We present HOI4D, a large-scale 4D egocentric dataset with rich annotations, to catalyze the research of category-level human-object interaction. HOI4D consists of 2.4M RGB-D egocentric video frames over 4000 sequences collected by 4 participants interacting with 800 different object instances from 16 categories over 610 different indoor rooms. Frame-wise annotations for panoptic segmentation, motion segmentation, 3D hand pose, category-level object pose and hand action have also been provided, together with reconstructed object meshes and scene point clouds. With HOI4D, we establish three benchmarking tasks to promote category-level HOI from 4D visual signals including semantic segmentation of 4D dynamic point cloud sequences, category-level object pose tracking, and egocentric action segmentation with diverse interaction targets. In-depth analysis shows HOI4D poses great challenges to existing methods and produces great research opportunities.
The ability to identify and temporally segment fine-grained actions in motion capture sequences is crucial for applications in human movement analysis. Motion capture is typically performed with optical or inertial measurement systems, which encode human movement as a time series of human joint locations and orientations or their higher-order representations. State-of-the-art action segmentation approaches use multiple stages of temporal convolutions. The main idea is to generate an initial prediction with several layers of temporal convolutions and refine these predictions over multiple stages, also with temporal convolutions. Although these approaches capture long-term temporal patterns, the initial predictions do not adequately consider the spatial hierarchy among the human joints. To address this limitation, we recently introduced multi-stage spatial-temporal graph convolutional neural networks (MS-GCN). Our framework replaces the initial stage of temporal convolutions with spatial graph convolutions and dilated temporal convolutions, which better exploit the spatial configuration of the joints and their long-term temporal dynamics. Our framework was compared to four strong baselines on five tasks. Experimental results demonstrate that our framework is a strong baseline for skeleton-based action segmentation.
Hand hygiene is among the most effective daily practices for preventing infectious diseases such as influenza, malaria, and skin infections. While professional guidelines emphasize proper handwashing to reduce the risk of viral infections, surveys reveal that adherence to these recommendations remains low. To address this gap, we propose UWash, a wearable solution leveraging smartwatches to evaluate handwashing procedures, aiming to raise awareness and cultivate high-quality handwashing habits. We frame the task of handwashing assessment as an action segmentation problem, similar to those in computer vision, and introduce a simple yet efficient two-stream UNet-like network to achieve this goal. Experiments involving 51 subjects demonstrate that UWash achieves 92.27% accuracy in handwashing gesture recognition, an error of <0.5 seconds in onset/offset detection, and an error of <5 points in gesture scoring under user-dependent settings. The system also performs robustly in user-independent and user-independent-location-independent evaluations. Remarkably, UWash maintains high performance in real-world tests, including evaluations with 10 random passersby at a hospital 9 months later and 10 passersby in an in-the-wild test conducted 2 years later. UWash is the first system to score handwashing quality based on gesture sequences, offering actionable guidance for improving daily hand hygiene. The code and dataset are publicly available at https://github.com/aiotgroup/UWash
Temporal action segmentation classifies the action of each frame in (long) video sequences. Due to the high cost of frame-wise labeling, we propose the first semi-supervised method for temporal action segmentation. Our method hinges on unsupervised representation learning, which, for temporal action segmentation, poses unique challenges. Actions in untrimmed videos vary in length and have unknown labels and start/end times. Ordering of actions across videos may also vary. We propose a novel way to learn frame-wise representations from temporal convolutional networks (TCNs) by clustering input features with added time-proximity condition and multi-resolution similarity. By merging representation learning with conventional supervised learning, we develop an "Iterative-Contrast-Classify (ICC)" semi-supervised learning scheme. With more labelled data, ICC progressively improves in performance; ICC semi-supervised learning, with 40% labelled videos, performs similar to fully-supervised counterparts. Our ICC improves MoF by {+1.8, +5.6, +2.5}% on Breakfast, 50Salads and GTEA respectively for 100% labelled videos.
For human action understanding, a popular research direction is to analyze short video clips with unambiguous semantic content, such as jumping and drinking. However, methods for understanding short semantic actions cannot be directly translated to long human dynamics such as dancing, where it becomes challenging even to label the human movements semantically. Meanwhile, the natural language processing (NLP) community has made progress in solving a similar challenge of annotation scarcity by large-scale pre-training, which improves several downstream tasks with one model. In this work, we study how to segment and cluster videos into recurring temporal patterns in a self-supervised way, namely acton discovery, the main roadblock towards video tokenization. We propose a two-stage framework that first obtains a frame-wise representation by contrasting two augmented views of video frames conditioned on their temporal context. The frame-wise representations across a collection of videos are then clustered by K-means. Actons are then automatically extracted by forming a continuous motion sequence from frames within the same cluster. We evaluate the frame-wise representation learning step by Kendall's Tau and the lexicon building step by normalized mutual information and language entropy. We also study three applications of this tokenization: genre classification, action segmentation, and action composition. On the AIST++ and PKU-MMD datasets, actons bring significant performance improvements compared to several baselines.
Existing temporal action localization (TAL) works rely on a large number of training videos with exhaustive segment-level annotation, preventing them from scaling to new classes. As a solution to this problem, few-shot TAL (FS-TAL) aims to adapt a model to a new class represented by as few as a single video. Exiting FS-TAL methods assume trimmed training videos for new classes. However, this setting is not only unnatural actions are typically captured in untrimmed videos, but also ignores background video segments containing vital contextual cues for foreground action segmentation. In this work, we first propose a new FS-TAL setting by proposing to use untrimmed training videos. Further, a novel FS-TAL model is proposed which maximizes the knowledge transfer from training classes whilst enabling the model to be dynamically adapted to both the new class and each video of that class simultaneously. This is achieved by introducing a query adaptive Transformer in the model. Extensive experiments on two action localization benchmarks demonstrate that our method can outperform all the state of the art alternatives significantly in both single-domain and cross-domain scenarios. The source code can be found in https://github.com/sauradip/fewshotQAT
Algorithms for the action segmentation task typically use temporal models to predict what action is occurring at each frame for a minute-long daily activity. Recent studies have shown the potential of Transformer in modeling the relations among elements in sequential data. However, there are several major concerns when directly applying the Transformer to the action segmentation task, such as the lack of inductive biases with small training sets, the deficit in processing long input sequence, and the limitation of the decoder architecture to utilize temporal relations among multiple action segments to refine the initial predictions. To address these concerns, we design an efficient Transformer-based model for action segmentation task, named ASFormer, with three distinctive characteristics: (i) We explicitly bring in the local connectivity inductive priors because of the high locality of features. It constrains the hypothesis space within a reliable scope, and is beneficial for the action segmentation task to learn a proper target function with small training sets. (ii) We apply a pre-defined hierarchical representation pattern that efficiently handles long input sequences. (iii) We carefully design the decoder to refine the initial predictions from the encoder. Extensive experiments on three public datasets demonstrate that effectiveness of our methods. Code is available at \url{https://github.com/ChinaYi/ASFormer}.
This paper focuses on task recognition and action segmentation in weakly-labeled instructional videos, where only the ordered sequence of video-level actions is available during training. We propose a two-stream framework, which exploits semantic and temporal hierarchies to recognize top-level tasks in instructional videos. Further, we present a novel top-down weakly-supervised action segmentation approach, where the predicted task is used to constrain the inference of fine-grained action sequences. Experimental results on the popular Breakfast and Cooking 2 datasets show that our two-stream hierarchical task modeling significantly outperforms existing methods in top-level task recognition for all datasets and metrics. Additionally, using our task recognition framework in the proposed top-down action segmentation approach consistently improves the state of the art, while also reducing segmentation inference time by 80-90 percent.
We present VideoCLIP, a contrastive approach to pre-train a unified model for zero-shot video and text understanding, without using any labels on downstream tasks. VideoCLIP trains a transformer for video and text by contrasting temporally overlapping positive video-text pairs with hard negatives from nearest neighbor retrieval. Our experiments on a diverse series of downstream tasks, including sequence-level text-video retrieval, VideoQA, token-level action localization, and action segmentation reveal state-of-the-art performance, surpassing prior work, and in some cases even outperforming supervised approaches. Code is made available at https://github.com/pytorch/fairseq/tree/main/examples/MMPT.
We present a novel approach for unsupervised activity segmentation which uses video frame clustering as a pretext task and simultaneously performs representation learning and online clustering. This is in contrast with prior works where representation learning and clustering are often performed sequentially. We leverage temporal information in videos by employing temporal optimal transport. In particular, we incorporate a temporal regularization term which preserves the temporal order of the activity into the standard optimal transport module for computing pseudo-label cluster assignments. The temporal optimal transport module enables our approach to learn effective representations for unsupervised activity segmentation. Furthermore, previous methods require storing learned features for the entire dataset before clustering them in an offline manner, whereas our approach processes one mini-batch at a time in an online manner. Extensive evaluations on three public datasets, i.e. 50-Salads, YouTube Instructions, and Breakfast, and our dataset, i.e., Desktop Assembly, show that our approach performs on par with or better than previous methods, despite having significantly less memory constraints. Our code and dataset are available on our research website: https://retrocausal.ai/research/
Temporal convolutional networks (TCNs) are a commonly used architecture for temporal video segmentation. TCNs however, tend to suffer from over-segmentation errors and require additional refinement modules to ensure smoothness and temporal coherency. In this work, we propose a novel temporal encoder-decoder to tackle the problem of sequence fragmentation. In particular, the decoder follows a coarse-to-fine structure with an implicit ensemble of multiple temporal resolutions. The ensembling produces smoother segmentations that are more accurate and better-calibrated, bypassing the need for additional refinement modules. In addition, we enhance our training with a multi-resolution feature-augmentation strategy to promote robustness to varying temporal resolutions. Finally, to support our architecture and encourage further sequence coherency, we propose an action loss that penalizes misclassifications at the video level. Experiments show that our stand-alone architecture, together with our novel feature-augmentation strategy and new loss, outperforms the state-of-the-art on three temporal video segmentation benchmarks.
We present a simplified, task-agnostic multi-modal pre-training approach that can accept either video or text input, or both for a variety of end tasks. Existing pre-training are task-specific by adopting either a single cross-modal encoder that requires both modalities, limiting their use for retrieval-style end tasks or more complex multitask learning with two unimodal encoders, limiting early cross-modal fusion. We instead introduce new pretraining masking schemes that better mix across modalities (e.g. by forcing masks for text to predict the closest video embeddings) while also maintaining separability (e.g. unimodal predictions are sometimes required, without using all the input). Experimental results show strong performance across a wider range of tasks than any previous methods, often outperforming task-specific pre-training. Code is made available at https://github.com/pytorch/fairseq/tree/main/examples/MMPT.
Freezing of gait (FOG) is a common and debilitating gait impairment in Parkinson's disease. Further insight into this phenomenon is hampered by the difficulty to objectively assess FOG. To meet this clinical need, this paper proposes an automated motion-capture-based FOG assessment method driven by a novel deep neural network. Automated FOG assessment can be formulated as an action segmentation problem, where temporal models are tasked to recognize and temporally localize the FOG segments in untrimmed motion capture trials. This paper takes a closer look at the performance of state-of-the-art action segmentation models when tasked to automatically assess FOG. Furthermore, a novel deep neural network architecture is proposed that aims to better capture the spatial and temporal dependencies than the state-of-the-art baselines. The proposed network, termed multi-stage spatial-temporal graph convolutional network (MS-GCN), combines the spatial-temporal graph convolutional network (ST-GCN) and the multi-stage temporal convolutional network (MS-TCN). The ST-GCN captures the hierarchical spatial-temporal motion among the joints inherent to motion capture, while the multi-stage component reduces over-segmentation errors by refining the predictions over multiple stages. The experiments indicate that the proposed model outperforms four state-of-the-art baselines. Moreover, FOG outcomes derived from MS-GCN predictions had an excellent (r=0.93 [0.87, 0.97]) and moderately strong (r=0.75 [0.55, 0.87]) linear relationship with FOG outcomes derived from manual annotations. The proposed MS-GCN may provide an automated and objective alternative to labor-intensive clinician-based FOG assessment. Future work is now possible that aims to assess the generalization of MS-GCN to a larger and more varied verification cohort.
Action segmentation refers to inferring boundaries of semantically consistent visual concepts in videos and is an important requirement for many video understanding tasks. For this and other video understanding tasks, supervised approaches have achieved encouraging performance but require a high volume of detailed frame-level annotations. We present a fully automatic and unsupervised approach for segmenting actions in a video that does not require any training. Our proposal is an effective temporally-weighted hierarchical clustering algorithm that can group semantically consistent frames of the video. Our main finding is that representing a video with a 1-nearest neighbor graph by taking into account the time progression is sufficient to form semantically and temporally consistent clusters of frames where each cluster may represent some action in the video. Additionally, we establish strong unsupervised baselines for action segmentation and show significant performance improvements over published unsupervised methods on five challenging action segmentation datasets. Our code is available at https://github.com/ssarfraz/FINCH-Clustering/tree/master/TW-FINCH
Dynamic Time Warping (DTW) is widely used for temporal data processing. However, existing methods can neither learn the discriminative prototypes of different classes nor exploit such prototypes for further analysis. We propose Discriminative Prototype DTW (DP-DTW), a novel method to learn class-specific discriminative prototypes for temporal recognition tasks. DP-DTW shows superior performance compared to conventional DTWs on time series classification benchmarks. Combined with end-to-end deep learning, DP-DTW can handle challenging weakly supervised action segmentation problems and achieves state of the art results on standard benchmarks. Moreover, detailed reasoning on the input video is enabled by the learned action prototypes. Specifically, an action-based video summarization can be obtained by aligning the input sequence with action prototypes.
Temporal action segmentation approaches have been very successful recently. However, annotating videos with frame-wise labels to train such models is very expensive and time consuming. While weakly supervised methods trained using only ordered action lists require less annotation effort, the performance is still worse than fully supervised approaches. In this paper, we propose to use timestamp supervision for the temporal action segmentation task. Timestamps require a comparable annotation effort to weakly supervised approaches, and yet provide a more supervisory signal. To demonstrate the effectiveness of timestamp supervision, we propose an approach to train a segmentation model using only timestamps annotations. Our approach uses the model output and the annotated timestamps to generate frame-wise labels by detecting the action changes. We further introduce a confidence loss that forces the predicted probabilities to monotonically decrease as the distance to the timestamps increases. This ensures that all and not only the most distinctive frames of an action are learned during training. The evaluation on four datasets shows that models trained with timestamps annotations achieve comparable performance to the fully supervised approaches.
Temporal receptive fields of models play an important role in action segmentation. Large receptive fields facilitate the long-term relations among video clips while small receptive fields help capture the local details. Existing methods construct models with hand-designed receptive fields in layers. Can we effectively search for receptive field combinations to replace hand-designed patterns? To answer this question, we propose to find better receptive field combinations through a global-to-local search scheme. Our search scheme exploits both global search to find the coarse combinations and local search to get the refined receptive field combination patterns further. The global search finds possible coarse combinations other than human-designed patterns. On top of the global search, we propose an expectation guided iterative local search scheme to refine combinations effectively. Our global-to-local search can be plugged into existing action segmentation methods to achieve state-of-the-art performance.
Temporal relational modeling in video is essential for human action understanding, such as action recognition and action segmentation. Although Graph Convolution Networks (GCNs) have shown promising advantages in relation reasoning on many tasks, it is still a challenge to apply graph convolution networks on long video sequences effectively. The main reason is that large number of nodes (i.e., video frames) makes GCNs hard to capture and model temporal relations in videos. To tackle this problem, in this paper, we introduce an effective GCN module, Dilated Temporal Graph Reasoning Module (DTGRM), designed to model temporal relations and dependencies between video frames at various time spans. In particular, we capture and model temporal relations via constructing multi-level dilated temporal graphs where the nodes represent frames from different moments in video. Moreover, to enhance temporal reasoning ability of the proposed model, an auxiliary self-supervised task is proposed to encourage the dilated temporal graph reasoning module to find and correct wrong temporal relations in videos. Our DTGRM model outperforms state-of-the-art action segmentation models on three challenging datasets: 50Salads, Georgia Tech Egocentric Activities (GTEA), and the Breakfast dataset. The code is available at https://github.com/redwang/DTGRM.
Automated airway segmentation is a prerequisite for pre-operative diagnosis and intra-operative navigation for pulmonary intervention. Due to the small size and scattered spatial distribution of peripheral bronchi, this is hampered by severe class imbalance between foreground and background regions, which makes it challenging for CNN-based methods to parse distal small airways. In this paper, we demonstrate that this problem is arisen by gradient erosion and dilation of the neighborhood voxels. During back-propagation, if the ratio of the foreground gradient to background gradient is small while the class imbalance is local, the foreground gradients can be eroded by their neighborhoods. This process cumulatively increases the noise information included in the gradient flow from top layers to the bottom ones, limiting the learning of small structures in CNNs. To alleviate this problem, we use group supervision and the corresponding WingsNet to provide complementary gradient flows to enhance the training of shallow layers. To further address the intra-class imbalance between large and small airways, we design a General Union loss function which obviates the impact of airway size by distance-based weights and adaptively tunes the gradient ratio based on the learning process. Extensive experiments on public datasets demonstrate that the proposed method can predict the airway structures with higher accuracy and better morphological completeness than the baselines.
In this paper, we introduce ActBERT for self-supervised learning of joint video-text representations from unlabeled data. First, we leverage global action information to catalyze the mutual interactions between linguistic texts and local regional objects. It uncovers global and local visual clues from paired video sequences and text descriptions for detailed visual and text relation modeling. Second, we introduce an ENtangled Transformer block (ENT) to encode three sources of information, i.e., global actions, local regional objects, and linguistic descriptions. Global-local correspondences are discovered via judicious clues extraction from contextual information. It enforces the joint videotext representation to be aware of fine-grained objects as well as global human intention. We validate the generalization capability of ActBERT on downstream video-and language tasks, i.e., text-video clip retrieval, video captioning, video question answering, action segmentation, and action step localization. ActBERT significantly outperforms the state-of-the-arts, demonstrating its superiority in video-text representation learning.