Skeleton-based Human Action Recognition (HAR) is a vital technology in robotics and human-robot interaction. However, most existing methods concentrate primarily on full-body movements and often overlook subtle hand motions that are critical for distinguishing fine-grained actions. Recent work leverages a unified graph representation that combines body, hand, and foot keypoints to capture detailed body dynamics. Yet, these models often blur fine hand details due to the disparity between body and hand action characteristics and the loss of subtle features during the spatial-pooling. In this paper, we propose BHaRNet (Body-Hand action Recognition Network), a novel framework that augments a typical body-expert model with a hand-expert model. Our model jointly trains both streams with an ensemble loss that fosters cooperative specialization, functioning in a manner reminiscent of a Mixture-of-Experts (MoE). Moreover, cross-attention is employed via an expertized branch method and a pooling-attention module to enable feature-level interactions and selectively fuse complementary information. Inspired by MMNet, we also demonstrate the applicability of our approach to multi-modal tasks by leveraging RGB information, where body features guide RGB learning to capture richer contextual cues. Experiments on large-scale benchmarks (NTU RGB+D 60, NTU RGB+D 120, PKU-MMD, and Northwestern-UCLA) demonstrate that BHaRNet achieves SOTA accuracies -- improving from 86.4\% to 93.0\% in hand-intensive actions -- while maintaining fewer GFLOPs and parameters than the relevant unified methods.
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.
Addressing multi-label action recognition in videos represents a significant challenge for robotic applications in dynamic environments, especially when the robot is required to cooperate with humans in tasks that involve objects. Existing methods still struggle to recognize unseen actions or require extensive training data. To overcome these problems, we propose Dual-VCLIP, a unified approach for zero-shot multi-label action recognition. Dual-VCLIP enhances VCLIP, a zero-shot action recognition method, with the DualCoOp method for multi-label image classification. The strength of our method is that at training time it only learns two prompts, and it is therefore much simpler than other methods. We validate our method on the Charades dataset that includes a majority of object-based actions, demonstrating that -- despite its simplicity -- our method performs favorably with respect to existing methods on the complete dataset, and promising performance when tested on unseen actions. Our contribution emphasizes the impact of verb-object class-splits during robots' training for new cooperative tasks, highlighting the influence on the performance and giving insights into mitigating biases.
Skeleton Action Recognition (SAR) involves identifying human actions using skeletal joint coordinates and their interconnections. While plain Transformers have been attempted for this task, they still fall short compared to the current leading methods, which are rooted in Graph Convolutional Networks (GCNs) due to the absence of structural priors. Recently, a novel selective state space model, Mamba, has surfaced as a compelling alternative to the attention mechanism in Transformers, offering efficient modeling of long sequences. In this work, to the utmost extent of our awareness, we present the first SAR framework incorporating Mamba. Each fundamental block of our model adopts a novel U-ShiftGCN architecture with Mamba as its core component. The encoder segment of the U-ShiftGCN is devised to extract spatial features from the skeletal data using downsampling vanilla Shift S-GCN blocks. These spatial features then undergo intermediate temporal modeling facilitated by the Mamba block before progressing to the encoder section, which comprises vanilla upsampling Shift S-GCN blocks. Additionally, a Shift T-GCN (ShiftTCN) temporal modeling unit is employed before the exit of each fundamental block to refine temporal representations. This particular integration of downsampling spatial, intermediate temporal, upsampling spatial, and ultimate temporal subunits yields promising results for skeleton action recognition. We dub the resulting model \textbf{Simba}, which attains state-of-the-art performance across three well-known benchmark skeleton action recognition datasets: NTU RGB+D, NTU RGB+D 120, and Northwestern-UCLA. Interestingly, U-ShiftGCN (Simba without Intermediate Mamba Block) by itself is capable of performing reasonably well and surpasses our baseline.
Human action or activity recognition in videos is a fundamental task in computer vision with applications in surveillance and monitoring, self-driving cars, sports analytics, human-robot interaction and many more. Traditional supervised methods require large annotated datasets for training, which are expensive and time-consuming to acquire. This work proposes a novel approach using Cross-Architecture Pseudo-Labeling with contrastive learning for semi-supervised action recognition. Our framework leverages both labeled and unlabelled data to robustly learn action representations in videos, combining pseudo-labeling with contrastive learning for effective learning from both types of samples. We introduce a novel cross-architecture approach where 3D Convolutional Neural Networks (3D CNNs) and video transformers (VIT) are utilised to capture different aspects of action representations; hence we call it ActNetFormer. The 3D CNNs excel at capturing spatial features and local dependencies in the temporal domain, while VIT excels at capturing long-range dependencies across frames. By integrating these complementary architectures within the ActNetFormer framework, our approach can effectively capture both local and global contextual information of an action. This comprehensive representation learning enables the model to achieve better performance in semi-supervised action recognition tasks by leveraging the strengths of each of these architectures. Experimental results on standard action recognition datasets demonstrate that our approach performs better than the existing methods, achieving state-of-the-art performance with only a fraction of labeled data. The official website of this work is available at: https://github.com/rana2149/ActNetFormer.
Human action recognition in videos is a critical task with significant implications for numerous applications, including surveillance, sports analytics, and healthcare. The challenge lies in creating models that are both precise in their recognition capabilities and efficient enough for practical use. This study conducts an in-depth analysis of various deep learning models to address this challenge. Utilizing a subset of the UCF101 Videos dataset, we focus on Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Two-Stream ConvNets. The research reveals that while CNNs effectively capture spatial features and RNNs encode temporal sequences, Two-Stream ConvNets exhibit superior performance by integrating spatial and temporal dimensions. These insights are distilled from the evaluation metrics of accuracy, precision, recall, and F1-score. The results of this study underscore the potential of composite models in achieving robust human action recognition and suggest avenues for future research in optimizing these models for real-world deployment.
Action recognition in videos poses a challenge due to its high computational cost, especially for Joint Space-Time video transformers (Joint VT). Despite their effectiveness, the excessive number of tokens in such architectures significantly limits their efficiency. In this paper, we propose HaltingVT, an efficient video transformer adaptively removing redundant video patch tokens, which is primarily composed of a Joint VT and a Glimpser module. Specifically, HaltingVT applies data-adaptive token reduction at each layer, resulting in a significant reduction in the overall computational cost. Besides, the Glimpser module quickly removes redundant tokens in shallow transformer layers, which may even be misleading for video recognition tasks based on our observations. To further encourage HaltingVT to focus on the key motion-related information in videos, we design an effective Motion Loss during training. HaltingVT acquires video analysis capabilities and token halting compression strategies simultaneously in a unified training process, without requiring additional training procedures or sub-networks. On the Mini-Kinetics dataset, we achieved 75.0% top-1 ACC with 24.2 GFLOPs, as well as 67.2% top-1 ACC with an extremely low 9.9 GFLOPs. The code is available at https://github.com/dun-research/HaltingVT.
In this work, we present a novel approach to multi-view action recognition where we guide learned action representations to be separated from view-relevant information in a video. When trying to classify action instances captured from multiple viewpoints, there is a higher degree of difficulty due to the difference in background, occlusion, and visibility of the captured action from different camera angles. To tackle the various problems introduced in multi-view action recognition, we propose a novel configuration of learnable transformer decoder queries, in conjunction with two supervised contrastive losses, to enforce the learning of action features that are robust to shifts in viewpoints. Our disentangled feature learning occurs in two stages: the transformer decoder uses separate queries to separately learn action and view information, which are then further disentangled using our two contrastive losses. We show that our model and method of training significantly outperforms all other uni-modal models on four multi-view action recognition datasets: NTU RGB+D, NTU RGB+D 120, PKU-MMD, and N-UCLA. Compared to previous RGB works, we see maximal improvements of 1.5\%, 4.8\%, 2.2\%, and 4.8\% on each dataset, respectively.
Recognizing human actions in videos requires spatial and temporal understanding. Most existing action recognition models lack a balanced spatio-temporal understanding of videos. In this work, we propose a novel two-stream architecture, called Cross-Attention in Space and Time (CAST), that achieves a balanced spatio-temporal understanding of videos using only RGB input. Our proposed bottleneck cross-attention mechanism enables the spatial and temporal expert models to exchange information and make synergistic predictions, leading to improved performance. We validate the proposed method with extensive experiments on public benchmarks with different characteristics: EPIC-KITCHENS-100, Something-Something-V2, and Kinetics-400. Our method consistently shows favorable performance across these datasets, while the performance of existing methods fluctuates depending on the dataset characteristics.
The Meta Video Dataset (MetaVD) provides annotated relations between action classes in major datasets for human action recognition in videos. Although these annotated relations enable dataset augmentation, it is only applicable to those covered by MetaVD. For an external dataset to enjoy the same benefit, the relations between its action classes and those in MetaVD need to be determined. To address this issue, we consider two new machine learning tasks: action class relation detection and classification. We propose a unified model to predict relations between action classes, using language and visual information associated with classes. Experimental results show that (i) pre-trained recent neural network models for texts and videos contribute to high predictive performance, (ii) the relation prediction based on action label texts is more accurate than based on videos, and (iii) a blending approach that combines predictions by both modalities can further improve the predictive performance in some cases.
Existing action recognition methods are typically actor-specific due to the intrinsic topological and apparent differences among the actors. This requires actor-specific pose estimation (e.g., humans vs. animals), leading to cumbersome model design complexity and high maintenance costs. Moreover, they often focus on learning the visual modality alone and single-label classification whilst neglecting other available information sources (e.g., class name text) and the concurrent occurrence of multiple actions. To overcome these limitations, we propose a new approach called 'actor-agnostic multi-modal multi-label action recognition,' which offers a unified solution for various types of actors, including humans and animals. We further formulate a novel Multi-modal Semantic Query Network (MSQNet) model in a transformer-based object detection framework (e.g., DETR), characterized by leveraging visual and textual modalities to represent the action classes better. The elimination of actor-specific model designs is a key advantage, as it removes the need for actor pose estimation altogether. Extensive experiments on five publicly available benchmarks show that our MSQNet consistently outperforms the prior arts of actor-specific alternatives on human and animal single- and multi-label action recognition tasks by up to 50%. Code is made available at https://github.com/mondalanindya/MSQNet.
Modern hierarchical vision transformers have added several vision-specific components in the pursuit of supervised classification performance. While these components lead to effective accuracies and attractive FLOP counts, the added complexity actually makes these transformers slower than their vanilla ViT counterparts. In this paper, we argue that this additional bulk is unnecessary. By pretraining with a strong visual pretext task (MAE), we can strip out all the bells-and-whistles from a state-of-the-art multi-stage vision transformer without losing accuracy. In the process, we create Hiera, an extremely simple hierarchical vision transformer that is more accurate than previous models while being significantly faster both at inference and during training. We evaluate Hiera on a variety of tasks for image and video recognition. Our code and models are available at https://github.com/facebookresearch/hiera.
Scale is the primary factor for building a powerful foundation model that could well generalize to a variety of downstream tasks. However, it is still challenging to train video foundation models with billions of parameters. This paper shows that video masked autoencoder (VideoMAE) is a scalable and general self-supervised pre-trainer for building video foundation models. We scale the VideoMAE in both model and data with a core design. Specifically, we present a dual masking strategy for efficient pre-training, with an encoder operating on a subset of video tokens and a decoder processing another subset of video tokens. Although VideoMAE is very efficient due to high masking ratio in encoder, masking decoder can still further reduce the overall computational cost. This enables the efficient pre-training of billion-level models in video. We also use a progressive training paradigm that involves an initial pre-training on a diverse multi-sourced unlabeled dataset, followed by a post-pre-training on a mixed labeled dataset. Finally, we successfully train a video ViT model with a billion parameters, which achieves a new state-of-the-art performance on the datasets of Kinetics (90.0% on K400 and 89.9% on K600) and Something-Something (68.7% on V1 and 77.0% on V2). In addition, we extensively verify the pre-trained video ViT models on a variety of downstream tasks, demonstrating its effectiveness as a general video representation learner. The code and model is available at \url{https://github.com/OpenGVLab/VideoMAEv2}.
In this paper, we efficiently transfer the surpassing representation power of the vision foundation models, such as ViT and Swin, for video understanding with only a few trainable parameters. Previous adaptation methods have simultaneously considered spatial and temporal modeling with a unified learnable module but still suffered from fully leveraging the representative capabilities of image transformers. We argue that the popular dual-path (two-stream) architecture in video models can mitigate this problem. We propose a novel DualPath adaptation separated into spatial and temporal adaptation paths, where a lightweight bottleneck adapter is employed in each transformer block. Especially for temporal dynamic modeling, we incorporate consecutive frames into a grid-like frameset to precisely imitate vision transformers' capability that extrapolates relationships between tokens. In addition, we extensively investigate the multiple baselines from a unified perspective in video understanding and compare them with DualPath. Experimental results on four action recognition benchmarks prove that pretrained image transformers with DualPath can be effectively generalized beyond the data domain.
Recognizing human actions in video sequences, known as Human Action Recognition (HAR), is a challenging task in pattern recognition. While Convolutional Neural Networks (ConvNets) have shown remarkable success in image recognition, they are not always directly applicable to HAR, as temporal features are critical for accurate classification. In this paper, we propose a novel dynamic PSO-ConvNet model for learning actions in videos, building on our recent work in image recognition. Our approach leverages a framework where the weight vector of each neural network represents the position of a particle in phase space, and particles share their current weight vectors and gradient estimates of the Loss function. To extend our approach to video, we integrate ConvNets with state-of-the-art temporal methods such as Transformer and Recurrent Neural Networks. Our experimental results on the UCF-101 dataset demonstrate substantial improvements of up to 9% in accuracy, which confirms the effectiveness of our proposed method. In addition, we conducted experiments on larger and more variety of datasets including Kinetics-400 and HMDB-51 and obtained preference for Collaborative Learning in comparison with Non-Collaborative Learning (Individual Learning). Overall, our dynamic PSO-ConvNet model provides a promising direction for improving HAR by better capturing the spatio-temporal dynamics of human actions in videos. The code is available at https://github.com/leonlha/Video-Action-Recognition-Collaborative-Learning-with-Dynamics-via-PSO-ConvNet-Transformer.
Class Incremental Learning (CIL) is a hot topic in machine learning for CNN models to learn new classes incrementally. However, most of the CIL studies are for image classification and object recognition tasks and few CIL studies are available for video action classification. To mitigate this problem, in this paper, we present a new Grow When Required network (GWR) based video CIL framework for action classification. GWR learns knowledge incrementally by modeling the manifold of video frames for each encountered action class in feature space. We also introduce a Knowledge Consolidation (KC) method to separate the feature manifolds of old class and new class and introduce an associative matrix for label prediction. Experimental results on KTH and Weizmann demonstrate the effectiveness of the framework.
We present a simple approach which can turn a ViT encoder into an efficient video model, which can seamlessly work with both image and video inputs. By sparsely sampling the inputs, the model is able to do training and inference from both inputs. The model is easily scalable and can be adapted to large-scale pre-trained ViTs without requiring full finetuning. The model achieves SOTA results and the code will be open-sourced.
Few-shot action recognition in videos is challenging for its lack of supervision and difficulty in generalizing to unseen actions. To address this task, we propose a simple yet effective method, called knowledge prompting, which leverages commonsense knowledge of actions from external resources to prompt a powerful pre-trained vision-language model for few-shot classification. We first collect large-scale language descriptions of actions, defined as text proposals, to build an action knowledge base. The collection of text proposals is done by filling in handcraft sentence templates with external action-related corpus or by extracting action-related phrases from captions of Web instruction videos.Then we feed these text proposals into the pre-trained vision-language model along with video frames to generate matching scores of the proposals to each frame, and the scores can be treated as action semantics with strong generalization. Finally, we design a lightweight temporal modeling network to capture the temporal evolution of action semantics for classification.Extensive experiments on six benchmark datasets demonstrate that our method generally achieves the state-of-the-art performance while reducing the training overhead to 0.001 of existing methods.
Frozen pretrained models have become a viable alternative to the pretraining-then-finetuning paradigm for transfer learning. However, with frozen models there are relatively few parameters available for adapting to downstream tasks, which is problematic in computer vision where tasks vary significantly in input/output format and the type of information that is of value. In this paper, we present a study of frozen pretrained models when applied to diverse and representative computer vision tasks, including object detection, semantic segmentation and video action recognition. From this empirical analysis, our work answers the questions of what pretraining task fits best with this frozen setting, how to make the frozen setting more flexible to various downstream tasks, and the effect of larger model sizes. We additionally examine the upper bound of performance using a giant frozen pretrained model with 3 billion parameters (SwinV2-G) and find that it reaches competitive performance on a varied set of major benchmarks with only one shared frozen base network: 60.0 box mAP and 52.2 mask mAP on COCO object detection test-dev, 57.6 val mIoU on ADE20K semantic segmentation, and 81.7 top-1 accuracy on Kinetics-400 action recognition. With this work, we hope to bring greater attention to this promising path of freezing pretrained image models.
During recent years transformers architectures have been growing in popularity. Modulated Detection Transformer (MDETR) is an end-to-end multi-modal understanding model that performs tasks such as phase grounding, referring expression comprehension, referring expression segmentation, and visual question answering. One remarkable aspect of the model is the capacity to infer over classes that it was not previously trained for. In this work we explore the use of MDETR in a new task, action detection, without any previous training. We obtain quantitative results using the Atomic Visual Actions dataset. Although the model does not report the best performance in the task, we believe that it is an interesting finding. We show that it is possible to use a multi-modal model to tackle a task that it was not designed for. Finally, we believe that this line of research may lead into the generalization of MDETR in additional downstream tasks.