Results 51 to 60 of about 32,447 (225)
Caption Feature Space Regularization for Audio Captioning
, 2022 Audio captioning aims at describing the content of audio clips with human language. Due to the ambiguity of audio, different people may perceive the same audio differently, resulting in caption disparities (i.e., one audio may correlate to several captions with diverse semantics).
Zhang, Yiming +4 more
openaire +2 more sources
Advanced Healthcare Materials, EarlyView.Coagulative granular hydrogels are composed of packed thrombin‐functionalized microgels that catalyze the conversion of fibrinogen into a secondary fibrin network, filling the interstitial voids. This bio‐inspired approach stabilizes the biomaterial to match the robustness of bulk hydrogels without compromising injectability, mimicking the initial ...
Zhipeng Deng +16 more
wiley +1 more source
Challenges and Prospects in Vision and Language Research
Frontiers in Artificial Intelligence, 2019 Language grounded image understanding tasks have often been proposed as a method for evaluating progress in artificial intelligence. Ideally, these tasks should test a plethora of capabilities that integrate computer vision, reasoning, and natural ...
Kushal Kafle +4 more
doaj +1 more source
Image Captioning with Semantic Attention
, 2016 Automatically generating a natural language description of an image has attracted interests recently both because of its importance in practical applications and because it connects two major artificial intelligence fields: computer vision and natural ...
Fang, Chen +4 more
core +1 more source
Aqueous Two‐Phase Bioinks for Discrete Packing and Compartmentalization of 3D Bioprinted Cells
Advanced Healthcare Materials, EarlyView.Aqueous two‐phase systems (ATPS) enable the formation of biomimetic interfaces crucial for tissue engineering. However, clinical translation remains limited by the challenge of precisely controlling cellular compartmentalization. Here, we developed ATPS biomaterial inks for 3D bioprinting allowing tuneable droplet formation via NaCl modulation.
Martina Marcotulli +17 more
wiley +1 more source
Image Captioning using Deep Neural Architectures
, 2017 Automatically creating the description of an image using any natural languages sentence like English is a very challenging task. It requires expertise of both image processing as well as natural language processing.
Bakarola, Vishvajit +2 more
core +1 more source
Fluorescent Nanosensor for Indole‐3‐Propionic Acid Detection in Gut Health Monitoring
Advanced Healthcare Materials, EarlyView.This work introduces a fluorescent nanosensor system with two optical modalities for detection of indole‐3‐propionic acid (IPA) gut metabolite: (1) blue‐emitting cationic conjugated polyelectrolyte (CP3) and (2) near‐infrared (NIR)‐emitting CP3‐wrapped single‐walled carbon nanotube (SWNT).
Mervin Chun‐Yi Ang +15 more
wiley +1 more source
Journal of Food Science, 2021 February Online Cover : Tumor growth in mice treated with different blueberry extracts, including microscope observations of lung and liver sections, from “Investigation on the biological activity of anthocyanins and polyphenols in blueberry” by Sen Yang, Chao Wang, Xingyuan Li, Caie Wu, Chen Liu, Zhaohui Xue ...
openaire +1 more source
Fluid Forces Control Structural Remodeling of Blind‐Ended Lymphatic Microvessels
Advanced Healthcare Materials, EarlyView.Using innovative microfluidic biofabrication with fluid mechanical insights, we recapitulated the blind‐ended microanatomy and physiological drainage properties of capillary lymphatics. Our results reveal the interrelationship between intra‐ and extraluminal regions of lymphatic vessels due to flow‐induced sprouting and morphological changes that ...
Jacob C. Holter +5 more
wiley +1 more source
AVCaps: An Audio-Visual Dataset With Modality-Specific Captions
IEEE Open Journal of Signal ProcessingThis paper introduces AVCaps, an audio-visual dataset that contains separate textual captions for the audio, visual, and audio-visual contents of video clips. The dataset contains 2061 video clips constituting a total of 28.8 hours.
Parthasaarathy Sudarsanam +3 more
doaj +1 more source