The skeleton-based temporal action segmentation (STAS) aims to densely segment and classify human actions within lengthy untrimmed skeletal motion sequences. Current methods primarily rely on graph convolutional networks (GCNs) for intraframe spatial modeling and temporal convolutional networks (TCNs) for interframe temporal modeling to discern motion patterns. However, these approaches often overlook the distinctive nature of essential action elements across various actions, including engaged core body parts and key subactions. This oversight limits the ability to distinguish different actions within a given sequence. To address these limitations, the snippet-aware Transformer with multiple action element (ME-ST) is proposed to enhance the discrimination and segmentation among actions, which leverages intrasnippet attention along joints and sequences to identify core joints and key subactions at different scales. Specifically, in terms of the spatial domain, the intrasnippet cross-joint attention (CJA) module divides the sequence into distinct snippets and computes attention to establish intricate joint semantic relationships, emphasizing the identification of core motion joints. In terms of the temporal domain, in the encoder, the intrasnippet cross-frame attention (CFA) module segments the sequence in a blockwise expansion manner and establishes interframe relationships to highlight the most discriminative frames. In the decoder, clip-level representations at various temporal scales are initially generated through an hourglass-like sampling process, followed by the intrasnippet cross-scale attention (CSA) module to integrate the key clip information across different time scales. The performance evaluation on five public datasets demonstrates that ME-ST achieves state-of-the-art (SOTA) performance.
Temporal action segmentation (TAS) has long been a key area of research in both robotics and computer vision. In robotics, algorithms have primarily focused on leveraging proprioceptive information to determine skill boundaries, with recent approaches in surgical robotics incorporating vision. In contrast, computer vision typically relies on exteroceptive sensors, such as cameras. Existing multimodal TAS models in robotics integrate feature fusion within the model, making it difficult to reuse learned features across different models. Meanwhile, pretrained vision-only feature extractors commonly used in computer vision struggle in scenarios with limited object visibility. In this work, we address these challenges by proposing M2R2, a multimodal feature extractor tailored for TAS, which combines information from both proprioceptive and exteroceptive sensors. We introduce a novel pretraining strategy that enables the reuse of learned features across multiple TAS models. Our method achieves state-of-the-art performance on the REASSEMBLE dataset, a challenging multimodal robotic assembly dataset, outperforming existing robotic action segmentation models by 46.6%. Additionally, we conduct an extensive ablation study to evaluate the contribution of different modalities in robotic TAS tasks.
While there has been substantial progress in temporal action segmentation, the challenge to generalize to unseen views remains unaddressed. Hence, we define a protocol for unseen view action segmentation where camera views for evaluating the model are unavailable during training. This includes changing from top-frontal views to a side view or even more challenging from exocentric to egocentric views. Furthermore, we present an approach for temporal action segmentation that tackles this challenge. Our approach leverages a shared representation at both the sequence and segment levels to reduce the impact of view differences during training. We achieve this by introducing a sequence loss and an action loss, which together facilitate consistent video and action representations across different views. The evaluation on the Assembly101, IkeaASM, and EgoExoLearn datasets demonstrate significant improvements, with a 12.8% increase in F1@50 for unseen exocentric views and a substantial 54% improvement for unseen egocentric views.
Understanding a procedural activity requires modeling both how action steps transform the scene, and how evolving scene transformations can influence the sequence of action steps, even those that are accidental or erroneous. Existing work has studied procedure-aware video representations by proposing novel approaches such as modeling the temporal order of actions and has not explicitly learned the state changes (scene transformations). In this work, we study procedure-aware video representation learning by incorporating state-change descriptions generated by Large Language Models (LLMs) as supervision signals for video encoders. Moreover, we generate state-change counterfactuals that simulate hypothesized failure outcomes, allowing models to learn by imagining the unseen ``What if'' scenarios. This counterfactual reasoning facilitates the model's ability to understand the cause and effect of each step in an activity. To verify the procedure awareness of our model, we conduct extensive experiments on procedure-aware tasks, including temporal action segmentation and error detection. Our results demonstrate the effectiveness of the proposed state-change descriptions and their counterfactuals and achieve significant improvements on multiple tasks. We will make our source code and data publicly available soon.
Temporal action segmentation in untrimmed procedural videos aims to densely label frames into action classes. These videos inherently exhibit long-tailed distributions, where actions vary widely in frequency and duration. In temporal action segmentation approaches, we identified a bi-level learning bias. This bias encompasses (1) a class-level bias, stemming from class imbalance favoring head classes, and (2) a transition-level bias arising from variations in transitions, prioritizing commonly observed transitions. As a remedy, we introduce a constrained optimization problem to alleviate both biases. We define learning states for action classes and their associated transitions and integrate them into the optimization process. We propose a novel cost-sensitive loss function formulated as a weighted cross-entropy loss, with weights adaptively adjusted based on the learning state of actions and their transitions. Experiments on three challenging temporal segmentation benchmarks and various frameworks demonstrate the effectiveness of our approach, resulting in significant improvements in both per-class frame-wise and segment-wise performance.
This work presents the first condensation approach for procedural video datasets used in temporal action segmentation. We propose a condensation framework that leverages generative prior learned from the dataset and network inversion to condense data into compact latent codes with significant storage reduced across temporal and channel aspects. Orthogonally, we propose sampling diverse and representative action sequences to minimize video-wise redundancy. Our evaluation on standard benchmarks demonstrates consistent effectiveness in condensing TAS datasets and achieving competitive performances. Specifically, on the Breakfast dataset, our approach reduces storage by over 500$\times$ while retaining 83% of the performance compared to training with the full dataset. Furthermore, when applied to a downstream incremental learning task, it yields superior performance compared to the state-of-the-art.
Temporal logical understanding, a core facet of human cognition, plays a pivotal role in capturing complex sequential events and their temporal relationships within videos. This capability is particularly crucial in tasks like Video Question Answering (VideoQA), where the goal is to process visual data over time together with textual data to provide coherent answers. However, current VideoQA benchmarks devote little focus to evaluating this critical skill due to the challenge of annotating temporal logic. Despite the advancement of vision-language models, assessing their temporal logical reasoning powers remains a challenge, primarily due to the lack QA pairs that demand formal, complex temporal reasoning. To bridge this gap, we introduce the TimeLogic QA (TLQA) framework to automatically generate the QA pairs, specifically designed to evaluate the temporal logical understanding. To this end, TLQA leverages temporal annotations from existing video datasets together with temporal operators derived from logic theory to construct questions that test understanding of event sequences and their temporal relationships. TLQA framework is generic and scalable, capable of leveraging both, existing video action datasets with temporal action segmentation annotations, or video datasets with temporal scene graph annotations, to automatically generate temporal logical questions. We leverage 4 datasets, STAR, Breakfast, AGQA, and CrossTask, and generate two VideoQA dataset variants - small (TLQA-S) and large (TLQA-L) - containing 2k and 10k QA pairs for each category, resulting in 32k and 160k total pairs per dataset. We undertake a comprehensive evaluation of leading-edge VideoQA models, employing the TLQA to benchmark their temporal logical understanding capabilities. We assess the VideoQA model's temporal reasoning performance on 16 categories of temporal logic with varying temporal complexity.
In this work, we address unsupervised temporal action segmentation, which segments a set of long, untrimmed videos into semantically meaningful segments that are consistent across videos. While recent approaches combine representation learning and clustering in a single step for this task, they do not cope with large variations within temporal segments of the same class. To address this limitation, we propose a novel method, termed Hierarchical Vector Quantization (HVQ), that consists of two subsequent vector quantization modules. This results in a hierarchical clustering where the additional subclusters cover the variations within a cluster. We demonstrate that our approach captures the distribution of segment lengths much better than the state of the art. To this end, we introduce a new metric based on the Jensen-Shannon Distance (JSD) for unsupervised temporal action segmentation. We evaluate our approach on three public datasets, namely Breakfast, YouTube Instructional and IKEA ASM. Our approach outperforms the state of the art in terms of F1 score, recall and JSD.
Temporal action segmentation and long-term action anticipation are two popular vision tasks for the temporal analysis of actions in videos. Despite apparent relevance and potential complementarity, these two problems have been investigated as separate and distinct tasks. In this work, we tackle these two problems, action segmentation and action anticipation, jointly using a unified diffusion model dubbed ActFusion. The key idea to unification is to train the model to effectively handle both visible and invisible parts of the sequence in an integrated manner; the visible part is for temporal segmentation, and the invisible part is for future anticipation. To this end, we introduce a new anticipative masking strategy during training in which a late part of the video frames is masked as invisible, and learnable tokens replace these frames to learn to predict the invisible future. Experimental results demonstrate the bi-directional benefits between action segmentation and anticipation. ActFusion achieves the state-of-the-art performance across the standard benchmarks of 50 Salads, Breakfast, and GTEA, outperforming task-specific models in both of the two tasks with a single unified model through joint learning.
This paper introduces TemporalVLM, a video large language model capable of effective temporal reasoning and fine-grained understanding in long videos. At the core, our approach includes a visual encoder for mapping a long-term input video into features which are time-aware and contain both local and global cues. In particular, it first divides the input video into short-term clips, which are jointly encoded with their timestamps into time-sensitive local features. Next, the local features are passed through a bidirectional long short-term memory module for global feature aggregation. The extracted time-aware and multi-level features are important for accurate temporal reasoning and fine-grained understanding in long videos. Moreover, to facilitate the evaluation of TemporalVLM, we present a large-scale long video dataset of industry assembly processes, namely IndustryASM, which consists of videos recorded on factory floors with actions and timestamps annotated by industrial engineers for time and motion studies and temporal action segmentation evaluation. Finally, extensive experiments on datasets of long videos, including TimeIT and IndustryASM, show that TemporalVLM achieves superior performance than previous methods across temporal reasoning and fine-grained understanding tasks, namely dense video captioning, temporal video grounding, video highlight detection, and temporal action segmentation.
Temporal context plays a significant role in temporal action segmentation. In an offline setting, the context is typically captured by the segmentation network after observing the entire sequence. However, capturing and using such context information in an online setting remains an under-explored problem. This work presents the an online framework for temporal action segmentation. At the core of the framework is an adaptive memory designed to accommodate dynamic changes in context over time, alongside a feature augmentation module that enhances the frames with the memory. In addition, we propose a post-processing approach to mitigate the severe over-segmentation in the online setting. On three common segmentation benchmarks, our approach achieves state-of-the-art performance.
Multimodal systems have great potential to assist humans in procedural activities, where people follow instructions to achieve their goals. Despite diverse application scenarios, systems are typically evaluated on traditional classification tasks, e.g., action recognition or temporal action segmentation. In this paper, we present a novel evaluation dataset, ProMQA, to measure system advancements in application-oriented scenarios. ProMQA consists of 401 multimodal procedural QA pairs on user recording of procedural activities coupled with their corresponding instruction. For QA annotation, we take a cost-effective human-LLM collaborative approach, where the existing annotation is augmented with LLM-generated QA pairs that are later verified by humans. We then provide the benchmark results to set the baseline performance on ProMQA. Our experiment reveals a significant gap between human performance and that of current systems, including competitive proprietary multimodal models. We hope our dataset sheds light on new aspects of models' multimodal understanding capabilities.
For the task of temporal action segmentation, existing works commonly treat it as a frame-wise classification problem. In this paper, we propose a straight but effective model namely ASQuery by learning central representation of each action category, which transforms the classification problem to the similarity calculation between category-specific queries and frame features. These central representations are dynamically generated through our Transformer decoder module, endowing them more flexible and comprehensive perception of the whole video. Moreover, we first introduce the boundary query for refining segmentation results, aiding to alleviating the troublesome over-segmentation problem. ASQuery demonstrates superior performance compared to state-of-the-art models, achieving improvements of 0.9% and 4.1% in the mean metrics on two public action segmentation datasets, i.e., Breakfast and Assembly101, respectively. The source codes are available at https://github.com/zlngan/ASQuery.
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.
With the development of video understanding, there is a proliferation of tasks for clip-level temporal video analysis, including temporal action detection (TAD), temporal action segmentation (TAS), and generic event boundary detection (GEBD). While task-specific video understanding models have exhibited outstanding performance in each task, there remains a dearth of a unified framework capable of simultaneously addressing multiple tasks, which is a promising direction for the next generation of AI. To this end, in this paper, we propose a single unified framework, coined as Temporal2Seq, to formulate the output of these temporal video understanding tasks as a sequence of discrete tokens. With this unified token representation, Temporal2Seq can train a generalist model within a single architecture on different video understanding tasks. In the absence of multi-task learning (MTL) benchmarks, we compile a comprehensive co-training dataset by borrowing the datasets from TAD, TAS, and GEBD tasks. We evaluate our Temporal2Seq generalist model on the corresponding test sets of three tasks, demonstrating that Temporal2Seq can produce reasonable results on various tasks and achieve advantages compared with single-task training on this framework. We also investigate the generalization performance of our generalist model on new datasets from different tasks, which yields superior performance to the specific model.
Understanding human actions from videos is essential in many domains, including sports. In figure skating, technical judgments are performed by watching skaters' 3D movements, and its part of the judging procedure can be regarded as a Temporal Action Segmentation (TAS) task. TAS tasks in figure skating that automatically assign temporal semantics to video are actively researched. However, there is a lack of datasets and effective methods for TAS tasks requiring 3D pose data. In this study, we first created the FS-Jump3D dataset of complex and dynamic figure skating jumps using optical markerless motion capture. We also propose a new fine-grained figure skating jump TAS dataset annotation method with which TAS models can learn jump procedures. In the experimental results, we validated the usefulness of 3D pose features as input and the fine-grained dataset for the TAS model in figure skating. FS-Jump3D Dataset is available at https://github.com/ryota-skating/FS-Jump3D.
Procedural activity videos often exhibit a long-tailed action distribution due to varying action frequencies and durations. However, state-of-the-art temporal action segmentation methods overlook the long tail and fail to recognize tail actions. Existing long-tail methods make class-independent assumptions and struggle to identify tail classes when applied to temporal segmentation frameworks. This work proposes a novel group-wise temporal logit adjustment~(G-TLA) framework that combines a group-wise softmax formulation while leveraging activity information and action ordering for logit adjustment. The proposed framework significantly improves in segmenting tail actions without any performance loss on head actions.
Temporal Action Segmentation (TAS) is an essential task in video analysis, aiming to segment and classify continuous frames into distinct action segments. However, the ambiguous boundaries between actions pose a significant challenge for high-precision segmentation. Recent advances in diffusion models have demonstrated substantial success in TAS tasks due to their stable training process and high-quality generation capabilities. However, the heavy sampling steps required by diffusion models pose a substantial computational burden, limiting their practicality in real-time applications. Additionally, most related works utilize Transformer-based encoder architectures. Although these architectures excel at capturing long-range dependencies, they incur high computational costs and face feature-smoothing issues when processing long video sequences. To address these challenges, we propose EffiDiffAct, an efficient and high-performance TAS algorithm. Specifically, we develop a lightweight temporal feature encoder that reduces computational overhead and mitigates the rank collapse phenomenon associated with traditional self-attention mechanisms. Furthermore, we introduce an adaptive skip strategy that allows for dynamic adjustment of timestep lengths based on computed similarity metrics during inference, thereby further enhancing computational efficiency. Comprehensive experiments on the 50Salads, Breakfast, and GTEA datasets demonstrated the effectiveness of the proposed algorithm.
Although the performance of Temporal Action Segmentation (TAS) has improved in recent years, achieving promising results often comes with a high computational cost due to dense inputs, complex model structures, and resource-intensive post-processing requirements. To improve the efficiency while keeping the performance, we present a novel perspective centered on per-segment classification. By harnessing the capabilities of Transformers, we tokenize each video segment as an instance token, endowed with intrinsic instance segmentation. To realize efficient action segmentation, we introduce BaFormer, a boundary-aware Transformer network. It employs instance queries for instance segmentation and a global query for class-agnostic boundary prediction, yielding continuous segment proposals. During inference, BaFormer employs a simple yet effective voting strategy to classify boundary-wise segments based on instance segmentation. Remarkably, as a single-stage approach, BaFormer significantly reduces the computational costs, utilizing only 6% of the running time compared to state-of-the-art method DiffAct, while producing better or comparable accuracy over several popular benchmarks. The code for this project is publicly available at https://github.com/peiyao-w/BaFormer.
Online temporal action segmentation shows a strong potential to facilitate many HRI tasks where extended human action sequences must be tracked and understood in real time. Traditional action segmentation approaches, however, operate in an offline two stage approach, relying on computationally expensive video wide features for segmentation, rendering them unsuitable for online HRI applications. In order to facilitate online action segmentation on a stream of incoming video data, we introduce two methods for improved training and inference of backbone action recognition models, allowing them to be deployed directly for online frame level classification. Firstly, we introduce surround dense sampling whilst training to facilitate training vs. inference clip matching and improve segment boundary predictions. Secondly, we introduce an Online Temporally Aware Label Cleaning (O-TALC) strategy to explicitly reduce oversegmentation during online inference. As our methods are backbone invariant, they can be deployed with computationally efficient spatio-temporal action recognition models capable of operating in real time with a small segmentation latency. We show our method outperforms similar online action segmentation work as well as matches the performance of many offline models with access to full temporal resolution when operating on challenging fine-grained datasets.