Object Priors For Classifying And Localizing Unseen Actions
2021 · Pascal Mettes, William Thong, Cees G. M. Snoek
Abstract
This work strives for the classification and localization of human actions in videos, without the need for any labeled video training examples. Where existing work relies on transferring global attribute or object information from seen to unseen action videos, we seek to classify and spatio-temporally localize unseen actions in videos from image-based object information only. We propose three spatial object priors, which encode local person and object detectors along with their spatial relations. On top we introduce three semantic object priors, which extend semantic matching through word embeddings with three simple functions that tackle semantic ambiguity, object discrimination, and object naming. A video embedding combines the spatial and semantic object priors. It enables us to introduce a new video retrieval task that retrieves action tubes in video collections based on user-specified objects, spatial relations, and object size. Experimental evaluation on five action datasets show
Authors
(none)
Tags
Stats
Related papers
- Object-centric Framework For Video Moment Retrieval (2025)0.00
- Object-aware Video-language Pre-training For Retrieval (2021)16.14
- Search Tracker: Human-derived Object Tracking In-the-wild Through Large-scale Search And Retrieval (2016)5.24
- Helping Hands: An Object-aware Ego-centric Video Recognition Model (2023)10.07
- Fine-grained Action Retrieval Through Multiple Parts-of-speech Embeddings (2019)15.62
- Fusing Local Similarities For Retrieval-based 3D Orientation Estimation Of Unseen Objects (2022)10.07
- Visual Relationship Detection With Language Priors (2016)20.75
- Object-centric Representation Learning From Unlabeled Videos (2016)7.16