Search

The development of Urdu scene text detection, recognition, and Visual Question Answering (VQA) technologies is crucial for advancing accessibility, information retrieval, and linguistic diversity in digital content, facilitating better understanding and interaction with Urdu-language visual data. This initiative seeks to bridge the gap between textual and visual comprehension. We propose a new multi-task Urdu scene text dataset comprising over 1000 natural scene images, which can be used for text detection, recognition, and VQA tasks. We provide fine-grained annotations for text instances, addressing the limitations of previous datasets for facing arbitrary-shaped texts. By incorporating additional annotation points, this dataset facilitates the development and assessment of methods that can handle diverse text layouts, intricate shapes, and non-standard orientations commonly encountered in real-world scenarios. Besides, the VQA annotations make it the first benchmark for the Urdu Text VQA method, which can prompt the development of Urdu scene text understanding. The proposed dataset is available at: https://github.com/Hiba-MeiRuan/Urdu-VQA-Dataset-/tree/main, Comment: Accepted by the International Conference on Document Analysis and Recognition (ICDAR) 2024

We create a manually-operated mechanical digger able to move within 2D densely packed granular media, in a manner intrinsically different from the existing biomimic diggers. The characteristics of our design include that the average grain size is about one tenth as large as the digger, the area packing density $\phi$ is about $90\%$ of the jamming density $\phi_{c}$, and the value of the dimensionless inertial number $I$ is in the quasi-static regime. Unlike conventional autonomous diggers that move by fluidizing the surrounding granular media with a much finer grain size, our digger swiftly bypasses this mobility mechanism as coarse grains with interparticle friction are hard to be fluidized. To achieve this, the digger has a circular shape and singly captures granular particles near the front entrance of the recess formed by the center unit running across its body using the equipped vibrating claw and then ejects the captured particles backwards. We validate this moving strategy in both experiments and numerical simulations, and demonstrate that the moving efficiency can be enhanced by the judgement of the human operator but the effectiveness is not significantly influenced by the shape of granular particles. In addition, localized vibration from the claw is needed to degrade friction between interlocked irregular-shaped particles., Comment: 9 pages, 8 figures

Scene text recognition is essential in many applications, including automated translation, information retrieval, driving assistance, and enhancing accessibility for individuals with visual impairments. Much research has been done to improve the accuracy and performance of scene text detection and recognition models. However, most of this research has been conducted in the most common languages, English and Chinese. There is a significant gap in low-resource languages, especially the Swahili Language. Swahili is widely spoken in East African countries but is still an under-explored language in scene text recognition. No studies have been focused explicitly on Swahili natural scene text detection and recognition, and no dataset for Swahili language scene text detection and recognition is publicly available. We propose a comprehensive dataset of Swahili scene text images and evaluate the dataset on different scene text detection and recognition models. The dataset contains 976 images collected in different places and under various circumstances. Each image has its annotation at the word level. The proposed dataset can also serve as a benchmark dataset specific to the Swahili language for evaluating and comparing different approaches and fostering future research endeavors. The dataset is available on GitHub via this link: https://github.com/FadilaW/Swahili-STR-Dataset, Comment: Accepted to ICDAR 2024

Artistic text recognition is an extremely challenging task with a wide range of applications. However, current scene text recognition methods mainly focus on irregular text while have not explored artistic text specifically. The challenges of artistic text recognition include the various appearance with special-designed fonts and effects, the complex connections and overlaps between characters, and the severe interference from background patterns. To alleviate these problems, we propose to recognize the artistic text at three levels. Firstly, corner points are applied to guide the extraction of local features inside characters, considering the robustness of corner structures to appearance and shape. In this way, the discreteness of the corner points cuts off the connection between characters, and the sparsity of them improves the robustness for background interference. Secondly, we design a character contrastive loss to model the character-level feature, improving the feature representation for character classification. Thirdly, we utilize Transformer to learn the global feature on image-level and model the global relationship of the corner points, with the assistance of a corner-query cross-attention mechanism. Besides, we provide an artistic text dataset to benchmark the performance. Experimental results verify the significant superiority of our proposed method on artistic text recognition and also achieve state-of-the-art performance on several blurred and perspective datasets., Comment: Accepted by ECCV2022 as an oral paper. The dataset and codes are available at https://github.com/xdxie/WordArt

We use scanning tunneling microscopy to study the domain structure of the nearly-commensurate charge density wave (NC-CDW) state of 1T-TaS$_2$. In our sub-angstrom characterization of the state, we find a continual evolution of the CDW lattice from domain wall to domain center, instead of a fixed CDW arrangement within a domain. Further, we uncover an intradomain chirality characterizing the NC-CDW state. Unlike the orbital-driven chirality previously observed in related transition metal dichalcogenides, the chiral nature of the NC-CDW state in 1T-TaS$_2$ appears driven by a strong coupling of the NC-CDW state to the lattice.

We apply a holistic 2D Tetris-like model, where particles move based on prescribed rules, to investigate the flow rate enhancement from a hopper. This phenomenon was originally reported in the literature as a feature of placing an obstacle at an optimal location near the exit of a hopper discharging athermal granular particles under gravity. We find that this phenomenon is limited to a system of sufficiently many particles. In addition to the waiting room effect, another mechanism able to explain and create the flow rate enhancement is the concentration mechanism of particles on their way to reaching the hopper exit after passing the obstacle. We elucidate the concentration mechanism by decomposing the flow rate into its constituent variables: the local area packing fraction $\phi_l^E$ and the averaged particle velocity $v_y^E$ at the hopper exit. In comparison to the case without an obstacle, our results show that an optimally placed obstacle can create a net flow rate enhancement of relatively weakly driven particles, caused by the exit-bottleneck coupling if $\phi_l^E > \phi_o^c$, where $\phi_o^c$ is a characteristic area packing fraction marking a transition from fast to slow flow regimes of Tetris particles. Utilizing the concentration mechanism by artificially guiding particles into the central sparse space under the obstacle or narrowing the hopper exit angle under the obstacle, we can create a man-made flow rate peak of relatively strongly-driven particles that initially exhibit no flow rate peak. Additionally, the enhanced flow rate can be maximized by an optimal obstacle shape, particle acceleration rate towards the hopper exit, or exit geometry of the hopper., Comment: 15 pages, 15 figures

In light of the rapid recent retreat of Arctic sea ice, the extreme weather events triggering the variability in Arctic ice cover has drawn increasing attention. A non-Gaussian $\alpha$-stable L\'evy process is thought to be an appropriate model to describe such extreme event. The maximal likely trajectory, based on the nonlocal Fokker-Planck equation, is applied to a nonautonomous Arctic sea ice system under $\alpha$-stable L\'evy noise. Two types of tipping times, the early-warning tipping time and the disaster-happening tipping time, are used to predict the critical time for the maximal likely transition from a perennially ice-covered state to a seasonally ice-free one, and from a seasonally ice-free state to a perennially ice-free one, respectively. We find that the increased intensity of extreme events results in shorter warning time for sea ice melting, and that an enhanced greenhouse effect will intensify this influence, making the arrival of warning time significantly earlier. Meanwhile, for the enhanced greenhouse effect, we discover that increased intensity and frequency of extreme events will advance the disaster-happening tipping time, in which an ice-free state is maintained throughout the year in the Arctic Ocean. Finally, we identify values of L\'evy index $\alpha$ and noise intensity $\epsilon$ in $\alpha \epsilon$-space that can trigger a transition between the Arctic sea ice state. These results provide an effective theoretical framework for studying Arctic sea ice variations under the influence of extreme events.