Related papers: Bridging Data Trials and Task Barriers: A Unified …
In the field of medical imaging, AI-assisted techniques such as object detection, segmentation, and classification are widely employed to alleviate the workload of physicians and doctors. However, single-task models are predominantly used,…
In this paper we address the issues of using edge detection techniques on facial images to produce cancellable biometric templates and a novel method for template verification against tampering. With increasing use of biometrics, there is a…
Recent advances in large pretrained text-to-image models have shown unprecedented capabilities for high-quality human-centric generation, however, customizing face identity is still an intractable problem. Existing methods cannot ensure…
Although multimodal fusion has made significant progress, its advancement is severely hindered by the lack of adequate evaluation benchmarks. Current fusion methods are typically evaluated on a small selection of public datasets, a limited…
Tracking objects of interest in a video is one of the most popular and widely applicable problems in computer vision. However, with the years, a Cambrian explosion of use cases and benchmarks has fragmented the problem in a multitude of…
Heterogeneous face matching is a challenge issue in face recognition due to large domain difference as well as insufficient pairwise images in different modalities during training. This paper proposes a coupled deep learning (CDL) approach…
Person re-identification plays a significant role in realistic scenarios due to its various applications in public security and video surveillance. Recently, leveraging the supervised or semi-unsupervised learning paradigms, which benefits…
Humans have remarkable selective sensitivity to identities -- easily distinguishing between highly similar identities, even across significantly different contexts such as diverse viewpoints or lighting. Vision models have struggled to…
A big, diverse and balanced training data is the key to the success of deep neural network training. However, existing publicly available datasets used in facial landmark localization are usually much smaller than those for other computer…
In embodied intelligence, the embodiment gap between robotic and human hands brings significant challenges for learning from human demonstrations. Although some studies have attempted to bridge this gap using reinforcement learning, they…
This paper proposes a novel scalable community-based neural framework for graph learning. The framework learns the graph topology through the task of community detection and link prediction by optimizing with our proposed joint SBM loss…
The recent emergence of ubiquitous, multi-platform eye tracking has raised user privacy concerns over re-identification across platforms, where a person is re-identified across multiple eye tracking-enabled platforms using personally…
Although pretraining has garnered significant attention and popularity in recent years, its application in graph-based recommender systems is relatively limited. It is challenging to exploit prior knowledge by pretraining in widely used…
In this work, we present a novel machine learning framework called Self-Directed Task Identification (SDTI), which enables models to autonomously identify the correct target variable for each dataset in a zero-shot setting without…
Cross-modal associations between voice and face from a person can be learnt algorithmically, which can benefit a lot of applications. The problem can be defined as voice-face matching and retrieval tasks. Much research attention has been…
How to tackle non-iid data is a crucial topic in federated learning. This challenging problem not only affects training process, but also harms performance of clients not participating in training. Existing literature mainly focuses on…
Unified Multimodal Models (UMMs) offer powerful cross-modality capabilities but introduce new safety risks not observed in single-task models. Despite their emergence, existing safety benchmarks remain fragmented across tasks and…
Recent deep image-to-image translation techniques allow fast generation of face images from freehand sketches. However, existing solutions tend to overfit to sketches, thus requiring professional sketches or even edge maps as input. To…
Sketch-based image manipulation is an interactive image editing task to modify an image based on input sketches from users. Existing methods typically formulate this task as a conditional inpainting problem, which requires users to draw an…
Computer-aided diagnosis (CAD) systems play a crucial role in analyzing neuroimaging data for neurological and psychiatric disorders. However, small-sample studies suffer from low reproducibility, while large-scale datasets introduce…