A Cross-Dataset Study for Text-based 3D Human Motion Retrieval

• URL: http://arxiv.org/abs/2405.16909v1
• Date: Mon, 27 May 2024 07:58:20 GMT
• Title: A Cross-Dataset Study for Text-based 3D Human Motion Retrieval
• Authors: Léore Bensabath, Mathis Petrovich, Gül Varol,
• Abstract summary: We employ a unified SMPL body format for all datasets, which allows us to perform training on one dataset, testing on the other, as well as training on a combination of datasets. Our results suggest that there exist dataset biases in standard text-motion benchmarks such as HumanML3D, KIT Motion-Language, and BABEL.
• Score: 13.673377919543228
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We provide results of our study on text-based 3D human motion retrieval and particularly focus on cross-dataset generalization. Due to practical reasons such as dataset-specific human body representations, existing works typically benchmarkby training and testing on partitions from the same dataset. Here, we employ a unified SMPL body format for all datasets, which allows us to perform training on one dataset, testing on the other, as well as training on a combination of datasets. Our results suggest that there exist dataset biases in standard text-motion benchmarks such as HumanML3D, KIT Motion-Language, and BABEL. We show that text augmentations help close the domain gap to some extent, but the gap remains. We further provide the first zero-shot action recognition results on BABEL, without using categorical action labels during training, opening up a new avenue for future research.

Related papers

• Joint-Dataset Learning and Cross-Consistent Regularization for Text-to-Motion Retrieval [4.454835029368504]
  We focus on the recently introduced text-motion retrieval which aim to search for sequences that are most relevant to a natural motion description. Despite recent efforts to explore these promising avenues, a primary challenge remains the insufficient data available to train robust text-motion models. We propose to investigate joint-dataset learning - where we train on multiple text-motion datasets simultaneously. We also introduce a transformer-based motion encoder, called MoT++, which employs the specified-temporal attention to process sequences of skeleton data.
  arXiv  Detail & Related papers  (2024-07-02T09:43:47Z)
• The Pursuit of Human Labeling: A New Perspective on Unsupervised Learning [6.17147517649596]
  We present HUME, a model-agnostic framework for inferring human labeling of a given dataset without any external supervision. HUME utilizes this insight to guide the search over all possible labelings of a dataset to discover an underlying human labeling. We show that the proposed optimization objective is strikingly well-correlated with the ground truth labeling of the dataset.
  arXiv  Detail & Related papers  (2023-11-06T08:16:41Z)
• MDT3D: Multi-Dataset Training for LiDAR 3D Object Detection Generalization [3.8243923744440926]
  3D object detection models trained on a source dataset with a specific point distribution have shown difficulties in generalizing to unseen datasets. We leverage the information available from several annotated source datasets with our Multi-Dataset Training for 3D Object Detection (MDT3D) method. We show how we managed the mix of datasets during training and finally introduce a new cross-dataset augmentation method: cross-dataset object injection.
  arXiv  Detail & Related papers  (2023-08-02T08:20:00Z)
• Navya3DSeg -- Navya 3D Semantic Segmentation Dataset & split generation for autonomous vehicles [63.20765930558542]
  3D semantic data are useful for core perception tasks such as obstacle detection and ego-vehicle localization. We propose a new dataset, Navya 3D (Navya3DSeg), with a diverse label space corresponding to a large scale production grade operational domain. It contains 23 labeled sequences and 25 supplementary sequences without labels, designed to explore self-supervised and semi-supervised semantic segmentation benchmarks on point clouds.
  arXiv  Detail & Related papers  (2023-02-16T13:41:19Z)
• Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formats [80.12253291709673]
  We propose a novel affine-combining autoencoder (ACAE) method to perform dimensionality reduction on the number of landmarks. Our approach scales to an extreme multi-dataset regime, where we use 28 3D human pose datasets to supervise one model.
  arXiv  Detail & Related papers  (2022-12-29T22:22:49Z)
• Video-based Pose-Estimation Data as Source for Transfer Learning in Human Activity Recognition [71.91734471596433]
  Human Activity Recognition (HAR) using on-body devices identifies specific human actions in unconstrained environments. Previous works demonstrated that transfer learning is a good strategy for addressing scenarios with scarce data. This paper proposes using datasets intended for human-pose estimation as a source for transfer learning.
  arXiv  Detail & Related papers  (2022-12-02T18:19:36Z)
• A Novel Dataset for Evaluating and Alleviating Domain Shift for Human Detection in Agricultural Fields [59.035813796601055]
  We evaluate the impact of domain shift on human detection models trained on well known object detection datasets when deployed on data outside the distribution of the training set. We introduce the OpenDR Humans in Field dataset, collected in the context of agricultural robotics applications, using the Robotti platform.
  arXiv  Detail & Related papers  (2022-09-27T07:04:28Z)
• 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)
• Omni-supervised Facial Expression Recognition via Distilled Data [120.11782405714234]
  We propose omni-supervised learning to exploit reliable samples in a large amount of unlabeled data for network training. We experimentally verify that the new dataset can significantly improve the ability of the learned FER model. To tackle this, we propose to apply a dataset distillation strategy to compress the created dataset into several informative class-wise images.
  arXiv  Detail & Related papers  (2020-05-18T09:36:51Z)

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.