Zobrazeno 1 - 10
of 71
pro vyhledávání: '"Zhang, Mengmi"'
A prior represents a set of beliefs or assumptions about a system, aiding inference and decision-making. In this work, we introduce the challenge of unsupervised prior learning in pose estimation, where AI models learn pose priors of animate objects
Externí odkaz:
http://arxiv.org/abs/2410.03858
Autor:
Han, Shuangpeng, Zhang, Mengmi
AI models make mistakes when recognizing images-whether in-domain, out-of-domain, or adversarial. Predicting these errors is critical for improving system reliability, reducing costly mistakes, and enabling proactive corrections in real-world applica
Externí odkaz:
http://arxiv.org/abs/2410.02384
Biological motion perception (BMP) refers to humans' ability to perceive and recognize the actions of living beings solely from their motion patterns, sometimes as minimal as those depicted on point-light displays. While humans excel at these tasks w
Externí odkaz:
http://arxiv.org/abs/2405.16493
Despite the rapid progress in image generation, emotional image editing remains under-explored. The semantics, context, and structure of an image can evoke emotional responses, making emotional image editing techniques valuable for various real-world
Externí odkaz:
http://arxiv.org/abs/2403.08255
Robot navigation under visual corruption presents a formidable challenge. To address this, we propose a Test-time Adaptation (TTA) method, named as TTA-Nav, for point-goal navigation under visual corruptions. Our "plug-and-play" method incorporates a
Externí odkaz:
http://arxiv.org/abs/2403.01977
Scene graph generation (SGG) involves analyzing images to extract meaningful information about objects and their relationships. Given the dynamic nature of the visual world, it becomes crucial for AI systems to detect new objects and establish their
Externí odkaz:
http://arxiv.org/abs/2310.01636
Autor:
Sikarwar, Ankur, Zhang, Mengmi
Working memory (WM), a fundamental cognitive process facilitating the temporary storage, integration, manipulation, and retrieval of information, plays a vital role in reasoning and decision-making tasks. Robust benchmark datasets that capture the mu
Externí odkaz:
http://arxiv.org/abs/2307.10768
Autor:
Tee, Ren Jie, Zhang, Mengmi
Humans engage in learning and reviewing processes with curricula when acquiring new skills or knowledge. This human learning behavior has inspired the integration of curricula with replay methods in continual learning agents. The goal is to emulate t
Externí odkaz:
http://arxiv.org/abs/2307.05747
This paper tackles the problem of object counting in images. Existing approaches rely on extensive training data with point annotations for each object, making data collection labor-intensive and time-consuming. To overcome this, we propose a trainin
Externí odkaz:
http://arxiv.org/abs/2307.00038
Learning object-centric representations from complex natural environments enables both humans and machines with reasoning abilities from low-level perceptual features. To capture compositional entities of the scene, we proposed cyclic walks between p
Externí odkaz:
http://arxiv.org/abs/2302.08023