Related papers: Learning to Discriminate Information for Online Ac…
Due to its importance in facial behaviour analysis, facial action unit (AU) detection has attracted increasing attention from the research community. Leveraging the online knowledge distillation framework, we propose the ``FANTrans" method…
Recurrent Neural Network (RNN) has been successfully applied in many sequence learning problems. Such as handwriting recognition, image description, natural language processing and video motion analysis. After years of development,…
In this work, we present a novel approach to multi-view action recognition where we guide learned action representations to be separated from view-relevant information in a video. When trying to classify action instances captured from…
In the world of action recognition research, one primary focus has been on how to construct and train networks to model the spatial-temporal volume of an input video. These methods typically uniformly sample a segment of an input clip…
Human action recognition from well-segmented 3D skeleton data has been intensively studied and has been attracting an increasing attention. Online action detection goes one step further and is more challenging, which identifies the action…
Current approaches for activity recognition often ignore constraints on computational resources: 1) they rely on extensive feature computation to obtain rich descriptors on all frames, and 2) they assume batch-mode access to the entire test…
This paper addresses the critical need for online action representation, which is essential for various applications like rehabilitation, surveillance, etc. The task can be defined as representation of actions as soon as they happen in a…
In online action detection, the goal is to detect the start of an action in a video stream as soon as it happens. For instance, if a child is chasing a ball, an autonomous car should recognize what is going on and respond immediately. This…
Action understanding, encompassing action detection and anticipation, plays a crucial role in numerous practical applications. However, untrimmed videos are often characterized by substantial redundant information and noise. Moreover, in…
Anticipating future actions based on spatiotemporal observations is essential in video understanding and predictive computer vision. Moreover, a model capable of anticipating the future has important applications, it can benefit…
Today, intelligent user interfaces on the web often come in form of recommendation services tailoring content to individual users. Recommendation of web content such as news articles often requires a certain amount of explicit ratings to…
Understanding instructional videos requires recognizing fine-grained actions and modeling their temporal relations, which remains challenging for current Video Foundation Models (VFMs). This difficulty stems from noisy web supervision and a…
Person Re-Identification (ReID) is a challenging problem in many video analytics and surveillance applications, where a person's identity must be associated across a distributed non-overlapping network of cameras. Video-based person ReID…
Recognition in planning seeks to find agent intentions, goals or activities given a set of observations and a knowledge library (e.g. goal states, plans or domain theories). In this work we introduce the problem of Online Action…
Current state-of-the-art action detection systems are tailored for offline batch-processing applications. However, for online applications like human-robot interaction, current systems fall short, either because they only detect one action…
Due to the distinctive characteristics of sensors, each modality exhibits unique physical properties. For this reason, in the context of multi-modal action recognition, it is important to consider not only the overall action content but…
We propose an approach to learn spatio-temporal features in videos from intermediate visual representations we call "percepts" using Gated-Recurrent-Unit Recurrent Networks (GRUs).Our method relies on percepts that are extracted from all…
Action detection aims to localize the starting and ending points of action instances in untrimmed videos, and predict the classes of those instances. In this paper, we make the observation that the outputs of the action detection task can…
In this paper, we address the challenging problem of efficient temporal activity detection in untrimmed long videos. While most recent work has focused and advanced the detection accuracy, the inference time can take seconds to minutes in…
Capturing the temporal dynamics of user preferences over items is important for recommendation. Existing methods mainly assume that all time steps in user-item interaction history are equally relevant to recommendation, which however does…