DR-NTU (Data) (Nanyang Technological University)
DR-NTU (Data) (Nanyang Technological University)Not a member yet
1955 research outputs found
Sort by
Supplementary Material 1: Building Damage Survey
No full textSupplementary Material 1 contains the damage survey for 589 buildings affected by the 2017-2018 Manaro Voui eruption on Ambae, Vanuatu. Survey location, construction type, tephra thickness, and damage state are provided. More detailed information, such as co-ordinates, detailed damage descriptions, photos, are not included to protect the privacy of those affected
Replication Data for: Coastal vertical land motion across Southeast Asia derived from combining tide gauge and satellite altimetry observations
No full textThis dataset contains the vertical land motion time series figures and data files derived from satellite altimetry and 50 tide gauge stations
Health Apps and Wearables Use in ASEAN
No full textThis is a large scale survey data of health apps and wearables use among selected ASEAN nation
Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively
No full textThe CLIP and Segment Anything Model (SAM) are remarkable vision foundation models (VFMs). SAM excels in segmentation tasks across diverse domains, whereas CLIP is renowned for its zero-shot recognition capabilities. This paper presents an in-depth exploration of integrating these two models into a unified framework. Specifically, we introduce the Open-Vocabulary SAM, a SAM-inspired model designed for simultaneous interactive segmentation and recognition, leveraging two unique knowledge transfer modules: SAM2CLIP and CLIP2SAM. The former adapts SAM’s knowledge into the CLIP via distillation and learnable transformer adapters, while the latter transfers CLIP knowledge into SAM, enhancing its recognition capabilities. Extensive experiments on various datasets and detectors show the effectiveness of Open-Vocabulary SAM in both segmentation and recognition tasks, significantly outperforming the naïve baselines of simply combining SAM and CLIP. Furthermore, aided with image classification data training, our method can segment and recognize approximately 22,000 classes
Data-Driven Approach to Understanding Complex Urban Phe-nomena: A Preliminary Study on the Gentrification of H Street NE in Washington DC
No full textPython scripts and secondary data sets used in our study of the gentrification of H Street NE in Washington DC
Supersonic Impinging Jet Flat Wall OpenFOAM
No full textSupersonic Impinging Jet Ma = 1.45 NPR = 4 H = 1.5D Medium Mesh 16M Cells OpenFOAM V211
Replication Data for: Three-dimensional flat Landau levels in an inhomogeneous acoustic crystal
No full textExperimental data for the paper "Three-dimensional flat Landau levels in an inhomogeneous acoustic crystal
FunQA: Towards Surprising Video Comprehension
No full textSurprising videos, e.g., funny clips, creative performances, or visual illusions, attract significant attention. Enjoyment of these videos is not simply a response to visual stimuli; rather, it hinges on the human capacity to understand (and appreciate) commonsense violations depicted in these videos. We introduce FunQA, a challenging video question answering (QA) dataset specifically designed to evaluate and enhance the depth of video reasoning based on counter-intuitive and fun videos. Unlike most video QA benchmarks which focus on less surprising contexts, e.g., cooking or instructional videos, FunQA covers three previously unexplored types of surprising videos: 1) HumorQA , 2) CreativeQA, and 3) MagicQA. For each subset, we establish rigorous QA tasks designed to assess the model's capability in counter-intuitive timestamp localization, detailed video description, and reasoning around counter-intuitiveness. We also pose higher-level tasks, such as attributing a fitting and vivid title to the video, and scoring the video creativity. In total, the FunQA benchmark consists of 312K free-text QA pairs derived from 4.3K video clips, spanning a total of 24 video hours. Extensive experiments with existing VideoQA models reveal significant performance gaps for the FunQA videos across spatial-temporal reasoning, visual-centered reasoning, and free-text generation
Related Data for: Visual hull based 3D reconstruction of shocks in under-expanded supersonic bevelled jets
No full textSchlieren images of supersonic jet optimized for 3D shock wave reconstruction
Replication Data for: Topological Directional Coupler
No full textY. Li, M. Jung, Y. Yu, Y. Han, B. Zhang, G. Shvets, Topological Directional Coupler. Laser Photonics Rev 2024, 2301313. https://doi.org/10.1002/lpor.20230131