相关论文: Weak-Annotation of HAR Datasets using Vision Found…

In this paper, we present a method to learn a visual representation adapted for e-commerce products. Based on weakly supervised learning, our model learns from noisy datasets crawled on e-commerce website catalogs and does not require any…

Large amounts of annotated data have become more important than ever, especially since the rise of deep learning techniques. However, manual annotations are costly. We propose a tool that enables researchers to create large, high-quality,…

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…

Labeling visual data is expensive and time-consuming. Crowdsourcing systems promise to enable highly parallelizable annotations through the participation of monetarily or otherwise motivated workers, but even this approach has its limits.…

We consider human activity recognition (HAR) from wearable sensor data in manual-work processes, like warehouse order-picking. Such structured domains can often be partitioned into distinct process steps, e.g., packaging or transporting.…

Most existing crowd counting methods require object location-level annotation, i.e., placing a dot at the center of an object. While being simpler than the bounding-box or pixel-level annotation, obtaining this annotation is still…

Precise identification of multiple cell classes in high-resolution Giga-pixel whole slide imaging (WSI) is critical for various clinical scenarios. Building an AI model for this purpose typically requires pixel-level annotations, which are…

Fully convolutional networks (FCN) have achieved great success in human parsing in recent years. In conventional human parsing tasks, pixel-level labeling is required for guiding the training, which usually involves enormous human labeling…

Fine-tuning pre-trained vision-language models, like CLIP, has yielded success on diverse downstream tasks. However, several pain points persist for this paradigm: (i) directly tuning entire pre-trained models becomes both time-intensive…

Foundation vision or vision-language models are trained on large unlabeled or noisy data and learn robust representations that can achieve impressive zero- or few-shot performance on diverse tasks. Given these properties, they are a natural…

The ubiquitous availability of smartphones and smartwatches with integrated inertial measurement units (IMUs) enables straightforward capturing of human activities. For specific applications of sensor based human activity recognition (HAR),…

To learn a reliable people counter from crowd images, head center annotations are normally required. Annotating head centers is however a laborious and tedious process in dense crowds. In this paper, we present an active learning framework…

Methods that move towards less supervised scenarios are key for image segmentation, as dense labels demand significant human intervention. Generally, the annotation burden is mitigated by labeling datasets with weaker forms of supervision,…

The availability of training data for supervision is a frequently encountered bottleneck of medical image analysis methods. While typically established by a clinical expert rater, the increase in acquired imaging data renders traditional…

Foundation models, pre-trained on a large amount of data have demonstrated impressive zero-shot capabilities in various downstream tasks. However, in object detection and instance segmentation, two fundamental computer vision tasks heavily…

Reliable classification and detection of certain medical conditions, in images, with state-of-the-art semantic segmentation networks, require vast amounts of pixel-wise annotation. However, the public availability of such datasets is…

Obtaining accurate labels for instance segmentation is particularly challenging due to the complex nature of the task. Each image necessitates multiple annotations, encompassing not only the object class but also its precise spatial…

Significant performance improvement has been achieved for fully-supervised video salient object detection with the pixel-wise labeled training datasets, which are time-consuming and expensive to obtain. To relieve the burden of data…

Wearable technologies enable continuous monitoring of various health metrics, such as physical activity, heart rate, sleep, and stress levels. A key challenge with wearable data is obtaining quality labels. Unlike modalities like video…

Temporal action localization is a challenging computer vision problem with numerous real-world applications. Most existing methods require laborious frame-level supervision to train action localization models. In this work, we propose a…