Deploying multiple machine learning models on resource-constrained robotic platforms for different perception tasks often results in redundant computations, large memory footprints, and complex integration challenges. In response, this work presents Visual Perception Engine (VPEngine), a modular framework designed to e...
Jakub {\L}ucki, Jonathan Becktor, Georgios Georgakis et al.· 0 citations
Generating semantically controllable 3D CT volumes from radiology reports requires more than a rich text encoder, it requires vision-language alignment grounded in volumetric space. Existing Text-to-CT approaches condition generation on encoders pretrained with language only or 2D vision-language objectives, providing...
Daniele Molino, Camillo Maria Caruso, Filippo Ruffini et al.· 0 citations
This work proposes Aesthetic Alignment: aligning generated images to explicit, user-specified compositional constraints using the Principles of Art (PoA), and introduces CompArt, a dataset of 80,032 WikiArt images augmented with captions and PoA analyses produced by a multimodal LLM under structured prompting.
Zheng-Hao Jin, Tat-Seng Chua· International Conference on...· 1 citation
Urban Land Cover (ULC) classification plays a crucial role in urban planning, environmental monitoring, and sustainable development. We study this task using the ULC dataset from the UCI Machine Learning Repository, which includes tabular features derived from high-resolution aerial imagery across nine classes (e.g., r...
Muntasir Tabasum, Tanpia Tasnim, Md. Ekramul Islam et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Early detection of dental caries remains challenging due to limitations in traditional diagnostic methods, particularly for proximal lesions in posterior teeth. Deep learning models show promise for automated caries detection but face scalability constraints due to requirements for large volumes of expertly annotated t...
Jihun Kim, Kyeonghun Kim, Jong-yeol Lee et al.· 0 citations
Reducing radiation dose in computed tomography significantly degrades image quality and poses challenges for accurate and clinically reliable reconstruction. While recent approaches have shown promise for low-dose CT, they often struggle to generalize across continuous and previously unseen dose levels, leading to arti...
Md Imam Ahasan, Guangchao Yang, A F M Abdun Noor et al.· 0 citations
Robustness controls show that the signal is not explained solely by accompanying OCR and depends on paired visual evidence, and that it extends beyond English.
Girish A. Koushik, Diptesh Kanojia, Helen Treharne· 0 citations
Across four models, attention heads causally necessary for OCR are identified, and it is discovered that these are in fact general-purpose heads that output interpretable semantic features across all image tokens.
Sheridan Feucht, Benno Krojer, Sarah Wang et al.· 0 citations
Generalist-Specialist-MoE (GS-MoE), a two-branch architecture that couples a cross-modal generalist model with distinct modality-specific specialists (experts) via domain-constrained feature fusion, is introduced.
Johannes Kaiser, Florian Braunmiller, D. Rückert et al.· 0 citations
Video streaming dominates global internet traffic, yet conventional pipelines remain inefficient for structured, human-centric content such as sports, performance, or interactive media. Standard codecs re-encode entire frames, foreground and background alike, treating all pixels uniformly and ignoring the semantic stru...
Emanuele Artioli, Daniele Lorenzi, Shivi Vats et al.· 0 citations
Precise multi-camera tracking traditionally relies on rigorous 3D site calibration, yet this requirement is often operationally impossible in large-scale deployments. Privacy regulations frequently prohibit recording video for offline calibration; limited bandwidth precludes synchronizing high-resolution streams from h...
David Voihanski, Mor Sinai, B. Bobrovsky· 0 citations
This work introduces physical rank consistency (PRC) to measure how well tokenization preserves local physical distance rankings after reconstruction, and presents ActionPiece, which preserves physical action relationships through joint supervision of representation learning and quantization.
Shijie Lian, Bin Yu, Zhao-Long Shen et al.· 1 citation
Exploring how generative AI could make machine vision more accessible to businesses. The post GenEye in a Box: Making Machine Vision Something You Can Just Ask For appeared first on GPT-Lab.
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity. The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.
Computer scientist, entrepreneur, and philanthropist will collaborate with the MIT Schwarzman College of Computing to advance AI and scientific discovery.
