Results 41 to 50 of about 222,124 (278)
Deep Multimodal Semantic Embeddings for Speech and Images
, 2015 In this paper, we present a model which takes as input a corpus of images with relevant spoken captions and finds a correspondence between the two modalities. We employ a pair of convolutional neural networks to model visual objects and speech signals at
Glass, James, Harwath, David
core +1 more source
Improving Image Captioning with Better Use of Caption
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020 ACL ...
Shi, Zhan +3 more
openaire +2 more sources
Substrate Stress Relaxation Regulates Cell‐Mediated Assembly of Extracellular Matrix
Advanced Functional Materials, EarlyView.Silicone‐based viscoelastic substrates with tunable stress relaxation reveal how matrix mechanics regulates cellular mechanosensing and cell‐mediated matrix remodelling in the stiff regime. High stress relaxation promotes assembly of fibronectin fibril‐like structures, increased nuclear localization of YAP and formation of β1 integrin‐enriched ...
Jonah L. Voigt +2 more
wiley +1 more source
SentiCap: Generating Image Descriptions with Sentiments
, 2015 The recent progress on image recognition and language modeling is making automatic description of image content a reality. However, stylized, non-factual aspects of the written description are missing from the current systems.
He, Xuming +2 more
core +1 more source
Advanced Functional Materials, EarlyView.Polymorph engineering in ErMnO3 enables low‐voltage, forming‐free threshold switching with tunable negative differential resistance. Conducting orthorhombic regions embedded in an insulating hexagonal matrix provide controlled Joule‐heating‐enhanced Poole–Frenkel transport. The hexagonal phase prevents excessive heating and breakdown.
Rong Wu +8 more
wiley +1 more source
Punny Captions: Witty Wordplay in Image Descriptions
, 2018 Wit is a form of rich interaction that is often grounded in a specific situation (e.g., a comment in response to an event). In this work, we attempt to build computational models that can produce witty descriptions for a given image.
Bansal, Mohit +2 more
core +1 more source
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
"Too close to call" : CNN's politics of captions in the coverage of the Florida Recount [PDF]
, 2006 Proceeding chronologically in terms of the events covered, Raimund Schieß in his paper „Too close to call: CNN’s politics of captions in the coverage of the Florida Recount“ focusses on Nov. 11, 2000, when the Bush campaign applied to Miami Federal Court
Schieß, Raimund
core
Image Representations and New Domains in Neural Image Captioning
, 2015 We examine the possibility that recent promising results in automatic caption generation are due primarily to language models. By varying image representation quality produced by a convolutional neural network, we find that a state-of-the-art neural ...
Hessel, Jack +2 more
core +1 more source