Related papers: Actor-centered Representations for Action Localiza…
The problem of action recognition involves locating the action in the video, both over time and spatially in the image. The dominant current approaches use supervised learning to solve this problem, and require large amounts of annotated…
This paper addresses the problem of spatiotemporal localization of actions in videos. Compared to leading approaches, which all learn to localize based on carefully annotated boxes on training video frames, we adhere to a weakly-supervised…
Devising intelligent agents able to live in an environment and learn by observing the surroundings is a longstanding goal of Artificial Intelligence. From a bare Machine Learning perspective, challenges arise when the agent is prevented…
Recognising human activities from streaming videos poses unique challenges to learning algorithms: predictive models need to be scalable, incrementally trainable, and must remain bounded in size even when the data stream is arbitrarily…
This work addresses the problem of Social Activity Recognition (SAR), a critical component in real-world tasks like surveillance and assistive robotics. Unlike traditional event understanding approaches, SAR necessitates modeling individual…
Video action detection (VAD) aims to detect actors and classify their actions in a video. We figure that VAD suffers more from classification rather than localization of actors. Hence, we analyze how prevailing methods form features for…
Visual event perception tasks such as action localization have primarily focused on supervised learning settings under a static observer, i.e., the camera is static and cannot be controlled by an algorithm. They are often restricted by the…
This paper focuses on building object-centric representations for long-term action anticipation in videos. Our key motivation is that objects provide important cues to recognize and predict human-object interactions, especially when the…
Understanding human actions in wild videos is an important task with a broad range of applications. In this paper we propose a novel approach named Hierarchical Attention Network (HAN), which enables to incorporate static spatial…
The temporal segmentation of events is an essential task and a precursor for the automatic recognition of human actions in the video. Several attempts have been made to capture frame-level salient aspects through attention but they lack the…
Despite the rapid progress, existing works on action understanding focus strictly on one type of action agent, which we call actor---a human adult, ignoring the diversity of actions performed by other actors. To overcome this narrow…
With advances in data-driven machine learning research, a wide variety of prediction models have been proposed to capture spatio-temporal features for the analysis of video streams. Recognising actions and detecting action transitions…
Understanding continuous video streams plays a fundamental role in real-time applications including embodied AI and autonomous driving. Unlike offline video understanding, streaming video understanding requires the ability to process video…
While observing complex events with multiple actors, humans do not assess each actor separately, but infer from the context. The surrounding context provides essential information for understanding actions. To this end, we propose to…
We propose an approach for forecasting video of complex human activity involving multiple people. Direct pixel-level prediction is too simple to handle the appearance variability in complex activities. Hence, we develop novel intermediate…
Weakly-supervised action localization aims to recognize and localize action instancese in untrimmed videos with only video-level labels. Most existing models rely on multiple instance learning(MIL), where the predictions of unlabeled…
This paper proposes a person-centric and online approach to the challenging problem of localization and prediction of actions and interactions in videos. Typically, localization or recognition is performed in an offline manner where all the…
We introduce the Action Transformer model for recognizing and localizing human actions in video clips. We repurpose a Transformer-style architecture to aggregate features from the spatiotemporal context around the person whose actions we…
Video understanding is a growing field and a subject of intense research, which includes many interesting tasks to understanding both spatial and temporal information, e.g., action detection, action recognition, video captioning, video…
We propose a method for human action recognition, one that can localize the spatiotemporal regions that `define' the actions. This is a challenging task due to the subtlety of human actions in video and the co-occurrence of contextual…