paper-with-me

홈 › Papers

Free-Form Composition Networks for Egocentric Action Recognition

2023-07-13 · Haoran Wang, Qinghua Cheng, Baosheng Yu, Yibing Zhan, Dapeng Tao, Liang Ding, Haibin Ling

Egocentric action recognition is gaining significant attention in the field of human action recognition. In this paper, we address data scarcity issue in egocentric action recognition from a compositional generalization perspective. To tackle this problem, we propose a free-form composition network (FFCN) that can simultaneously learn disentangled verb, preposition, and noun representations, and then use them to compose new samples in the feature space for rare classes of action videos. First, we use a graph to capture the spatial-temporal relations among different hand/object instances in each action video. We thus decompose each action into a set of verb and preposition spatial-temporal representations using the edge features in the graph. The temporal decomposition extracts verb and preposition representations from different video frames, while the spatial decomposition adaptively learns verb and preposition representations from action-related instances in each frame. With these spatial-temporal representations of verbs and prepositions, we can compose new samples for those rare classes in a free-form manner, which is not restricted to a rigid form of a verb and a noun. The proposed FFCN can directly generate new training data samples for rare classes, hence significantly improve action recognition performance. We evaluated our method on three popular egocentric action recognition datasets, Something-Something V2, H2O, and EPIC-KITCHENS-100, and the experimental results demonstrate the effectiveness of the proposed method for handling data scarcity problems, including long-tailed and few-shot egocentric action recognition.

📄 PDF Abstract BibTeX arXiv:2307.06527

Code (0)

등록된 구현이 없습니다.

Tasks

Action RecognitionFormTemporal Action Localization

Similar Papers 제목 키워드 기반

Collaborative Learning for 3D Hand-Object Reconstruction and Compositional Action Recognition from Egocentric RGB Videos Using Superquadrics

2025-01-13 · Tze Ho Elden Tse, Runyang Feng, Linfang Zheng, Jiho Park 외

With the availability of egocentric 3D hand-object interaction datasets, there is increasing interest in developing unified models for hand-object pose estimation and action recognition. However, existing methods still s…

Action Recognitionhand-object poseObjectObject Reconstruction+1

Opening the Vocabulary of Egocentric Actions

2023-08-22 · NeurIPS 2023 11 · Dibyadip Chatterjee, Fadime Sener, Shugao Ma, Angela Yao

Human actions in egocentric videos are often hand-object interactions composed from a verb (performed by the hand) applied to an object. Despite their extensive scaling up, egocentric datasets still face two limitations …

Action RecognitionObjectOpen Vocabulary Action Recognition

Knowledge Guided Learning: Towards Open Domain Egocentric Action Recognition with Zero Supervision

2020-09-16 · Sathyanarayanan N. Aakur, Sanjoy Kundu, Nikhil Gunti

Advances in deep learning have enabled the development of models that have exhibited a remarkable tendency to recognize and even localize actions in videos. However, they tend to experience errors when faced with scenes …

Action RecognitionDomain AdaptationNovel Object Detectionobject-detection+2

Unifying Few- and Zero-Shot Egocentric Action Recognition

2020-05-27 · Scott Tyler R., Shvartsman Michael, Ridgeway Karl

Although there has been significant research in egocentric action recognition, most methods and tasks, including EPIC-KITCHENS, suppose a fixed set of action classes. Fixed-set classification is useful for benchmarking m…

Action RecognitionBenchmarkingClassificationGeneral Classification+5

Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applications

2022-08-07 · Lingzhi Zhang, Shenghao Zhou, Simon Stent, Jianbo Shi

Egocentric videos offer fine-grained information for high-fidelity modeling of human behaviors. Hands and interacting objects are one crucial aspect of understanding a viewer's behaviors and intentions. We provide a labe…

Activity RecognitionData AugmentationObjectSegmentation+2