Zobrazeno 1 - 10
of 1 433
pro vyhledávání: '"Noël, E"'
Autor:
Yan, Sen, O'Connor, David J., Wang, Xiaojun, O'Connor, Noel E., Smeaton, Alan F., Liu, Mingming
Urban pollution poses serious health risks, particularly in relation to traffic-related air pollution, which remains a major concern in many cities. Vehicle emissions contribute to respiratory and cardiovascular issues, especially for vulnerable and
Externí odkaz:
http://arxiv.org/abs/2412.13966
Autor:
Sirotkin, Kirill, Escudero-Viñolo, Marcos, Carballeira, Pablo, Maniparambil, Mayug, Barata, Catarina, O'Connor, Noel E.
Foundation models trained on web-scraped datasets propagate societal biases to downstream tasks. While counterfactual generation enables bias analysis, existing methods introduce artifacts by modifying contextual elements like clothing and background
Externí odkaz:
http://arxiv.org/abs/2412.09160
Autor:
Maniparambil, Mayug, Akshulakov, Raiymbek, Djilali, Yasser Abdelaziz Dahou, Narayan, Sanath, Singh, Ankit, O'Connor, Noel E.
Recent contrastive multimodal vision-language models like CLIP have demonstrated robust open-world semantic understanding, becoming the standard image backbones for vision-language applications due to their aligned latent space. However, this practic
Externí odkaz:
http://arxiv.org/abs/2409.19425
Event Cameras, also known as Neuromorphic sensors, capture changes in local light intensity at the pixel level, producing asynchronously generated data termed ``events''. This distinct data format mitigates common issues observed in conventional came
Externí odkaz:
http://arxiv.org/abs/2408.10395
This paper proposes a framework for time series generation built to investigate anomaly detection in cloud microservices. In the field of cloud computing, ensuring the reliability of microservices is of paramount concern and yet a remarkably challeng
Externí odkaz:
http://arxiv.org/abs/2408.00006
Autor:
Albert, Paul, Valmadre, Jack, Arazo, Eric, Krishna, Tarun, O'Connor, Noel E., McGuinness, Kevin
Training a classifier on web-crawled data demands learning algorithms that are robust to annotation errors and irrelevant examples. This paper builds upon the recent empirical observation that applying unsupervised contrastive learning to noisy, web-
Externí odkaz:
http://arxiv.org/abs/2407.05528
Cine cardiac magnetic resonance (CMR) imaging is recognised as the benchmark modality for the comprehensive assessment of cardiac function. Nevertheless, the acquisition process of cine CMR is considered as an impediment due to its prolonged scanning
Externí odkaz:
http://arxiv.org/abs/2404.06941
Autor:
Aleem, Sidra, Wang, Fangyijie, Maniparambil, Mayug, Arazo, Eric, Dietlmeier, Julia, Silvestre, Guenole, Curran, Kathleen, O'Connor, Noel E., Little, Suzanne
The Segment Anything Model (SAM) and CLIP are remarkable vision foundation models (VFMs). SAM, a prompt driven segmentation model, excels in segmentation tasks across diverse domains, while CLIP is renowned for its zero shot recognition capabilities.
Externí odkaz:
http://arxiv.org/abs/2404.06362
Autor:
Maniparambil, Mayug, Akshulakov, Raiymbek, Djilali, Yasser Abdelaziz Dahou, Narayan, Sanath, Seddik, Mohamed El Amine, Mangalam, Karttikeya, O'Connor, Noel E.
Aligned text-image encoders such as CLIP have become the de facto model for vision-language tasks. Furthermore, modality-specific encoders achieve impressive performances in their respective domains. This raises a central question: does an alignment
Externí odkaz:
http://arxiv.org/abs/2401.05224
Autor:
Rai, Ayush K., Krishna, Tarun, Hu, Feiyan, Drimbarean, Alexandru, McGuinness, Kevin, Smeaton, Alan F., O'Connor, Noel E.
Video Anomaly Detection (VAD) is an open-set recognition task, which is usually formulated as a one-class classification (OCC) problem, where training data is comprised of videos with normal instances while test data contains both normal and anomalou
Externí odkaz:
http://arxiv.org/abs/2311.16514