Results 41 to 50 of about 5,597 (161)

Assembling a True “Olympic Gel” From over 16 000 Combinatorial DNA Rings

open access: yesAdvanced Materials, EarlyView.
Olympic gels are an elusive class of soft matter, consisting of molecular networks held together purely by mechanically interlocked rings. Their topological structure promises unique properties and functions, but their synthesis has proven notoriously difficult.
Sarah K. Speed   +9 more
wiley   +1 more source

Temporal Deformable Convolutional Encoder-Decoder Networks for Video Captioning

open access: yes, 2019
It is well believed that video captioning is a fundamental but challenging task in both computer vision and artificial intelligence fields. The prevalent approach is to map an input video to a variable-length output sentence in a sequence to sequence ...
Chao, Hongyang   +5 more
core   +1 more source

Sub‐Unit‐Cell Logic Governs Transport in TPMS Architectures

open access: yesAdvanced Science, EarlyView.
ABSTRACT Next‐generation energy, thermal, and chemical systems require architectures capable of highly efficient transport across multiple length scales. Triply periodic minimal surfaces (TPMS), first conceptualized in 1865, offer inherently scalable geometries with exceptional transport potential, yet mechanistic links between topology and performance
Haozhang Zhong   +16 more
wiley   +1 more source

Hierarchically Structured Reinforcement Learning for Topically Coherent Visual Story Generation

open access: yes, 2019
We propose a hierarchically structured reinforcement learning approach to address the challenges of planning for generating coherent multi-sentence stories for the visual storytelling task.
Celikyilmaz, Asli   +5 more
core   +1 more source

Pellet Printing for Soft Robotic Devices

open access: yesAdvanced Science, EarlyView.
Fused Granulate Fabrication (FGF) is established here as a reliable method for fabricating soft, airtight robotic devices. Through coordinated optimization of hardware, material selection, and process parameters, this approach enables high‐speed printing of thermoplastic elastomers with silicone‐like softness and modulus.
Yijia Wu   +6 more
wiley   +1 more source

Hierarchical Photo-Scene Encoder for Album Storytelling

open access: yes, 2019
In this paper, we propose a novel model with a hierarchical photo-scene encoder and a reconstructor for the task of album storytelling. The photo-scene encoder contains two sub-encoders, namely the photo and scene encoders, which are stacked together and
Jiang, Wenhao   +4 more
core   +1 more source

Dynamic Self‐Clickable Decellularized Matrix Hydrogels for Regulating Vascularity and Enhancing Muscle Regeneration

open access: yesAdvanced Science, EarlyView.
Dynamic decellularized hydrogels are prepared using bovine decellularized small intestine submucosa (SIS) norbornene (dSIS‐NB). Bovine dSIS contained significant amounts of disulfide‐rich fibrillin‐I, enabling ‘self‐clickable’ thiol‐norbornene gelation and spatiotemporal tuning of hydrogel physicochemical properties.
Van Thuy Duong   +4 more
wiley   +1 more source

Smart Exploration of Perovskite Photovoltaics: From AI Driven Discovery to Autonomous Laboratories

open access: yesAdvanced Energy Materials, EarlyView.
In this review, we summarize the fundamentals of AI in automated materials science, and review AI applications in perovskite solar cells. Then, we sum up recent progress in AI‐guided manufacturing optimization, and highlight AI‐driven high‐throughput and autonomous laboratories.
Wenning Chen   +4 more
wiley   +1 more source

Underground video semantic extraction and description generation technology based on multimodal large model

open access: yesMeitan kexue jishu
With the rapid advancement of intelligent coal mine construction, the volume of underground operational video data has surged dramatically. Current video processing and storage methods predominantly rely on single-scene video analysis and raw-format ...
Xiang FU   +6 more
doaj   +1 more source

Person Search with Natural Language Description

open access: yes, 2017
Searching persons in large-scale image databases with the query of natural language description has important applications in video surveillance. Existing methods mainly focused on searching persons with image-based or attribute-based queries, which have
Li, Hongsheng   +5 more
core   +1 more source

Home - About - Disclaimer - Privacy