The SkatingVerse Workshop & Challenge aims to encourage research in developing novel and accurate methods for human action understanding. The SkatingVerse dataset used for the SkatingVerse Challenge has been publicly released. There are two subsets in the dataset, i.e., the training subset and testing subset. The training subsets consists of 19,993 RGB video sequences, and the testing subsets consists of 8,586 RGB video sequences. Around 10 participating teams from the globe competed in the SkatingVerse Challenge. In this paper, we provide a brief summary of the SkatingVerse Workshop & Challenge including brief introductions to the top three methods. The submission leaderboard will be reopened for researchers that are interested in the human action understanding challenge. The benchmark dataset and other information can be found at: https://skatingverse.github.io/.
Existing action quality assessment (AQA) methods mainly learn deep representations at the video level for scoring diverse actions. Due to the lack of a fine-grained understanding of actions in videos, they harshly suffer from low credibility and interpretability, thus insufficient for stringent applications, such as Olympic diving events. We argue that a fine-grained understanding of actions requires the model to perceive and parse actions in both time and space, which is also the key to the credibility and interpretability of the AQA technique. Based on this insight, we propose a new fine-grained spatial-temporal action parser named \textbf{FineParser}. It learns human-centric foreground action representations by focusing on target action regions within each frame and exploiting their fine-grained alignments in time and space to minimize the impact of invalid backgrounds during the assessment. In addition, we construct fine-grained annotations of human-centric foreground action masks for the FineDiving dataset, called \textbf{FineDiving-HM}. With refined annotations on diverse target action procedures, FineDiving-HM can promote the development of real-world AQA systems. Through extensive experiments, we demonstrate the effectiveness of FineParser, which outperforms state-of-the-art methods while supporting more tasks of fine-grained action understanding. Data and code are available at \url{https://github.com/PKU-ICST-MIPL/FineParser_CVPR2024}.
For a complete comprehension of multi-person scenes, it is essential to go beyond basic tasks like detection and tracking. Higher-level tasks, such as understanding the interactions and social activities among individuals, are also crucial. Progress towards models that can fully understand scenes involving multiple people is hindered by a lack of sufficient annotated data for such high-level tasks. To address this challenge, we introduce Social-MAE, a simple yet effective transformer-based masked autoencoder framework for multi-person human motion data. The framework uses masked modeling to pre-train the encoder to reconstruct masked human joint trajectories, enabling it to learn generalizable and data efficient representations of motion in human crowded scenes. Social-MAE comprises a transformer as the MAE encoder and a lighter-weight transformer as the MAE decoder which operates on multi-person joints' trajectory in the frequency domain. After the reconstruction task, the MAE decoder is replaced with a task-specific decoder and the model is fine-tuned end-to-end for a variety of high-level social tasks. Our proposed model combined with our pre-training approach achieves the state-of-the-art results on various high-level social tasks, including multi-person pose forecasting, social grouping, and social action understanding. These improvements are demonstrated across four popular multi-person datasets encompassing both human 2D and 3D body pose.
Owing to their ability to extract relevant spatio-temporal video embeddings, Vision Transformers (ViTs) are currently the best performing models in video action understanding. However, their generalization over domains or datasets is somewhat limited. In contrast, Visual Language Models (VLMs) have demonstrated exceptional generalization performance, but are currently unable to process videos. Consequently, they cannot extract spatio-temporal patterns that are crucial for action understanding. In this paper, we propose the Four-tiered Prompts (FTP) framework that takes advantage of the complementary strengths of ViTs and VLMs. We retain ViTs' strong spatio-temporal representation ability but improve the visual encodings to be more comprehensive and general by aligning them with VLM outputs. The FTP framework adds four feature processors that focus on specific aspects of human action in videos: action category, action components, action description, and context information. The VLMs are only employed during training, and inference incurs a minimal computation cost. Our approach consistently yields state-of-the-art performance. For instance, we achieve remarkable top-1 accuracy of 93.8% on Kinetics-400 and 83.4% on Something-Something V2, surpassing VideoMAEv2 by 2.8% and 2.6%, respectively.
Action knowledge involves the understanding of textual, visual, and temporal aspects of actions. We introduce the Action Dynamics Benchmark (ActionBench) containing two carefully designed probing tasks: Action Antonym and Video Reversal, which targets multimodal alignment capabilities and temporal understanding skills of the model, respectively. Despite recent video-language models' (VidLM) impressive performance on various benchmark tasks, our diagnostic tasks reveal their surprising deficiency (near-random performance) in action knowledge, suggesting that current models rely on object recognition abilities as a shortcut for action understanding. To remedy this, we propose a novel framework, Paxion, along with a new Discriminative Video Dynamics Modeling (DVDM) objective. The Paxion framework utilizes a Knowledge Patcher network to encode new action knowledge and a Knowledge Fuser component to integrate the Patcher into frozen VidLMs without compromising their existing capabilities. Due to limitations of the widely-used Video-Text Contrastive (VTC) loss for learning action knowledge, we introduce the DVDM objective to train the Knowledge Patcher. DVDM forces the model to encode the correlation between the action text and the correct ordering of video frames. Our extensive analyses show that Paxion and DVDM together effectively fill the gap in action knowledge understanding (~50% to 80%), while maintaining or improving performance on a wide spectrum of both object- and action-centric downstream tasks. The code and data will be made publicly available for research purposes at https://github.com/MikeWangWZHL/Paxion.git.
Large language models (LLMs) have immense potential to make information more accessible, particularly in medicine, where complex medical jargon can hinder patient comprehension of clinical notes. We developed a patient-facing tool using LLMs to make clinical notes more readable by simplifying, extracting information from, and adding context to the notes. We piloted the tool with clinical notes donated by patients with a history of breast cancer and synthetic notes from a clinician. Participants (N=200, healthy, female-identifying patients) were randomly assigned three clinical notes in our tool with varying levels of augmentations and answered quantitative and qualitative questions evaluating their understanding of follow-up actions. Augmentations significantly increased their quantitative understanding scores. In-depth interviews were conducted with participants (N=7, patients with a history of breast cancer), revealing both positive sentiments about the augmentations and concerns about AI. We also performed a qualitative clinician-driven analysis of the model's error modes.
Minimally invasive surgery (MIS) has revolutionized many procedures and led to reduced recovery time and risk of patient injury. However, MIS poses additional complexity and burden on surgical teams. Data-driven surgical vision algorithms are thought to be key building blocks in the development of future MIS systems with improved autonomy. Recent advancements in machine learning and computer vision have led to successful applications in analyzing videos obtained from MIS with the promise of alleviating challenges in MIS videos. Surgical scene and action understanding encompasses multiple related tasks that, when solved individually, can be memory-intensive, inefficient, and fail to capture task relationships. Multitask learning (MTL), a learning paradigm that leverages information from multiple related tasks to improve performance and aid generalization, is wellsuited for fine-grained and high-level understanding of MIS data. This review provides an overview of the current state-of-the-art MTL systems that leverage videos obtained from MIS. Beyond listing published approaches, we discuss the benefits and limitations of these MTL systems. Moreover, this manuscript presents an analysis of the literature for various application fields of MTL in MIS, including those with large models, highlighting notable trends, new directions of research, and developments.
Reasoning over sports videos for question answering is an important task with numerous applications, such as player training and information retrieval. However, this task has not been explored due to the lack of relevant datasets and the challenging nature it presents. Most datasets for video question answering (VideoQA) focus mainly on general and coarse-grained understanding of daily-life videos, which is not applicable to sports scenarios requiring professional action understanding and fine-grained motion analysis. In this paper, we introduce the first dataset, named Sports-QA, specifically designed for the sports VideoQA task. The Sports-QA dataset includes various types of questions, such as descriptions, chronologies, causalities, and counterfactual conditions, covering multiple sports. Furthermore, to address the characteristics of the sports VideoQA task, we propose a new Auto-Focus Transformer (AFT) capable of automatically focusing on particular scales of temporal information for question answering. We conduct extensive experiments on Sports-QA, including baseline studies and the evaluation of different methods. The results demonstrate that our AFT achieves state-of-the-art performance.
A comprehensive understanding of videos is inseparable from describing the action with its contextual action-object interactions. However, many current video understanding tasks prioritize general action classification and overlook the actors and relationships that shape the nature of the action, resulting in a superficial understanding of the action. Motivated by this, we introduce Open-vocabulary Video Relation Extraction (OVRE), a novel task that views action understanding through the lens of action-centric relation triplets. OVRE focuses on pairwise relations that take part in the action and describes these relation triplets with natural languages. Moreover, we curate the Moments-OVRE dataset, which comprises 180K videos with action-centric relation triplets, sourced from a multi-label action classification dataset. With Moments-OVRE, we further propose a crossmodal mapping model to generate relation triplets as a sequence. Finally, we benchmark existing cross-modal generation models on the new task of OVRE.
Developing end-to-end action recognition models on long videos is fundamental and crucial for long-video action understanding. Due to the unaffordable cost of end-to-end training on the whole long videos, existing works generally train models on short clips trimmed from long videos. However, this ``trimming-then-training'' practice requires action interval annotations for clip-level supervision, i.e., knowing which actions are trimmed into the clips. Unfortunately, collecting such annotations is very expensive and prevents model training at scale. To this end, this work aims to build a weakly supervised end-to-end framework for training recognition models on long videos, with only video-level action category labels. Without knowing the precise temporal locations of actions in long videos, our proposed weakly supervised framework, namely AdaptFocus, estimates where and how likely the actions will occur to adaptively focus on informative action clips for end-to-end training. The effectiveness of the proposed AdaptFocus framework is demonstrated on three long-video datasets. Furthermore, for downstream long-video tasks, our AdaptFocus framework provides a weakly supervised feature extraction pipeline for extracting more robust long-video features, such that the state-of-the-art methods on downstream tasks are significantly advanced. We will release the code and models.
Deontological ethics, specifically understood through Immanuel Kant, provides a moral framework that emphasizes the importance of duties and principles, rather than the consequences of action. Understanding that despite the prominence of deontology, it is currently an overlooked approach in fairness metrics, this paper explores the compatibility of a Kantian deontological framework in fairness metrics, part of the AI alignment field. We revisit Kant's critique of utilitarianism, which is the primary approach in AI fairness metrics and argue that fairness principles should align with the Kantian deontological framework. By integrating Kantian ethics into AI alignment, we not only bring in a widely-accepted prominent moral theory but also strive for a more morally grounded AI landscape that better balances outcomes and procedures in pursuit of fairness and justice.
Unsupervised pre-training has shown great success in skeleton-based action understanding recently. Existing works typically train separate modality-specific models, then integrate the multi-modal information for action understanding by a late-fusion strategy. Although these approaches have achieved significant performance, they suffer from the complex yet redundant multi-stream model designs, each of which is also limited to the fixed input skeleton modality. To alleviate these issues, in this paper, we propose a Unified Multimodal Unsupervised Representation Learning framework, called UmURL, which exploits an efficient early-fusion strategy to jointly encode the multi-modal features in a single-stream manner. Specifically, instead of designing separate modality-specific optimization processes for uni-modal unsupervised learning, we feed different modality inputs into the same stream with an early-fusion strategy to learn their multi-modal features for reducing model complexity. To ensure that the fused multi-modal features do not exhibit modality bias, i.e., being dominated by a certain modality input, we further propose both intra- and inter-modal consistency learning to guarantee that the multi-modal features contain the complete semantics of each modal via feature decomposition and distinct alignment. In this manner, our framework is able to learn the unified representations of uni-modal or multi-modal skeleton input, which is flexible to different kinds of modality input for robust action understanding in practical cases. Extensive experiments conducted on three large-scale datasets, i.e., NTU-60, NTU-120, and PKU-MMD II, demonstrate that UmURL is highly efficient, possessing the approximate complexity with the uni-modal methods, while achieving new state-of-the-art performance across various downstream task scenarios in skeleton-based action representation learning.
Most existing forecasting systems are memory-based methods, which attempt to mimic human forecasting ability by employing various memory mechanisms and have progressed in temporal modeling for memory dependency. Nevertheless, an obvious weakness of this paradigm is that it can only model limited historical dependence and can not transcend the past. In this paper, we rethink the temporal dependence of event evolution and propose a novel memory-anticipation-based paradigm to model an entire temporal structure, including the past, present, and future. Based on this idea, we present Memory-and-Anticipation Transformer (MAT), a memory-anticipation-based approach, to address the online action detection and anticipation tasks. In addition, owing to the inherent superiority of MAT, it can process online action detection and anticipation tasks in a unified manner. The proposed MAT model is tested on four challenging benchmarks TVSeries, THUMOS'14, HDD, and EPIC-Kitchens-100, for online action detection and anticipation tasks, and it significantly outperforms all existing methods. Code is available at https://github.com/Echo0125/Memory-and-Anticipation-Transformer.
Self-supervised learning has proved effective for skeleton-based human action understanding, which is an important yet challenging topic. Previous works mainly rely on contrastive learning or masked motion modeling paradigm to model the skeleton relations. However, the sequence-level and joint-level representation learning cannot be effectively and simultaneously handled by these methods. As a result, the learned representations fail to generalize to different downstream tasks. Moreover, combining these two paradigms in a naive manner leaves the synergy between them untapped and can lead to interference in training. To address these problems, we propose Prompted Contrast with Masked Motion Modeling, PCM$^{\rm 3}$, for versatile 3D action representation learning. Our method integrates the contrastive learning and masked prediction tasks in a mutually beneficial manner, which substantially boosts the generalization capacity for various downstream tasks. Specifically, masked prediction provides novel training views for contrastive learning, which in turn guides the masked prediction training with high-level semantic information. Moreover, we propose a dual-prompted multi-task pretraining strategy, which further improves model representations by reducing the interference caused by learning the two different pretext tasks. Extensive experiments on five downstream tasks under three large-scale datasets are conducted, demonstrating the superior generalization capacity of PCM$^{\rm 3}$ compared to the state-of-the-art works. Our project is publicly available at: https://jhang2020.github.io/Projects/PCM3/PCM3.html .
Developmental psychologists have spent decades devising experiments to test the intelligence and knowledge of infants and children, tracing the origin of crucial concepts and capacities. Moreover, experimental techniques in developmental psychology have been carefully designed to discriminate the cognitive capacities that underlie particular behaviors. We propose that using classical experiments from child development is a particularly effective way to probe the computational abilities of AI models, in general, and LLMs in particular. First, the methodological techniques of developmental psychology, such as the use of novel stimuli to control for past experience or control conditions to determine whether children are using simple associations, can be equally helpful for assessing the capacities of LLMs. In parallel, testing LLMs in this way can tell us whether the information that is encoded in text is sufficient to enable particular responses, or whether those responses depend on other kinds of information, such as information from exploration of the physical world. In this work we adapt classical developmental experiments to evaluate the capabilities of LaMDA, a large language model from Google. We propose a novel LLM Response Score (LRS) metric which can be used to evaluate other language models, such as GPT. We find that LaMDA generates appropriate responses that are similar to those of children in experiments involving social understanding, perhaps providing evidence that knowledge of these domains is discovered through language. On the other hand, LaMDA's responses in early object and action understanding, theory of mind, and especially causal reasoning tasks are very different from those of young children, perhaps showing that these domains require more real-world, self-initiated exploration and cannot simply be learned from patterns in language input.
With the emergence of collaborative robots (cobots), human-robot collaboration in industrial manufacturing is coming into focus. For a cobot to act autonomously and as an assistant, it must understand human actions during assembly. To effectively train models for this task, a dataset containing suitable assembly actions in a realistic setting is crucial. For this purpose, we present the ATTACH dataset, which contains 51.6 hours of assembly with 95.2k annotated fine-grained actions monitored by three cameras, which represent potential viewpoints of a cobot. Since in an assembly context workers tend to perform different actions simultaneously with their two hands, we annotated the performed actions for each hand separately. Therefore, in the ATTACH dataset, more than 68% of annotations overlap with other annotations, which is many times more than in related datasets, typically featuring more simplistic assembly tasks. For better generalization with respect to the background of the working area, we did not only record color and depth images, but also used the Azure Kinect body tracking SDK for estimating 3D skeletons of the worker. To create a first baseline, we report the performance of state-of-the-art methods for action recognition as well as action detection on video and skeleton-sequence inputs. The dataset is available at https://www.tu-ilmenau.de/neurob/data-sets-code/attach-dataset .
Action understanding has attracted long-term attention. It can be formed as the mapping from the physical space to the semantic space. Typically, researchers built datasets according to idiosyncratic choices to define classes and push the envelope of benchmarks respectively. Datasets are incompatible with each other like "Isolated Islands" due to semantic gaps and various class granularities, e.g., do housework in dataset A and wash plate in dataset B. We argue that we need a more principled semantic space to concentrate the community efforts and use all datasets together to pursue generalizable action learning. To this end, we design a structured action semantic space given verb taxonomy hierarchy and covering massive actions. By aligning the classes of previous datasets to our semantic space, we gather (image/video/skeleton/MoCap) datasets into a unified database in a unified label system, i.e., bridging "isolated islands" into a "Pangea". Accordingly, we propose a novel model mapping from the physical space to semantic space to fully use Pangea. In extensive experiments, our new system shows significant superiority, especially in transfer learning. Our code and data will be made public at https://mvig-rhos.com/pangea.
The ability to estimate 3D human body pose and movement, also known as human pose estimation (HPE), enables many applications for home-based health monitoring, such as remote rehabilitation training. Several possible solutions have emerged using sensors ranging from RGB cameras, depth sensors, millimeter-Wave (mmWave) radars, and wearable inertial sensors. Despite previous efforts on datasets and benchmarks for HPE, few dataset exploits multiple modalities and focuses on home-based health monitoring. To bridge the gap, we present mRI, a multi-modal 3D human pose estimation dataset with mmWave, RGB-D, and Inertial Sensors. Our dataset consists of over 160k synchronized frames from 20 subjects performing rehabilitation exercises and supports the benchmarks of HPE and action detection. We perform extensive experiments using our dataset and delineate the strength of each modality. We hope that the release of mRI can catalyze the research in pose estimation, multi-modal learning, and action understanding, and more importantly facilitate the applications of home-based health monitoring.
Action understanding has evolved into the era of fine granularity, as most human behaviors in real life have only minor differences. To detect these fine-grained actions accurately in a label-efficient way, we tackle the problem of weakly-supervised fine-grained temporal action detection in videos for the first time. Without the careful design to capture subtle differences between fine-grained actions, previous weakly-supervised models for general action detection cannot perform well in the fine-grained setting. We propose to model actions as the combinations of reusable atomic actions which are automatically discovered from data through self-supervised clustering, in order to capture the commonality and individuality of fine-grained actions. The learnt atomic actions, represented by visual concepts, are further mapped to fine and coarse action labels leveraging the semantic label hierarchy. Our approach constructs a visual representation hierarchy of four levels: clip level, atomic action level, fine action class level and coarse action class level, with supervision at each level. Extensive experiments on two large-scale fine-grained video datasets, FineAction and FineGym, show the benefit of our proposed weakly-supervised model for fine-grained action detection, and it achieves state-of-the-art results.
Action Quality Assessment(AQA) is important for action understanding and resolving the task poses unique challenges due to subtle visual differences. Existing state-of-the-art methods typically rely on the holistic video representations for score regression or ranking, which limits the generalization to capture fine-grained intra-class variation. To overcome the above limitation, we propose a temporal parsing transformer to decompose the holistic feature into temporal part-level representations. Specifically, we utilize a set of learnable queries to represent the atomic temporal patterns for a specific action. Our decoding process converts the frame representations to a fixed number of temporally ordered part representations. To obtain the quality score, we adopt the state-of-the-art contrastive regression based on the part representations. Since existing AQA datasets do not provide temporal part-level labels or partitions, we propose two novel loss functions on the cross attention responses of the decoder: a ranking loss to ensure the learnable queries to satisfy the temporal order in cross attention and a sparsity loss to encourage the part representations to be more discriminative. Extensive experiments show that our proposed method outperforms prior work on three public AQA benchmarks by a considerable margin.