Related papers: Action-slot: Visual Action-centric Representations…
In this paper, we introduce a new hierarchical model for human action recognition using body joint locations. Our model can categorize complex actions in videos, and perform spatio-temporal annotations of the atomic actions that compose the…
The goal of this paper is to recognize actions in video without the need for examples. Different from traditional zero-shot approaches we do not demand the design and specification of attribute classifiers and class-to-attribute mappings to…
Weakly-supervised Temporal Action Localization (WS-TAL) methods learn to localize temporal starts and ends of action instances in a video under only video-level supervision. Existing WS-TAL methods rely on deep features learned for action…
Precise action spotting has attracted considerable attention due to its promising applications. While existing methods achieve substantial performance by employing well-designed model architecture, they overlook a significant challenge: the…
One-shot action recognition aims to recognize new action categories from a single reference example, typically referred to as the anchor example. This work presents a novel approach for one-shot action recognition in the wild that computes…
Spatio-temporal action detection is an important and challenging problem in video understanding. However, the application of the existing large-scale spatio-temporal action datasets in specific fields is limited, and there is currently no…
While imitation learning has shown impressive results in single-task robot manipulation, scaling it to multi-task settings remains a fundamental challenge due to issues such as suboptimal demonstrations, trajectory noise, and behavioral…
Machine learning models of visual action recognition are typically trained and tested on data from specific situations where actions are associated with certain objects. It is an open question how action-object associations in the training…
Object-centric representation learning aims to decompose visual scenes into fixed-size vectors called "slots" or "object files", where each slot captures a distinct object. Current state-of-the-art object-centric models have shown…
Action recognition has typically treated actions and activities as monolithic events that occur in videos. However, there is evidence from Cognitive Science and Neuroscience that people actively encode activities into consistent…
We present a system for concurrent activity recognition. To extract features associated with different activities, we propose a feature-to-activity attention that maps the extracted global features to sub-features associated with individual…
Zero-Shot Learning (ZSL) promises to scale visual recognition by bypassing the conventional model training requirement of annotated examples for every category. This is achieved by establishing a mapping connecting low-level features and a…
Localizing actions in video is a core task in computer vision. The weakly supervised temporal localization problem investigates whether this task can be adequately solved with only video-level labels, significantly reducing the amount of…
Action recognition is an important problem in multimedia understanding. This paper addresses this problem by building an expressive compositional action model. We model one action instance in the video with an ensemble of spatio-temporal…
Robustness to domain changes is a key capability for effective deployment of human action recognition systems in real-world scenarios, where action categories at inference can present important domain shifts or even unseen actions from…
Learning an egocentric action recognition model from video data is challenging due to distractors (e.g., irrelevant objects) in the background. Further integrating object information into an action model is hence beneficial. Existing…
Temporal Activity Detection aims to predict activity classes per frame, in contrast to video-level predictions in Activity Classification (i.e., Activity Recognition). Due to the expensive frame-level annotations required for detection, the…
Manual spatio-temporal annotation of human action in videos is laborious, requires several annotators and contains human biases. In this paper, we present a weakly supervised approach to automatically obtain spatio-temporal annotations of…
Multi-task learning is central to many real-world applications. Unfortunately, obtaining labelled data for all tasks is time-consuming, challenging, and expensive. Active Learning (AL) can be used to reduce this burden. Existing techniques…
Action classification in still images has been a popular research topic in computer vision. Labelling large scale datasets for action classification requires tremendous manual work, which is hard to scale up. Besides, the action categories…