Related papers: Deep Action- and Context-Aware Sequence Learning f…
This paper proposes a two-stream flow-guided convolutional attention networks for action recognition in videos. The central idea is that optical flows, when properly compensated for the camera motion, can be used to guide attention to the…
Anticipating future actions is a highly challenging task due to the diversity and scale of potential future actions; yet, information from different modalities help narrow down plausible action choices. Each modality can provide diverse and…
Smart devices of everyday use (such as smartphones and wearables) are increasingly integrated with sensors that provide immense amounts of information about a person's daily life such as behavior and context. The automatic and unobtrusive…
In this paper, we introduce the concept of learning latent super-events from activity videos, and present how it benefits activity detection in continuous videos. We define a super-event as a set of multiple events occurring together in…
Motion is a salient cue to recognize actions in video. Modern action recognition models leverage motion information either explicitly by using optical flow as input or implicitly by means of 3D convolutional filters that simultaneously…
Recognizing and categorizing human actions is an important task with applications in various fields such as human-robot interaction, video analysis, surveillance, video retrieval, health care system and entertainment industry. This thesis…
Recently, much progress has been made for self-supervised action recognition. Most existing approaches emphasize the contrastive relations among videos, including appearance and motion consistency. However, two main issues remain for…
Deep learning models have been efficient lately on image parsing tasks. However, deep learning models are not fully capable of exploiting visual and contextual information simultaneously. The proposed three-layer context-based deep…
While deep neural networks have led to human-level performance on computer vision tasks, they have yet to demonstrate similar gains for holistic scene understanding. In particular, 3D context has been shown to be an extremely important cue…
Video recognition models often learn scene-biased action representation due to the spurious correlation between actions and scenes in the training data. Such models show poor performance when the test data consists of videos with unseen…
Detecting and recognizing human action in videos with crowded scenes is a challenging problem due to the complex environment and diversity events. Prior works always fail to deal with this problem in two aspects: (1) lacking utilizing…
Human action recognition has drawn a lot of attention in the recent years due to the research and application significance. Most existing works on action recognition focus on learning effective spatial-temporal features from videos, but…
Recent video action recognition methods have shown excellent performance by adapting large-scale pre-trained language-image models to the video domain. However, language models contain rich common sense priors - the scene contexts that…
Dynamic imaging is a recently proposed action description paradigm for simultaneously capturing motion and temporal evolution information, particularly in the context of deep convolutional neural networks (CNNs). Compared with optical flow…
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…
Human action understanding is a fundamental and challenging task in computer vision. Although there exists tremendous research on this area, most works focus on action recognition, while action retrieval has received less attention. In this…
Human action recognition is one of the challenging tasks in computer vision. The current action recognition methods use computationally expensive models for learning spatio-temporal dependencies of the action. Models utilizing RGB channels…
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…
We address the problem of action detection in videos. Driven by the latest progress in object detection from 2D images, we build action models using rich feature hierarchies derived from shape and kinematic cues. We incorporate appearance…
This paper presents a novel spatiotemporal transformer network that introduces several original components to detect actions in untrimmed videos. First, the multi-feature selective semantic attention model calculates the correlations…