Related papers: BU-CVKit: Extendable Computer Vision Framework for…

Recommender systems are a long-standing research problem in data mining and machine learning. They are incremental in nature, as new user-item interaction logs arrive. In real-world applications, we need to periodically train a…

Although occlusion widely exists in nature and remains a fundamental challenge for pose estimation, existing heatmap-based approaches suffer serious degradation on occlusions. Their intrinsic problem is that they directly localize the…

Computer Vision (CV) has achieved remarkable results, outperforming humans in several tasks. Nonetheless, it may result in significant discrimination if not handled properly as CV systems highly depend on the data they are fed with and can…

The integration of vision-language models such as CLIP and Concept Bottleneck Models (CBMs) offers a promising approach to explaining deep neural network (DNN) decisions using concepts understandable by humans, addressing the black-box…

Modern top-performing object detectors depend heavily on backbone networks, whose advances bring consistent performance gains through exploring more effective network structures. In this paper, we propose a novel and flexible backbone…

We propose a unified representation learning framework to address the Cross Model Compatibility (CMC) problem in the context of visual search applications. Cross compatibility between different embedding models enables the visual search…

Vector maps are essential in autonomous driving for tasks like localization and planning, yet their creation and maintenance are notably costly. While recent advances in online vector map generation for autonomous vehicles are promising,…

Utilizing the latest advances in Artificial Intelligence (AI), the computer vision community is now witnessing an unprecedented evolution in all kinds of perception tasks, particularly in object detection. Based on multiple spatially…

Gait recognition enables contact-free, long-range person identification that is robust to clothing variations and non-cooperative scenarios. While existing methods perform well in controlled indoor environments, they struggle with…

Human pose estimators are typically retrained from scratch or naively fine-tuned whenever keypoint sets, sensing modalities, or deployment domains change--an inefficient, compute-intensive practice that rarely matches field constraints. We…

Continuous-variable (CV) quantum computing offers a promising framework for scalable quantum machine learning, leveraging optical systems with infinite-dimensional Hilbert spaces. While discrete-variable (DV) quantum neural networks have…

We present a conceptually simple, flexible, and universal visual perception head for variant visual tasks, e.g., classification, object detection, instance segmentation and pose estimation, and different frameworks, such as one-stage or…

Infrared-visible (IR-VIS) feature matching plays an essential role in cross-modality visual localization, navigation and perception. Along with the rapid development of deep learning techniques, a number of representative image matching…

Researchers have identified datasets used for training computer vision (CV) models as an important source of hazardous outcomes, and continue to examine popular CV datasets to expose their harms. These works tend to treat datasets as…

Constructing environments for training and evaluating claw-like agents remains a manual, human-intensive process that does not scale. We argue that what is needed is not just a dataset, but an automated pipeline capable of generating…

Conventional CNNs-based dehazing models suffer from two essential issues: the dehazing framework (limited in interpretability) and the convolution layers (content-independent and ineffective to learn long-range dependency information). In…

Vision-Language Models (VLMs) have achieved remarkable progress on a wide range of challenging multimodal understanding and reasoning tasks. However, existing reasoning paradigms, such as the classical Chain-of-Thought (CoT), rely solely on…

In this paper, we propose a compact network called CUNet (compact unsupervised network) to counter the image classification challenge. Different from the traditional convolutional neural networks learning filters by the time-consuming…

We present an integrated framework for using Convolutional Networks for classification, localization and detection. We show how a multiscale and sliding window approach can be efficiently implemented within a ConvNet. We also introduce a…

Computer-aided diagnosis (CAD) has significantly advanced automated chest X-ray diagnosis but remains isolated from clinical workflows and lacks reliable decision support and interpretability. Human-AI collaboration seeks to enhance the…