Recovering Complete Actions for Cross-dataset Skeleton Action Recognition

• URL: http://arxiv.org/abs/2410.23641v1
• Date: Thu, 31 Oct 2024 05:27:58 GMT
• Title: Recovering Complete Actions for Cross-dataset Skeleton Action Recognition
• Authors: Hanchao Liu, Yujiang Li, Tai-Jiang Mu, Shi-Min Hu,
• Abstract summary: We present a recover-and-resample augmentation framework based on a novel complete action prior. By recovering complete actions and resampling from these full sequences, we can generate strong augmentations for unseen domains. We validate our approach on a cross-dataset setting with three skeleton action datasets.
• Score: 25.276593723734727
• License:
• Abstract: Despite huge progress in skeleton-based action recognition, its generalizability to different domains remains a challenging issue. In this paper, to solve the skeleton action generalization problem, we present a recover-and-resample augmentation framework based on a novel complete action prior. We observe that human daily actions are confronted with temporal mismatch across different datasets, as they are usually partial observations of their complete action sequences. By recovering complete actions and resampling from these full sequences, we can generate strong augmentations for unseen domains. At the same time, we discover the nature of general action completeness within large datasets, indicated by the per-frame diversity over time. This allows us to exploit two assets of transferable knowledge that can be shared across action samples and be helpful for action completion: boundary poses for determining the action start, and linear temporal transforms for capturing global action patterns. Therefore, we formulate the recovering stage as a two-step stochastic action completion with boundary pose-conditioned extrapolation followed by smooth linear transforms. Both the boundary poses and linear transforms can be efficiently learned from the whole dataset via clustering. We validate our approach on a cross-dataset setting with three skeleton action datasets, outperforming other domain generalization approaches by a considerable margin.

Related papers

• FCA-RAC: First Cycle Annotated Repetitive Action Counting [30.253568218869237]
  We propose a framework called First Cycle Annotated Repetitive Action Counting (FCA-RAC) FCA-RAC contains 4 parts: 1) a labeling technique that annotates each training video with the start and end of the first action cycle, along with the total action count. This technique enables the model to capture the correlation between the initial action cycle and subsequent actions.
  arXiv  Detail & Related papers  (2024-06-18T01:12:43Z)
• SkelFormer: Markerless 3D Pose and Shape Estimation using Skeletal Transformers [57.46911575980854]
  We introduce SkelFormer, a novel markerless motion capture pipeline for multi-view human pose and shape estimation. Our method first uses off-the-shelf 2D keypoint estimators, pre-trained on large-scale in-the-wild data, to obtain 3D joint positions. Next, we design a regression-based inverse-kinematic skeletal transformer that maps the joint positions to pose and shape representations from heavily noisy observations.
  arXiv  Detail & Related papers  (2024-04-19T04:51:18Z)
• STARFlow: Spatial Temporal Feature Re-embedding with Attentive Learning for Real-world Scene Flow [6.155589434533128]
  We propose global attentive flow embedding to match all-to-all point pairs in both Euclidean space. We leverage novel domain adaptive losses to bridge the gap of motion inference from synthetic to real-world. Our approach achieves state-of-the-art performance across various datasets, with particularly outstanding results on real-world LiDAR-scanned datasets.
  arXiv  Detail & Related papers  (2024-03-11T04:56:10Z)
• Navigating Open Set Scenarios for Skeleton-based Action Recognition [45.488649741347]
  We tackle the unexplored Open-Set Skeleton-based Action Recognition (OS-SAR) task. We propose a distance-based cross-modality method that leverages the cross-modal alignment of skeleton joints, bones, and velocities.
  arXiv  Detail & Related papers  (2023-12-11T12:29:32Z)
• SkeleTR: Towrads Skeleton-based Action Recognition in the Wild [86.03082891242698]
  SkeleTR is a new framework for skeleton-based action recognition. It first models the intra-person skeleton dynamics for each skeleton sequence with graph convolutions. It then uses stacked Transformer encoders to capture person interactions that are important for action recognition in general scenarios.
  arXiv  Detail & Related papers  (2023-09-20T16:22:33Z)
• DIR-AS: Decoupling Individual Identification and Temporal Reasoning for Action Segmentation [84.78383981697377]
  Fully supervised action segmentation works on frame-wise action recognition with dense annotations and often suffers from the over-segmentation issue. We develop a novel local-global attention mechanism with temporal pyramid dilation and temporal pyramid pooling for efficient multi-scale attention. We achieve state-of-the-art accuracy, eg, 82.8% (+2.6%) on GTEA and 74.7% (+1.2%) on Breakfast, which demonstrates the effectiveness of our proposed method.
  arXiv  Detail & Related papers  (2023-04-04T20:27:18Z)
• Multi-dataset Training of Transformers for Robust Action Recognition [75.5695991766902]
  We study the task of robust feature representations, aiming to generalize well on multiple datasets for action recognition. Here, we propose a novel multi-dataset training paradigm, MultiTrain, with the design of two new loss terms, namely informative loss and projection loss. We verify the effectiveness of our method on five challenging datasets, Kinetics-400, Kinetics-700, Moments-in-Time, Activitynet and Something-something-v2.
  arXiv  Detail & Related papers  (2022-09-26T01:30:43Z)
• Learning from Temporal Spatial Cubism for Cross-Dataset Skeleton-based Action Recognition [88.34182299496074]
  Action labels are only available on a source dataset, but unavailable on a target dataset in the training stage. We utilize a self-supervision scheme to reduce the domain shift between two skeleton-based action datasets. By segmenting and permuting temporal segments or human body parts, we design two self-supervised learning classification tasks.
  arXiv  Detail & Related papers  (2022-07-17T07:05:39Z)
• Unsupervised Action Segmentation with Self-supervised Feature Learning and Co-occurrence Parsing [32.66011849112014]
  temporal action segmentation is a task to classify each frame in the video with an action label. In this work we explore a self-supervised method that operates on a corpus of unlabeled videos and predicts a likely set of temporal segments across the videos. We develop CAP, a novel co-occurrence action parsing algorithm that can not only capture the correlation among sub-actions underlying the structure of activities, but also estimate the temporal trajectory of the sub-actions in an accurate and general way.
  arXiv  Detail & Related papers  (2021-05-29T00:29:40Z)
• MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation [87.16030562892537]
  We propose a multi-stage architecture for the temporal action segmentation task. The first stage generates an initial prediction that is refined by the next ones. Our models achieve state-of-the-art results on three datasets.
  arXiv  Detail & Related papers  (2020-06-16T14:50:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.