Benchmarking Data and Computational Efficiency of ActionFormer on Temporal Action Localization Tasks: Analysing the Performance and Generalizability of ActionFormer in Resource-constrained Environments

In temporal action localization, given an input video, the goal is to predict which actions it contains, where they begin and where they end. Training and testing current state-of-the-art, deep learning models is done assuming access to large amounts of data and computational power. Gathering such data is however a challenging task and access to...

Group Equivariant Video Action Recognition: Making action-recognition networks equivariant to temporal direction and discrete spatial rotations

This work applies the theory of group equivariance to the domain of video action recognition replacing standard 3Dconvolutions with group convolutions which are equivariant to temporal direction, and multiples of 90-degree spatial rotations. We propose a temporal direction symmetry group T2 and extend the standard planar rotations group to three...

Long-term behaviour recognition in videos with actor-focused region attention

Long-Term activities involve humans performing complex, minutes-long actions. Differently than in traditional action recognition, complex activities are normally composed of a set of sub-actions, that can appear in different order, duration, and quantity. These aspects introduce a large intra-class variability, that can be hard to model. Our...

Contrastive Learning of Visual Representations from Unlabeled Videos

This thesis presents a novel self-supervised approach of learning visual representations from videos containing human actions. Our approach tackles the complex problem of learning without the need of labeled data by exploring to what extent the ideas successfully used for images can be transferred, adapted and extended to videos for action...

Using Phase Instead of Optical Flow for Action Recognition

Currently, the most common motion representation for action recognition is optical flow. Optical flow is based on particle tracking which adheres to a Lagrangian perspective on dynamics. In contrast to the Lagrangian perspective, the Eulerian model of dynamics does not track, but describes local changes. For video, an Eulerian phase-based...

Learning Phase-Based Descriptions for Action Recognition

Action recognition continues to receive significant attention from the research community, with new neural network architectures being developed continuously. Optical flow is by far the most popular input motion representation to these architectures, leaving a lot of undiscovered potential for other types of motion representations. Eulerian...

Action Recognition From Variable Viewpoints: Towards a safer living environment for elderly

The Dutch Central Bureau of Statistics expects the elderly population to grow from 2.4 million in 2012 to 4.7 million in 2041, putting intense pressure on health care budgets. As elderly get older and older, even more pressure on health care budgets will exist in the near future. Therefore, there is currently a focus on prevention: reduce...

Featureless: Bypassing feature extraction in action categorization

This method introduces an efficient manner of learning action categories without the need of feature estimation. The approach starts from low-level values, in a similar style to the successful CNN methods. However, rather than extracting general image features, we learn to predict specific video representations from raw video data. The benefit...

Kinect sensing of shopping related actions

Surveillance systems in shopping malls or supermarkets are usually used for detecting abnormal behavior. We used the distributed video cameras system to design digital shopping assistants which assess the behavior of customers while shopping, detect when they need assistance, and offer their support in case there is a selling opportunity. In...

Body Posture Analysis in the Context of Shopping

Shopping is a daily common activity for all individuals. In that context, there are needs related to security, efficiency and satisfaction. Store owners, customers and producer brands are three parties sharing these needs and there are intelligent systems that offer solutions. Intelligent systems could use the video information from the store...

Single person pose recognition and tracking

The goal of this research is to improve a system capable to detect, track a single person and recognize poses real time for controlling a spatial game. After performing background subtraction, the human blob is segmented in order to track the torso and hands. Angles and distances between hands and torso center are used to compute the features....