Search Results

More efforts are being put into improving the capabilities of Large Language Models (LLM) than into dealing with their implications. Current LLMs are able to generate high-quality texts seemingly indistinguishable from those written by human experts. ...

Role classification of players according to their uniform or playing kit in unseen soccer game scenes remains a challenging problem. While multiple methods have being proposed for this task, both handcrafted and deep learning methods have been designed ...

Knowledge Distillation (KD), which extracts knowledge from a well-performed large neural network (a.k.a teacher network) to guide the training of a small network (a.k.a student network), has emerged as a promising approach for transfer learning and model ...

Current metric learning approaches for image retrieval are usually based on learning a space of informative latent representations where simple approaches such as the cosine distance would work well. Recent state of the art methods such as HypViT move to ...

Real-world datasets usually contain inevitable noisy labels, which will cause deep networks to overfit inaccurate information and yield degenerated performance. Previous literature typically focuses on sample selection to alleviate noisy labels. ...

In recent years, few-shot classification algorithms based on metric learning have gained significant attention in the field. However, in the context of cross-domain few-shot classification tasks, their performance still requires further ...

Aerial scene classification in remote sensing presents a significant challenge due to high intra-class variability and the different scales and orientations of the objects within dataset images. While deep learning architectures are commonly used for ...

Identifying electrical signatures preceding a ventricular arrhythmia from the implantable cardioverter-defibrillators (ICDs) can help predict an upcoming ICD shock. To achieve this, we first deployed a large-scale study (N=326) to continuously monitor ...

Deep learning has proven itself to be a successful set of models for learning useful semantic representations of data. In this paper, we explore the similar information and semantic information on vector space of images with self-attention mechanism. For ...

For better performance and less resource consumption, multi-scenario recommendation (MSR) is proposed to train a unified model to serve all scenarios by leveraging data from multiple scenarios. Current works in MSR focus on designing effective networks ...

Domain adaptation solves the challenge of inadequate labeled samples in the target domain by leveraging the knowledge learned from the labeled source domain. Most existing approaches aim to reduce the domain shift by performing some coarse alignments ...

The advancement of generative models has made it easier to create highly realistic Deepfake videos. This accessibility has led to a surge in research on Deepfake detection to mitigate potential misuse. Typically, Deepfake detection models utilize binary ...

Few‐shot image classification is the task of classifying novel classes using extremely limited labelled samples. To perform classification using the limited samples, one solution is to learn the feature alignment (FA) information between the ...

Since facial manipulation technology has raised serious concerns, facial forgery detection has also attracted increasing attention. Although recent work has made good achievements, the detection of unseen fake faces is still a big challenge. In ...

Subspace clustering, which recoveries the subspace representation in the form of an affinity graph, has drawn tons of attention due to its effectiveness in various clustering tasks. However, existing subspace clustering methods are usually fed with raw ...

Gait recognition aims at identifying individuals by unique walking patterns at a long distance. However, prevailing methods suffer from a large degradation when applied to large-scale surveillance systems. We find a significant cause of this issue is ...

Domain generalizable person Re-identification is a challenging and realistic task. It requires a model to train on multi-source domains and then generalizes well on unseen target domains. Existing approaches typically mix images from different domains in ...

Few-Shot Classification is a challenging problem as it uses only very few labeled examples to assign labels for query samples. The Prototypical Network effectively addresses the issue by matching the nearest mean-based prototype for each query ...

Few-shot classification aims to classify query samples using very few labeled examples. Most existing methods follow the Prototypical Network to classify query samples by matching them to the nearest centroid. However, scarce labeled examples tend ...

Few-shot image classification (FSIC) studies the problem of classifying images when given only a few training samples, which presents a challenge for deep learning models to generalize well on unseen image categories. To learn FSIC tasks ...$$$\mathrm{}$