English
Related papers

Related papers: BABEL: Bodies, Action and Behavior with English La…

200 papers

We tackle the problem of generating long-term 3D human motion from multiple action labels. Two main previous approaches, such as action- and motion-conditioned methods, have limitations to solve this problem. The action-conditioned methods…

Computer Vision and Pattern Recognition · Computer Science 2023-02-20 Taeryung Lee , Gyeongsik Moon , Kyoung Mu Lee

Anticipating human motion depends on two factors: the past motion and the person's intention. While the first factor has been extensively utilized to forecast short sequences of human motion, the second one remains elusive. In this work we…

Computer Vision and Pattern Recognition · Computer Science 2019-12-16 Julian Tanke , Andreas Weber , Juergen Gall

Isolated facial movements, so-called Action Units, can describe combined emotions or physical states such as pain. As datasets are limited and mostly imbalanced, we present an approach incorporating a multi-label class balancing algorithm.…

Computer Vision and Pattern Recognition · Computer Science 2020-02-11 Jaspar Pahl , Ines Rieger , Dominik Seuss

We introduce MABe22, a large-scale, multi-agent video and trajectory benchmark to assess the quality of learned behavior representations. This dataset is collected from a variety of biology experiments, and includes triplets of interacting…

We present the Moments in Time Dataset, a large-scale human-annotated collection of one million short videos corresponding to dynamic events unfolding within three seconds. Modeling the spatial-audio-temporal dynamics even for actions…

Computer Vision and Pattern Recognition · Computer Science 2019-02-19 Mathew Monfort , Alex Andonian , Bolei Zhou , Kandan Ramakrishnan , Sarah Adel Bargal , Tom Yan , Lisa Brown , Quanfu Fan , Dan Gutfruend , Carl Vondrick , Aude Oliva

In competitive combat sports like boxing, analyzing a boxers's performance statics is crucial for evaluating the quantity and variety of punches delivered during bouts. These statistics provide valuable data and feedback, which are…

Computer Vision and Pattern Recognition · Computer Science 2025-02-18 Shashikanta Sahoo

This paper introduces a video dataset of spatio-temporally localized Atomic Visual Actions (AVA). The AVA dataset densely annotates 80 atomic visual actions in 430 15-minute video clips, where actions are localized in space and time,…

The canonical approach to video action recognition dictates a neural model to do a classic and standard 1-of-N majority vote task. They are trained to predict a fixed set of predefined categories, limiting their transferable ability on new…

Computer Vision and Pattern Recognition · Computer Science 2021-09-20 Mengmeng Wang , Jiazheng Xing , Yong Liu

Understanding human activity is a crucial yet intricate task in egocentric vision, a field that focuses on capturing visual perspectives from the camera wearer's viewpoint. Traditional methods heavily rely on representation learning that is…

Computer Vision and Pattern Recognition · Computer Science 2024-07-19 Sanghwan Kim , Daoji Huang , Yongqin Xian , Otmar Hilliges , Luc Van Gool , Xi Wang

Learning robot policies using imitation learning requires collecting large amounts of costly action-labeled expert demonstrations, which fundamentally limits the scale of training data. A promising approach to address this bottleneck is to…

Robotics · Computer Science 2025-05-12 Anthony Liang , Pavel Czempin , Matthew Hong , Yutai Zhou , Erdem Biyik , Stephen Tu

In this paper, we present Motion-X, a large-scale 3D expressive whole-body motion dataset. Existing motion datasets predominantly contain body-only poses, lacking facial expressions, hand gestures, and fine-grained pose descriptions.…

Computer Vision and Pattern Recognition · Computer Science 2024-01-29 Jing Lin , Ailing Zeng , Shunlin Lu , Yuanhao Cai , Ruimao Zhang , Haoqian Wang , Lei Zhang

Recent advances in 3D human motion and language integration have primarily focused on text-to-motion generation, leaving the task of motion understanding relatively unexplored. We introduce Dense Motion Captioning, a novel task that aims to…

Computer Vision and Pattern Recognition · Computer Science 2025-11-10 Shiyao Xu , Benedetta Liberatori , Gül Varol , Paolo Rota

Understanding human actions from body poses is critical for assistive robots sharing space with humans in order to make informed and safe decisions about the next interaction. However, precise temporal localization and annotation of…

Computer Vision and Pattern Recognition · Computer Science 2024-08-07 Yi Xu , Kunyu Peng , Di Wen , Ruiping Liu , Junwei Zheng , Yufan Chen , Jiaming Zhang , Alina Roitberg , Kailun Yang , Rainer Stiefelhagen

Action Detection is a complex task that aims to detect and classify human actions in video clips. Typically, it has been addressed by processing fine-grained features extracted from a video classification backbone. Recently, thanks to the…

Computer Vision and Pattern Recognition · Computer Science 2021-03-02 Matteo Tomei , Lorenzo Baraldi , Simone Calderara , Simone Bronzin , Rita Cucchiara

Large Language Models (LLMs) have demonstrated remarkable capabilities in various domains, including data augmentation and synthetic data generation. This work explores the use of LLMs to generate rich textual descriptions for motion…

Computer Vision and Pattern Recognition · Computer Science 2024-04-19 Radu Chivereanu , Adrian Cosma , Andy Catruna , Razvan Rughinis , Emilian Radoi

Current fully-supervised video datasets consist of only a few hundred thousand videos and fewer than a thousand domain-specific labels. This hinders the progress towards advanced video architectures. This paper presents an in-depth study of…

Computer Vision and Pattern Recognition · Computer Science 2019-05-03 Deepti Ghadiyaram , Matt Feiszli , Du Tran , Xueting Yan , Heng Wang , Dhruv Mahajan

Robotic deployment in real-world environments depends on rich, domain-specific action data as much as on strong model architecture. General-purpose robot foundation models show modest performance in complex unseen tasks such as manipulation…

Active learning (AL) seeks to reduce annotation costs by selecting the most informative samples for labeling, making it particularly valuable in resource-constrained settings. However, traditional evaluation methods, which focus solely on…

Machine Learning · Computer Science 2025-07-22 Julia Machnio , Mads Nielsen , Mostafa Mehdipour Ghazi

Humans constantly interact with daily objects to accomplish tasks. To understand such interactions, computers need to reconstruct these from cameras observing whole-body interaction with scenes. This is challenging due to occlusion between…

Computer Vision and Pattern Recognition · Computer Science 2022-10-04 Yinghao Huang , Omid Tehari , Michael J. Black , Dimitrios Tzionas

We address the problem of accurate capture of interactive behaviors between two people in daily scenarios. Most previous works either only consider one person or solely focus on conversational gestures of two people, assuming the body…

Computer Vision and Pattern Recognition · Computer Science 2025-09-09 Leo Ho , Yinghao Huang , Dafei Qin , Mingyi Shi , Wangpok Tse , Wei Liu , Junichi Yamagishi , Taku Komura