RA-CoA is a model-agnostic approach that works with frozen VLMs to improve fine-grained attribute precision in product captions without the need for fine-tuning, and is proposed as a novel, training-free framework that disentangles fashion image captioning into two interpretable stages.
A. S. Penamakuri, Shreya Shukla, Anand Mishra· Trans. Mach. Learn. Res.· 0 citations
Completeness-aware Motion Correspondence (CMC), a ground-truth-anchored evaluation protocol that jointly measures localization, trajectory completeness, visibility, and continuity, counting missing predictions as failures on visible dynamic points, is introduced.
Kun-Wei Wu, Xiang Liu, Guo-Cai Yao et al.· 0 citations
GraMRAG is proposed, a graph memory-guided multi-agent RAG framework that integrates a dynamic multimodal memory graph to enable stable, multi-step multimodal reasoning and introduces a vision-text bridged reasoning paradigm that unifies multi-scale entity cropping with a ReAct-style visual toolchain, enhancing the lon...
SGWIB is developed, an information-bottleneck framework for single-modal video highlight detection that learns compact bottleneck representations while preserving inter-segment temporal structure and Home-Away-Related Contextual Pseudo-Labels and a contextual disentanglement module that reduce sports-specific contextua...
Han-Juan Huang, Yung-Chieh Yeh, H. Pao· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
It is argued that dynamic social encoding does not necessarily imply dynamic social activation, and a generation-aware bias activation model is proposed, a generation-aware bias activation model for human trajectory prediction that consistently improves the resonance-based baseline and achieves competitive state-of-the...
Jia-Heng Chen, Jia-Xing Li, Leixia Wang et al.· 0 citations
Breast ultrasound imaging plays an important role in the early detection and diagnosis of breast cancer, particularly for patients with dense breast tissue. However, developing reliable deep learning models for ultrasound analysis is challenging due to limited annotated medical data and the need for interpretable predi...
This work presents an end-to-end pipeline that converts real-world driving footage from the Joint Attention in Autonomous Driving dataset into synthetic dynamic vision sensor (DVS) event streams using the v2e simulator, and trains a novel convolutional spiking neural network (Conv-SNN) with clip-consistent DVS augmenta...
Henok Teklu, Mustafa Sakhai, Maciej Wielgosz et al.· 1 citation
The proposed framework can substantially reduce exhaustive protocol testing while enabling task-based, dose-aware protocol selection before the diagnostic scan and shows that the proposed framework can substantially reduce exhaustive protocol testing while enabling task-based, dose-aware protocol selection before the d...
J. Zou, David Fenwick, Vahid Tarokh et al.· 0 citations
Medical image classification is frequently complicated by transitional categories whose feature distributions overlap those of adjacent classes, producing ambiguous decision boundaries. Conformal prediction returns uncertainty-aware prediction sets, but these are not directly actionable in clinical screening, where a s...
Saibal Ghosh, Samarup Bhattacharya, Sanjoy Kumar Saha et al.· 0 citations
Anomaly detection in structured images is challenging in small-data settings where deep learning approaches are costly or impractical. Classical template matching is simple and interpretable but lacks robustness to geometric variations such as scale, rotation, and perspective. We propose a variational template matching...
Diffusion large language models (dLLMs) achieve high decoding efficiency through block-parallel, arbitrary-order generation, making them attractive for latency-sensitive applications. GUI agents represent a natural testbed for this paradigm, as they must repeatedly perceive screen states and emit structured, spatially...
Zhangxuan Gu, Hao-Xin Chen, Qiujieli Qin et al.· 0 citations
Among adaptation strategies, LoRA matches or surpasses full fine-tuning on crater detection and IMP segmentation while using far fewer trainable parameters, whereas full fine-tuning performs best for ice prospectivity regression.
Paolo Fraccaro, Gabrielle Nyirjesy, Daniela Szwarcman et al.· 0 citations
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.
