In skeleton-based human action recognition, temporal pooling is a critical step for capturing spatiotemporal relationship of joint dynamics. Conventional pooling methods overlook the preservation of motion information and treat each frame equally. However, in an action sequence, only a few segments of frames carry discriminative information related to the action. This paper presents a novel Joint Motion Adaptive Temporal Pooling (JMAP) method for improving skeleton-based action recognition. Two variants of JMAP, frame-wise pooling and joint-wise pooling, are introduced. The efficacy of JMAP has been validated through experiments on the popular NTU RGB+D 120 and PKU-MMD datasets.
Human Action Recognition (HAR) stands as a pivotal research domain in both computer vision and artificial intelligence, with RGB cameras dominating as the preferred tool for investigation and innovation in this field. However, in real-world applications, RGB cameras encounter numerous challenges, including light conditions, fast motion, and privacy concerns. Consequently, bio-inspired event cameras have garnered increasing attention due to their advantages of low energy consumption, high dynamic range, etc. Nevertheless, most existing event-based HAR datasets are low resolution ($346 \times 260$). In this paper, we propose a large-scale, high-definition ($1280 \times 800$) human action recognition dataset based on the CeleX-V event camera, termed CeleX-HAR. It encompasses 150 commonly occurring action categories, comprising a total of 124,625 video sequences. Various factors such as multi-view, illumination, action speed, and occlusion are considered when recording these data. To build a more comprehensive benchmark dataset, we report over 20 mainstream HAR models for future works to compare. In addition, we also propose a novel Mamba vision backbone network for event stream based HAR, termed EVMamba, which equips the spatial plane multi-directional scanning and novel voxel temporal scanning mechanism. By encoding and mining the spatio-temporal information of event streams, our EVMamba has achieved favorable results across multiple datasets. Both the dataset and source code will be released on \url{https://github.com/Event-AHU/CeleX-HAR}
In recent years, video action recognition, as a fundamental task in the field of video understanding, has been deeply explored by numerous researchers.Most traditional video action recognition methods typically involve converting videos into three-dimensional data that encapsulates both spatial and temporal information, subsequently leveraging prevalent image understanding models to model and analyze these data. However,these methods have significant drawbacks. Firstly, when delving into video action recognition tasks, image understanding models often need to be adapted accordingly in terms of model architecture and preprocessing for these spatiotemporal tasks; Secondly, dealing with high-dimensional data often poses greater challenges and incurs higher time costs compared to its lower-dimensional counterparts.To bridge the gap between image-understanding and video-understanding tasks while simplifying the complexity of video comprehension, we introduce a novel video representation architecture, Flatten, which serves as a plug-and-play module that can be seamlessly integrated into any image-understanding network for efficient and effective 3D temporal data modeling.Specifically, by applying specific flattening operations (e.g., row-major transform), 3D spatiotemporal data is transformed into 2D spatial information, and then ordinary image understanding models are used to capture temporal dynamic and spatial semantic information, which in turn accomplishes effective and efficient video action recognition. Extensive experiments on commonly used datasets (Kinetics-400, Something-Something v2, and HMDB-51) and three classical image classification models (Uniformer, SwinV2, and ResNet), have demonstrated that embedding Flatten provides a significant performance improvements over original model.
Online video understanding often relies on individual frames, leading to frame-by-frame predictions. Recent advancements such as Online Temporal Action Localization (OnTAL), extend this approach to instance-level predictions. However, existing methods mainly focus on short-term context, neglecting historical information. To address this, we introduce the History-Augmented Anchor Transformer (HAT) Framework for OnTAL. By integrating historical context, our framework enhances the synergy between long-term and short-term information, improving the quality of anchor features crucial for classification and localization. We evaluate our model on both procedural egocentric (PREGO) datasets (EGTEA and EPIC) and standard non-PREGO OnTAL datasets (THUMOS and MUSES). Results show that our model outperforms state-of-the-art approaches significantly on PREGO datasets and achieves comparable or slightly superior performance on non-PREGO datasets, underscoring the importance of leveraging long-term history, especially in procedural and egocentric action scenarios. Code is available at: https://github.com/sakibreza/ECCV24-HAT/
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.
Online temporal action localization (On-TAL) is the task of identifying multiple action instances given a streaming video. Since existing methods take as input only a video segment of fixed size per iteration, they are limited in considering long-term context and require tuning the segment size carefully. To overcome these limitations, we propose memory-augmented transformer (MATR). MATR utilizes the memory queue that selectively preserves the past segment features, allowing to leverage long-term context for inference. We also propose a novel action localization method that observes the current input segment to predict the end time of the ongoing action and accesses the memory queue to estimate the start time of the action. Our method outperformed existing methods on two datasets, THUMOS14 and MUSES, surpassing not only TAL methods in the online setting but also some offline TAL methods.
This paper proposes a hybrid fusion-based deep learning approach based on two different modalities, audio and video, to improve human activity recognition and violence detection in public places. To take advantage of audiovisual fusion, late fusion, intermediate fusion, and hybrid fusion-based deep learning (HFBDL) are used and compared. Since the objective is to detect and recognize human violence in public places, Real-life violence situation (RLVS) dataset is expanded and used. Simulating results of HFBDL show 96.67\% accuracy on validation data, which is more accurate than the other state-of-the-art methods on this dataset. To showcase our model's ability in real-world scenarios, another dataset of 54 sounded videos of both violent and non-violent situations was recorded. The model could successfully detect 52 out of 54 videos correctly. The proposed method shows a promising performance on real scenarios. Thus, it can be used for human action recognition and violence detection in public places for security purposes.
In order to unlock the potential of diverse sensors, we investigate a method to transfer knowledge between time-series modalities using a multimodal \textit{temporal} representation space for Human Activity Recognition (HAR). Specifically, we explore the setting where the modality used in testing has no labeled data during training, which we refer to as Unsupervised Modality Adaptation (UMA). We categorize existing UMA approaches as Student-Teacher or Contrastive Alignment methods. These methods typically compress continuous-time data samples into single latent vectors during alignment, inhibiting their ability to transfer temporal information through real-world temporal distortions. To address this, we introduce Cross-modal Transfer Through Time (C3T), which preserves temporal information during alignment to handle dynamic sensor data better. C3T achieves this by aligning a set of temporal latent vectors across sensing modalities. Our extensive experiments on various camera+IMU datasets demonstrate that C3T outperforms existing methods in UMA by at least 8% in accuracy and shows superior robustness to temporal distortions such as time-shift, misalignment, and dilation. Our findings suggest that C3T has significant potential for developing generalizable models for time-series sensor data, opening new avenues for various multimodal applications.
The complexity of state-of-the-art Transformer-based models for skeleton-based action recognition poses significant challenges in terms of computational efficiency and resource utilization. In this paper, we explore the application of Singular Value Decomposition (SVD) to effectively reduce the model sizes of these pre-trained models, aiming to minimize their resource consumption while preserving accuracy. Our method, LORTSAR (LOw-Rank Transformer for Skeleton-based Action Recognition), also includes a fine-tuning step to compensate for any potential accuracy degradation caused by model compression, and is applied to two leading Transformer-based models, "Hyperformer" and "STEP-CATFormer". Experimental results on the "NTU RGB+D" and "NTU RGB+D 120" datasets show that our method can reduce the number of model parameters substantially with negligible degradation or even performance increase in recognition accuracy. This confirms that SVD combined with post-compression fine-tuning can boost model efficiency, paving the way for more sustainable, lightweight, and high-performance technologies in human action recognition.
In sewer pipe Closed-Circuit Television (CCTV) inspection, accurate temporal defect localization is essential for effective defect classification, detection, segmentation and quantification. Industry standards typically do not require time-interval annotations, even though they are more informative than time-point annotations for defect localization, resulting in additional annotation costs when fully supervised methods are used. Additionally, differences in scene types and camera motion patterns between pipe inspections and Temporal Action Localization (TAL) hinder the effective transfer of point-supervised TAL methods. Therefore, this study introduces a Semi-supervised multi-Prototype-based method incorporating visual Odometry for enhanced attention guidance (PipeSPO). PipeSPO fully leverages unlabeled data through unsupervised pretext tasks and utilizes time-point annotated data with a weakly supervised multi-prototype-based method, relying on visual odometry features to capture camera pose information. Experiments on real-world datasets demonstrate that PipeSPO achieves 41.89% average precision across Intersection over Union (IoU) thresholds of 0.1-0.7, improving by 8.14% over current state-of-the-art methods.
Online Temporal Action Localization (On-TAL) is a critical task that aims to instantaneously identify action instances in untrimmed streaming videos as soon as an action concludes -- a major leap from frame-based Online Action Detection (OAD). Yet, the challenge of detecting overlapping actions is often overlooked even though it is a common scenario in streaming videos. Current methods that can address concurrent actions depend heavily on class information, limiting their flexibility. This paper introduces ActionSwitch, the first class-agnostic On-TAL framework capable of detecting overlapping actions. By obviating the reliance on class information, ActionSwitch provides wider applicability to various situations, including overlapping actions of the same class or scenarios where class information is unavailable. This approach is complemented by the proposed "conservativeness loss", which directly embeds a conservative decision-making principle into the loss function for On-TAL. Our ActionSwitch achieves state-of-the-art performance in complex datasets, including Epic-Kitchens 100 targeting the challenging egocentric view and FineAction consisting of fine-grained actions.
Temporal Action Localization (TAL) is a critical task in video analysis, identifying precise start and end times of actions. Existing methods like CNNs, RNNs, GCNs, and Transformers have limitations in capturing long-range dependencies and temporal causality. To address these challenges, we propose a novel TAL architecture leveraging the Selective State Space Model (S6). Our approach integrates the Feature Aggregated Bi-S6 block, Dual Bi-S6 structure, and a recurrent mechanism to enhance temporal and channel-wise dependency modeling without increasing parameter complexity. Extensive experiments on benchmark datasets demonstrate state-of-the-art results with mAP scores of 74.2% on THUMOS-14, 42.9% on ActivityNet, 29.6% on FineAction, and 45.8% on HACS. Ablation studies validate our method's effectiveness, showing that the Dual structure in the Stem module and the recurrent mechanism outperform traditional approaches. Our findings demonstrate the potential of S6-based models in TAL tasks, paving the way for future research.
Recent studies have revealed the vulnerability of deep neural networks (DNNs) to various backdoor attacks, where the behavior of DNNs can be compromised by utilizing certain types of triggers or poisoning mechanisms. State-of-the-art (SOTA) defenses employ too-sophisticated mechanisms that require either a computationally expensive adversarial search module for reverse-engineering the trigger distribution or an over-sensitive hyper-parameter selection module. Moreover, they offer sub-par performance in challenging scenarios, e.g., limited validation data and strong attacks. In this paper, we propose Neural mask Fine-Tuning (NFT) with an aim to optimally re-organize the neuron activities in a way that the effect of the backdoor is removed. Utilizing a simple data augmentation like MixUp, NFT relaxes the trigger synthesis process and eliminates the requirement of the adversarial search module. Our study further reveals that direct weight fine-tuning under limited validation data results in poor post-purification clean test accuracy, primarily due to overfitting issue. To overcome this, we propose to fine-tune neural masks instead of model weights. In addition, a mask regularizer has been devised to further mitigate the model drift during the purification process. The distinct characteristics of NFT render it highly efficient in both runtime and sample usage, as it can remove the backdoor even when a single sample is available from each class. We validate the effectiveness of NFT through extensive experiments covering the tasks of image classification, object detection, video action recognition, 3D point cloud, and natural language processing. We evaluate our method against 14 different attacks (LIRA, WaNet, etc.) on 11 benchmark data sets such as ImageNet, UCF101, Pascal VOC, ModelNet, OpenSubtitles2012, etc.
Weakly-supervised Temporal Action Localization (WSTAL) aims to localize actions in untrimmed videos using only video-level supervision. Latest WSTAL methods introduce pseudo label learning framework to bridge the gap between classification-based training and inferencing targets at localization, and achieve cutting-edge results. In these frameworks, a classification-based model is used to generate pseudo labels for a regression-based student model to learn from. However, the quality of pseudo labels in the framework, which is a key factor to the final result, is not carefully studied. In this paper, we propose a set of simple yet efficient pseudo label quality enhancement mechanisms to build our FuSTAL framework. FuSTAL enhances pseudo label quality at three stages: cross-video contrastive learning at proposal Generation-Stage, prior-based filtering at proposal Selection-Stage and EMA-based distillation at Training-Stage. These designs enhance pseudo label quality at different stages in the framework, and help produce more informative, less false and smoother action proposals. With the help of these comprehensive designs at all stages, FuSTAL achieves an average mAP of 50.8% on THUMOS'14, outperforming the previous best method by 1.2%, and becomes the first method to reach the milestone of 50%.
Human Action Recognition (HAR) encompasses the task of monitoring human activities across various domains, including but not limited to medical, educational, entertainment, visual surveillance, video retrieval, and the identification of anomalous activities. Over the past decade, the field of HAR has witnessed substantial progress by leveraging Convolutional Neural Networks (CNNs) to effectively extract and comprehend intricate information, thereby enhancing the overall performance of HAR systems. Recently, the domain of computer vision has witnessed the emergence of Vision Transformers (ViTs) as a potent solution. The efficacy of transformer architecture has been validated beyond the confines of image analysis, extending their applicability to diverse video-related tasks. Notably, within this landscape, the research community has shown keen interest in HAR, acknowledging its manifold utility and widespread adoption across various domains. This article aims to present an encompassing survey that focuses on CNNs and the evolution of Recurrent Neural Networks (RNNs) to ViTs given their importance in the domain of HAR. By conducting a thorough examination of existing literature and exploring emerging trends, this study undertakes a critical analysis and synthesis of the accumulated knowledge in this field. Additionally, it investigates the ongoing efforts to develop hybrid approaches. Following this direction, this article presents a novel hybrid model that seeks to integrate the inherent strengths of CNNs and ViTs.
Alleviating noisy pseudo labels remains a key challenge in Semi-Supervised Temporal Action Localization (SS-TAL). Existing methods often filter pseudo labels based on strict conditions, but they typically assess classification and localization quality separately, leading to suboptimal pseudo-label ranking and selection. In particular, there might be inaccurate pseudo labels within selected positives, alongside reliable counterparts erroneously assigned to negatives. To tackle these problems, we propose a novel Adaptive Pseudo-label Learning (APL) framework to facilitate better pseudo-label selection. Specifically, to improve the ranking quality, Adaptive Label Quality Assessment (ALQA) is proposed to jointly learn classification confidence and localization reliability, followed by dynamically selecting pseudo labels based on the joint score. Additionally, we propose an Instance-level Consistency Discriminator (ICD) for eliminating ambiguous positives and mining potential positives simultaneously based on inter-instance intrinsic consistency, thereby leading to a more precise selection. We further introduce a general unsupervised Action-aware Contrastive Pre-training (ACP) to enhance the discrimination both within actions and between actions and backgrounds, which benefits SS-TAL. Extensive experiments on THUMOS14 and ActivityNet v1.3 demonstrate that our method achieves state-of-the-art performance under various semi-supervised settings.
Understanding the content of events occurring in the video and their inherent temporal logic is crucial for video-text retrieval. However, web-crawled pre-training datasets often lack sufficient event information, and the widely adopted video-level cross-modal contrastive learning also struggles to capture detailed and complex video-text event alignment. To address these challenges, we make improvements from both data and model perspectives. In terms of pre-training data, we focus on supplementing the missing specific event content and event temporal transitions with the proposed event augmentation strategies. Based on the event-augmented data, we construct a novel Event-Aware Video-Text Retrieval model, ie, EA-VTR, which achieves powerful video-text retrieval ability through superior video event awareness. EA-VTR can efficiently encode frame-level and video-level visual representations simultaneously, enabling detailed event content and complex event temporal cross-modal alignment, ultimately enhancing the comprehensive understanding of video events. Our method not only significantly outperforms existing approaches on multiple datasets for Text-to-Video Retrieval and Video Action Recognition tasks, but also demonstrates superior event content perceive ability on Multi-event Video-Text Retrieval and Video Moment Retrieval tasks, as well as outstanding event temporal logic understanding ability on Test of Time task.
The vocabulary size in temporal action localization (TAL) is limited by the scarcity of large-scale annotated datasets. To overcome this, recent works integrate vision-language models (VLMs), such as CLIP, for open-vocabulary TAL (OV-TAL). However, despite the success of VLMs trained on extensive datasets, existing OV-TAL methods still rely on human-labeled TAL datasets of limited size to train action localizers, limiting their generalizability. In this paper, we explore the scalability of self-training with unlabeled YouTube videos for OV-TAL. Our approach consists of two stages: (1) a class-agnostic action localizer is trained on a human-labeled TAL dataset to generate pseudo-labels for unlabeled videos, and (2) the large-scale pseudo-labeled dataset is then used to train the localizer. Extensive experiments demonstrate that leveraging web-scale videos in self-training significantly enhances the generalizability of an action localizer. Additionally, we identify limitations in existing OV-TAL evaluation schemes and propose a new benchmark for thorough assessment. Finally, we showcase the TAL performance of the large multimodal model Gemini-1.5 on our new benchmark. Code is released at https://github.com/HYUNJS/STOV-TAL.
Pre-trained vision-language models (VLMs) have shown impressive results in various visual classification tasks. However, we often fail to fully unleash their potential when adapting them for new concept understanding due to limited information on new classes. To address this limitation, we introduce a novel adaptation framework, AWT (Augment, Weight, then Transport). AWT comprises three key components: augmenting inputs with diverse visual perspectives and enriched class descriptions through image transformations and language models; dynamically weighting inputs based on the prediction entropy; and employing optimal transport to mine semantic correlations in the vision-language space. AWT can be seamlessly integrated into various VLMs, enhancing their zero-shot capabilities without additional training and facilitating few-shot learning through an integrated multimodal adapter module. We verify AWT in multiple challenging scenarios, including zero-shot and few-shot image classification, zero-shot video action recognition, and out-of-distribution generalization. AWT consistently outperforms the state-of-the-art methods in each setting. In addition, our extensive studies further demonstrate AWT's effectiveness and adaptability across different VLMs, architectures, and scales.