame-level pseudo-label generation model with a context-aware denoising algorithm to refine the boundaries. Second, we introduce an online-revised teacher-student framework with a missing instance compensation module and an ambiguous instance correction module to solve the short-action-missing and many-to-one problems. Besides, we apply a high-quality pseudo-label mining loss in our online-revised teacher-student framework to add different weights to the noisy labels to train more effectively. Our model outperforms the previous state-of-the-art method in detection accuracy and inference speed greatly upon the THUMOS14 and ActivityNet v1.2 benchmarks.
The current biodiversity loss crisis makes animal monitoring a relevant field of study. In light of this, data collected through monitoring can provide essential insights, and information for decision-making aimed at preserving global biodiversity. Despite the importance of such data, there is a notable scarcity of datasets featuring videos of birds, and none of the existing datasets offer detailed annotations of bird behaviors in video format. In response to this gap, our study introduces the first fine-grained video dataset specifically designed for bird behavior detection and species classification. This dataset addresses the need for comprehensive bird video datasets and provides detailed data on bird actions, facilitating the development of deep learning models to recognize these, similar to the advancements made in human action recognition. The proposed dataset comprises 178 videos recorded in Spanish wetlands, capturing 13 different bird species performing 7 distinct behavior classes. In addition, we also present baseline results using state of the art models on two tasks: bird behavior recognition and species classification.
Most existing traffic video datasets including Waymo are structured, focusing predominantly on Western traffic, which hinders global applicability. Specifically, most Asian scenarios are far more complex, involving numerous objects with distinct motions and behaviors. Addressing this gap, we present a new dataset, DAVE, designed for evaluating perception methods with high representation of Vulnerable Road Users (VRUs: e.g. pedestrians, animals, motorbikes, and bicycles) in complex and unpredictable environments. DAVE is a manually annotated dataset encompassing 16 diverse actor categories (spanning animals, humans, vehicles, etc.) and 16 action types (complex and rare cases like cut-ins, zigzag movement, U-turn, etc.), which require high reasoning ability. DAVE densely annotates over 13 million bounding boxes (bboxes) actors with identification, and more than 1.6 million boxes are annotated with both actor identification and action/behavior details. The videos within DAVE are collected based on a broad spectrum of factors, such as weather conditions, the time of day, road scenarios, and traffic density. DAVE can benchmark video tasks like Tracking, Detection, Spatiotemporal Action Localization, Language-Visual Moment retrieval, and Multi-label Video Action Recognition. Given the critical importance of accurately identifying VRUs to prevent accidents and ensure road safety, in DAVE, vulnerable road users constitute 41.13% of instances, compared to 23.71% in Waymo. DAVE provides an invaluable resource for the development of more sensitive and accurate visual perception algorithms in the complex real world. Our experiments show that existing methods suffer degradation in performance when evaluated on DAVE, highlighting its benefit for future video recognition research.
Weakly supervised temporal action localization (WS-TAL) is a task of targeting at localizing complete action instances and categorizing them with video-level labels. Action-background ambiguity, primarily caused by background noise resulting from aggregation and intra-action variation, is a significant challenge for existing WS-TAL methods. In this paper, we introduce a hybrid multi-head attention (HMHA) module and generalized uncertainty-based evidential fusion (GUEF) module to address the problem. The proposed HMHA effectively enhances RGB and optical flow features by filtering redundant information and adjusting their feature distribution to better align with the WS-TAL task. Additionally, the proposed GUEF adaptively eliminates the interference of background noise by fusing snippet-level evidences to refine uncertainty measurement and select superior foreground feature information, which enables the model to concentrate on integral action instances to achieve better action localization and classification performance. Experimental results conducted on the THUMOS14 dataset demonstrate that our method outperforms state-of-the-art methods. Our code is available in \url{https://github.com/heyuanpengpku/GUEF/tree/main}.
It is significantly challenging to recognize daily human actions in homes due to the diversity and dynamic changes in unconstrained home environments. It spurs the need to continually adapt to various users and scenes. Fine-tuning current video understanding models on newly encountered domains often leads to catastrophic forgetting, where the models lose their ability to perform well on previously learned scenarios. To address this issue, we formalize the problem of Video Domain Incremental Learning (VDIL), which enables models to learn continually from different domains while maintaining a fixed set of action classes. Existing continual learning research primarily focuses on class-incremental learning, while the domain incremental learning has been largely overlooked in video understanding. In this work, we introduce a novel benchmark of domain incremental human action recognition for unconstrained home environments. We design three domain split types (user, scene, hybrid) to systematically assess the challenges posed by domain shifts in real-world home settings. Furthermore, we propose a baseline learning strategy based on replay and reservoir sampling techniques without domain labels to handle scenarios with limited memory and task agnosticism. Extensive experimental results demonstrate that our simple sampling and replay strategy outperforms most existing continual learning methods across the three proposed benchmarks.
Visual-based human action recognition can be found in various application fields, e.g., surveillance systems, sports analytics, medical assistive technologies, or human-robot interaction frameworks, and it concerns the identification and classification of individuals' activities within a video. Since actions typically occur over a sequence of consecutive images, it is particularly challenging due to the inclusion of temporal analysis, which introduces an extra layer of complexity. However, although multiple approaches try to handle temporal analysis, there are still difficulties because of their computational cost and lack of adaptability. Therefore, different types of vision data, containing transition information between consecutive images, provided by next-generation hardware sensors will guide the robotics community in tackling the problem of human action recognition. On the other hand, while there is a plethora of still-image datasets, that researchers can adopt to train new artificial intelligence models, videos representing human activities are of limited capabilities, e.g., small and unbalanced datasets or selected without control from multiple sources. To this end, generating new and realistic synthetic videos is possible since labeling is performed throughout the data creation process, while reinforcement learning techniques can permit the avoidance of considerable dataset dependence. At the same time, human factors' involvement raises ethical issues for the research community, as doubts and concerns about new technologies already exist.
Temporal action localization (TAL) involves dual tasks to classify and localize actions within untrimmed videos. However, the two tasks often have conflicting requirements for features. Existing methods typically employ separate heads for classification and localization tasks but share the same input feature, leading to suboptimal performance. To address this issue, we propose a novel TAL method with Cross Layer Task Decoupling and Refinement (CLTDR). Based on the feature pyramid of video, CLTDR strategy integrates semantically strong features from higher pyramid layers and detailed boundary-aware boundary features from lower pyramid layers to effectively disentangle the action classification and localization tasks. Moreover, the multiple features from cross layers are also employed to refine and align the disentangled classification and regression results. At last, a lightweight Gated Multi-Granularity (GMG) module is proposed to comprehensively extract and aggregate video features at instant, local, and global temporal granularities. Benefiting from the CLTDR and GMG modules, our method achieves state-of-the-art performance on five challenging benchmarks: THUMOS14, MultiTHUMOS, EPIC-KITCHENS-100, ActivityNet-1.3, and HACS. Our code and pre-trained models are publicly available at: https://github.com/LiQiang0307/CLTDR-GMG.
We introduce a novel state-space model (SSM)-based framework for skeleton-based human action recognition, with an anatomically-guided architecture that improves state-of-the-art performance in both clinical diagnostics and general action recognition tasks. Our approach decomposes skeletal motion analysis into spatial, temporal, and spatio-temporal streams, using channel partitioning to capture distinct movement characteristics efficiently. By implementing a structured, multi-directional scanning strategy within SSMs, our model captures local joint interactions and global motion patterns across multiple anatomical body parts. This anatomically-aware decomposition enhances the ability to identify subtle motion patterns critical in medical diagnosis, such as gait anomalies associated with neurological conditions. On public action recognition benchmarks, i.e., NTU RGB+D, NTU RGB+D 120, and NW-UCLA, our model outperforms current state-of-the-art methods, achieving accuracy improvements up to $3.2\%$ with lower computational complexity than previous leading transformer-based models. We also introduce a novel medical dataset for motion-based patient neurological disorder analysis to validate our method's potential in automated disease diagnosis.
With the rapid advancements in deep learning, computer vision tasks have seen significant improvements, making two-stream neural networks a popular focus for video based action recognition. Traditional models using RGB and optical flow streams achieve strong performance but at a high computational cost. To address this, we introduce a representation flow algorithm to replace the optical flow branch in the egocentric action recognition model, enabling end-to-end training while reducing computational cost and prediction time. Our model, designed for egocentric action recognition, uses class activation maps (CAMs) to improve accuracy and ConvLSTM for spatio temporal encoding with spatial attention. When evaluated on the GTEA61, EGTEA GAZE+, and HMDB datasets, our model matches the accuracy of the original model on GTEA61 and exceeds it by 0.65% and 0.84% on EGTEA GAZE+ and HMDB, respectively. Prediction runtimes are significantly reduced to 0.1881s, 0.1503s, and 0.1459s, compared to the original model's 101.6795s, 25.3799s, and 203.9958s. Ablation studies were also conducted to study the impact of different parameters on model performance. Keywords: two-stream, egocentric, action recognition, CAM, representation flow, CAM, ConvLSTM
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.
Video action recognition has made significant strides, but challenges remain in effectively using both spatial and temporal information. While existing methods often focus on either spatial features (e.g., object appearance) or temporal dynamics (e.g., motion), they rarely address the need for a comprehensive integration of both. Capturing the rich temporal evolution of video frames, while preserving their spatial details, is crucial for improving accuracy. In this paper, we introduce the Temporal Integration and Motion Enhancement (TIME) layer, a novel preprocessing technique designed to incorporate temporal information. The TIME layer generates new video frames by rearranging the original sequence, preserving temporal order while embedding $N^2$ temporally evolving frames into a single spatial grid of size $N \times N$. This transformation creates new frames that balance both spatial and temporal information, making them compatible with existing video models. When $N=1$, the layer captures rich spatial details, similar to existing methods. As $N$ increases ($N\geq2$), temporal information becomes more prominent, while the spatial information decreases to ensure compatibility with model inputs. We demonstrate the effectiveness of the TIME layer by integrating it into popular action recognition models, such as ResNet-50, Vision Transformer, and Video Masked Autoencoders, for both RGB and depth video data. Our experiments show that the TIME layer enhances recognition accuracy, offering valuable insights for video processing tasks.
The shared topology of human skeletons motivated the recent investigation of graph convolutional network (GCN) solutions for action recognition. However, the existing GCNs rely on the binary connection of two neighbouring vertices (joints) formed by an edge (bone), overlooking the potential of constructing multi-vertex convolution structures. In this paper we address this oversight and explore the merits of a hyper-graph convolutional network (Hyper-GCN) to achieve the aggregation of rich semantic information conveyed by skeleton vertices. In particular, our Hyper-GCN adaptively optimises multi-scale hyper-graphs during training, revealing the action-driven multi-vertex relations. Besides, virtual connections are often designed to support efficient feature aggregation, implicitly extending the spectrum of dependencies within the skeleton. By injecting virtual connections into hyper-graphs, the semantic clues of diverse action categories can be highlighted. The results of experiments conducted on the NTU-60, NTU-120, and NW-UCLA datasets, demonstrate the merits of our Hyper-GCN, compared to the state-of-the-art methods. Specifically, we outperform the existing solutions on NTU-120, achieving 90.2\% and 91.4\% in terms of the top-1 recognition accuracy on X-Sub and X-Set.
Pre-trained vision-language models provide a robust foundation for efficient transfer learning across various downstream tasks. In the field of video action recognition, mainstream approaches often introduce additional parameter modules to capture temporal information. While the increased model capacity brought by these additional parameters helps better fit the video-specific inductive biases, existing methods require learning a large number of parameters and are prone to catastrophic forgetting of the original generalizable knowledge. In this paper, we propose a simple yet effective Multi-modal Spatio-Temporal Adapter (MSTA) to improve the alignment between representations in the text and vision branches, achieving a balance between general knowledge and task-specific knowledge. Furthermore, to mitigate over-fitting and enhance generalizability, we introduce a spatio-temporal description-guided consistency constraint. This constraint involves feeding template inputs (i.e., ``a video of $\{\textbf{cls}\}$'') into the trainable language branch, while LLM-generated spatio-temporal descriptions are input into the pre-trained language branch, enforcing consistency between the outputs of the two branches. This mechanism prevents over-fitting to downstream tasks and improves the distinguishability of the trainable branch within the spatio-temporal semantic space. We evaluate the effectiveness of our approach across four tasks: zero-shot transfer, few-shot learning, base-to-novel generalization, and fully-supervised learning. Compared to many state-of-the-art methods, our MSTA achieves outstanding performance across all evaluations, while using only 2-7\% of the trainable parameters in the original model. Code will be avaliable at https://github.com/chenhaoxing/ETL4Video.
Recent breakthroughs in Multimodal Large Language Models (MLLMs) have gained significant recognition within the deep learning community, where the fusion of the Video Foundation Models (VFMs) and Large Language Models(LLMs) has proven instrumental in constructing robust video understanding systems, effectively surmounting constraints associated with predefined visual tasks. These sophisticated MLLMs exhibit remarkable proficiency in comprehending videos, swiftly attaining unprecedented performance levels across diverse benchmarks. However, their operation demands substantial memory and computational resources, underscoring the continued importance of traditional models in video comprehension tasks. In this paper, we introduce a novel learning paradigm termed MLLM4WTAL. This paradigm harnesses the potential of MLLM to offer temporal action key semantics and complete semantic priors for conventional Weakly-supervised Temporal Action Localization (WTAL) methods. MLLM4WTAL facilitates the enhancement of WTAL by leveraging MLLM guidance. It achieves this by integrating two distinct modules: Key Semantic Matching (KSM) and Complete Semantic Reconstruction (CSR). These modules work in tandem to effectively address prevalent issues like incomplete and over-complete outcomes common in WTAL methods. Rigorous experiments are conducted to validate the efficacy of our proposed approach in augmenting the performance of various heterogeneous WTAL models.
Graph convolutional networks (GCNs) are an effective skeleton-based human action recognition (HAR) technique. GCNs enable the specification of CNNs to a non-Euclidean frame that is more flexible. The previous GCN-based models still have a lot of issues: (I) The graph structure is the same for all model layers and input data.
Human Action Recognition (HAR) is an interesting research area in human-computer interaction used to monitor the activities of elderly and disabled individuals affected by physical and mental health. In the recent era, skeleton-based HAR has received much attention because skeleton data has shown that it can handle changes in striking, body size, camera views, and complex backgrounds. One key characteristic of ST-GCN is automatically learning spatial and temporal patterns from skeleton sequences. It has some limitations, as this method only works for short-range correlation due to its limited receptive field. Consequently, understanding human action requires long-range interconnection. To address this issue, we developed a spatial-temporal relative transformer ST-RTR model. The ST-RTR includes joint and relay nodes, which allow efficient communication and data transmission within the network. These nodes help to break the inherent spatial and temporal skeleton topologies, which enables the model to understand long-range human action better. Furthermore, we combine ST-RTR with a fusion model for further performance improvements. To assess the performance of the ST-RTR method, we conducted experiments on three skeleton-based HAR benchmarks: NTU RGB+D 60, NTU RGB+D 120, and UAV-Human. It boosted CS and CV by 2.11 % and 1.45% on NTU RGB+D 60, 1.25% and 1.05% on NTU RGB+D 120. On UAV-Human datasets, accuracy improved by 2.54%. The experimental outcomes explain that the proposed ST-RTR model significantly improves action recognition associated with the standard ST-GCN method.