LAC - Latent Action Composition for Skeleton-based Action Segmentation - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2023

LAC - Latent Action Composition for Skeleton-based Action Segmentation

Abstract

Skeleton-based action segmentation requires recognizing composable actions in untrimmed videos. Current approaches decouple this problem by first extracting local visual features from skeleton sequences and then processing them by a temporal model to classify frame-wise actions. However, their performances remain limited as the visual features cannot sufficiently express composable actions. In this context, we propose Latent Action Composition (LAC) 1 , a novel self-supervised framework aiming at learning from synthesized composable motions for skeleton-based action segmentation. LAC is composed of a novel generation module towards synthesizing new sequences. Specifically, we design a linear latent space in the generator to represent primitive motion. New composed motions can be synthesized by simply performing arithmetic operations on latent representations of multiple input skeleton sequences. LAC leverages such synthesized sequences, which have large diversity and complexity, for learning visual representations of skeletons in both sequence and frame spaces via contrastive learning. The resulting visual encoder has a high expressive power and can be effectively transferred onto action segmentation tasks by end-to-end fine-tuning without the need for additional temporal models. We conduct a study focusing on transfer-learning and we show that representations learned from pre-trained LAC outperform the state-of-the-art by a large margin on TSU, Charades, PKU-MMD datasets.
Fichier principal
Vignette du fichier
LAC_Yang.pdf (9.43 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04236097 , version 1 (10-10-2023)
hal-04236097 , version 2 (21-02-2024)

Identifiers

Cite

Di Yang, Yaohui Wang, Antitza Dantcheva, Quan Kong, Lorenzo Garattoni, et al.. LAC - Latent Action Composition for Skeleton-based Action Segmentation. ICCV 2023 - IEEE/CVF International Conference on Computer Vision, Oct 2023, Paris, France. ⟨hal-04236097v2⟩
30 View
13 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More