相关论文: Differentiable Frequency-based Disentanglement for…

Existing deep learning methods for action recognition in videos require a large number of labeled videos for training, which is labor-intensive and time-consuming. For the same action, the knowledge learned from different media types, e.g.,…

Human behavior understanding in videos is a complex, still unsolved problem and requires to accurately model motion at both the local (pixel-wise dense prediction) and global (aggregation of motion cues) levels. Current approaches based on…

Recent advancements in human video synthesis have enabled the generation of high-quality videos through the application of stable diffusion models. However, existing methods predominantly concentrate on animating solely the human element…

Adaptive sampling that exploits the spatiotemporal redundancy in videos is critical for always-on action recognition on wearable devices with limited computing and battery resources. The commonly used fixed sampling strategy is not…

Uncertainty estimation in deep neural networks is essential for designing reliable and robust AI systems. Applications such as video surveillance for identifying suspicious activities are designed with deep neural networks (DNNs), but DNNs…

Advanced driver assistance and automated driving systems rely on risk estimation modules to predict and avoid dangerous situations. Current methods use expensive sensor setups and complex processing pipeline, limiting their availability and…

Latent traversal is a popular approach to visualize the disentangled latent representations. Given a bunch of variations in a single unit of the latent representation, it is expected that there is a change in a single factor of variation of…

Temporal modeling is crucial for multi-frame human pose estimation. Most existing methods directly employ optical flow or deformable convolution to predict full-spectrum motion fields, which might incur numerous irrelevant cues, such as a…

We propose a new formulation of temporal action detection (TAD) with denoising diffusion, DiffTAD in short. Taking as input random temporal proposals, it can yield action proposals accurately given an untrimmed long video. This presents a…

Sensor-based human activity recognition (HAR) requires to predict the action of a person based on sensor-generated time series data. HAR has attracted major interest in the past few years, thanks to the large number of applications enabled…

The low resolution of objects of interest in aerial images makes pedestrian detection and action detection extremely challenging tasks. Furthermore, using deep convolutional neural networks to process large images can be demanding in terms…

As the success of deep models has led to their deployment in all areas of computer vision, it is increasingly important to understand how these representations work and what they are capturing. In this paper, we shed light on deep…

The recognition of human actions in video streams is a challenging task in computer vision, with cardinal applications in e.g. brain-computer interface and surveillance. Deep learning has shown remarkable results recently, but can be found…

In this work we present an adversarial training algorithm that exploits correlations in video to learn --without supervision-- an image generator model with a disentangled latent space. The proposed methodology requires only a few…

In this work, we propose an approach to the spatiotemporal localisation (detection) and classification of multiple concurrent actions within temporally untrimmed videos. Our framework is composed of three stages. In stage 1, appearance and…

Visual saliency, which predicts regions in the field of view that draw the most visual attention, has attracted a lot of interest from researchers. It has already been used in several vision tasks, e.g., image classification, object…

We present a novel and unified deep learning framework which is capable of learning domain-invariant representation from data across multiple domains. Realized by adversarial training with additional ability to exploit domain-specific…

In this work, we aim to segment and detect water in videos. Water detection is beneficial for appllications such as video search, outdoor surveillance, and systems such as unmanned ground vehicles and unmanned aerial vehicles. The specific…

Automating the analysis of surveillance video footage is of great interest when urban environments or industrial sites are monitored by a large number of cameras. As anomalies are often context-specific, it is hard to predefine events of…

Drones are enabling new forms of human actions surveillance due to their low cost and fast mobility. However, using deep neural networks for automatic aerial action recognition is difficult due to the need for a large number of training…