Related papers: Hierarchical Graph-RNNs for Action Detection of Mu…
Deep neural networks have achieved great success for video analysis and understanding. However, designing a high-performance neural architecture requires substantial efforts and expertise. In this paper, we make the first attempt to let…
Many human activities take minutes to unfold. To represent them, related works opt for statistical pooling, which neglects the temporal structure. Others opt for convolutional methods, as CNN and Non-Local. While successful in learning…
Object detection, scene graph generation and region captioning, which are three scene understanding tasks at different semantic levels, are tied together: scene graphs are generated on top of objects detected in an image with their pairwise…
Understanding how neuronal networks reorganize in response to external stimuli and give rise to behavior is a central challenge in neuroscience and artificial intelligence. However, existing methods often fail to capture the evolving…
Temporal action localization (TAL) in videos is a challenging task, especially due to the large variation in action temporal scales. Short actions usually occupy a major proportion in the datasets, but tend to have the lowest performance.…
In the field of action recognition, video clips are always treated as ordered frames for subsequent processing. To achieve spatio-temporal perception, existing approaches propose to embed adjacent temporal interaction in the convolutional…
To have a robot actively supporting a human during a collaborative task, it is crucial that robots are able to identify the current action in order to predict the next one. Common approaches make use of high-level knowledge, such as object…
In this paper, a novel video classification method is presented that aims to recognize different categories of third-person videos efficiently. Our motivation is to achieve a light model that could be trained with insufficient training…
Numerous powerful point process models have been developed to understand temporal patterns in sequential data from fields such as health-care, electronic commerce, social networks, and natural disaster forecasting. In this paper, we develop…
Events defined by the interaction of objects in a scene are often of critical importance; yet important events may have insufficient labeled examples to train a conventional deep model to generalize to future object appearance. Activity…
In this paper, we present a framework that jointly retrieves and spatiotemporally highlights actions in videos by enhancing current deep cross-modal retrieval methods. Our work takes on the novel task of action highlighting, which…
State-of-the-art temporal action detectors inefficiently search the entire video for specific actions. Despite the encouraging progress these methods achieve, it is crucial to design automated approaches that only explore parts of the video…
Temporal action proposal generation is an essential and challenging task that aims at localizing temporal intervals containing human actions in untrimmed videos. Most of existing approaches are unable to follow the human cognitive process…
Visual-based human action recognition can be found in various application fields, e.g., surveillance systems, sports analytics, medical assistive technologies, or human-robot interaction frameworks, and it concerns the identification and…
In this thesis, we focus on video action understanding problems from an online and real-time processing point of view. We start with the conversion of the traditional offline spatiotemporal action detection pipeline into an online…
Action detection is an essential and challenging task, especially for densely labelled datasets of untrimmed videos. There are many real-world challenges in those datasets, such as composite action, co-occurring action, and high temporal…
In this dissertation, I present my work towards exploring temporal information for better video understanding. Specifically, I have worked on two problems: action recognition and semantic segmentation. For action recognition, I have…
In this paper, we propose a method for activity recognition from videos based on sparse local features and hypergraph matching. We benefit from special properties of the temporal domain in the data to derive a sequential and fast graph…
Understanding human motion behaviour is a critical task for several possible applications like self-driving cars or social robots, and in general for all those settings where an autonomous agent has to navigate inside a human-centric…
Predicting future motions of nearby agents is essential for an autonomous vehicle to take safe and effective actions. In this paper, we propose TSGN, a framework using Temporal Scene Graph Neural Networks with projected vectorized…