Fine-grained Details Research Articles

JGRCAN: A Visual Question Answering Co-Attention Network via Joint Grid-Region Features

In recent years, region features extracted from target detection networks have played an important role in visual question answering. The region features only extract the areas that are related to the target, but they lose a lot of nontarget context information and fine-grained details. On the contrary, the grid feature does not lose the details of nontargets but is not conducive to the recognition of the counting question of multiple small targets in the image. To solve this problem, this paper proposes a visual question answering network via joint grid-region features (JGRCAN), which consists of a feature extraction layer, co-attention layer, and fusion layer. The feature extraction layer includes extracting grid features and region features from the image and text features from the question and extracting multivisual feature representation and question feature representation through the co-attention layer to output attention weight and attention feature representation, respectively. The proposed approach effectively integrates grid features and region features, realizes the complementary advantages of region features and grid features, and is able to accurately focus on areas of the image that are relevant to the answer to the question. The results show that the overall classification accuracy of the algorithm on the test-dev and test-std subsets of VQA-v2 is 70.87% and 71.18%, respectively. Compared with baseline models, our proposed JGRCAN has good performance.

Multi-Feature Aggregation for Semantic Segmentation of an Urban Scene Point Cloud

With the rapid development of cities, semantic segmentation of urban scenes, as an important and effective imaging method, can accurately obtain the distribution information of typical urban ground features, reflecting the development scale and the level of greenery in the cities. There are some challenging problems in the semantic segmentation of point clouds in urban scenes, including different scales, imbalanced class distribution, and missing data caused by occlusion. Based on the point cloud semantic segmentation network RandLA-Net, we propose the semantic segmentation networks RandLA-Net++ and RandLA-Net3+. The RandLA-Net++ network is a deep fusion of the shallow and deep features of the point clouds, and a series of nested dense skip connections is used between the encoder and decoder. RandLA-Net3+ is based on the multi-scale connection between the encoder and decoder; it also connects internally within the decoder to capture fine-grained details and coarse-grained semantic information at a full scale. We also propose incorporating dilated convolution to increase the receptive field and compare the improvement effect of different loss functions on sample class imbalance. After verification and analysis of our labeled urban scene LiDAR point cloud dataset—called NJSeg-3D—the mIoU of the RandLA-Net++ and RandLA-Net3+ networks is 3.4% and 3.2% higher, respectively, than the benchmark network RandLA-Net.

HR-PrGAN: High-resolution story visualization with progressive generative adversarial networks

Generating a series of images to describe a story of multiple sentences is a challenging task in computer vision as it needs to consider both the image-level precision and story-level consistency. Existing methods usually focus on the consistency between images at the cost of the fine-grained object details. We propose a progressive adversarial learning algorithm, termed HR-PrGAN, to achieve high-resolution image sequences with rich details by decomposing the problem of generating into multiple stages. Specifically, HR-PrGAN has two stages, where the Coarse-grain Stage generates a series of coherent coarse-grained images from both the story and context embeddings, and an additional unconditional loss is proposed to restrict their deformation and preserve the object contours and layouts. Subsequently, the Refinement Stage further refines the series of coherent coarse-grained images by injecting the story-level text embeddings and preserving the image-level details via a Coarse-grained feature Supplementary Module (CSM). Moreover, two commonly-used datasets, i.e. the CLEVR-SV and PororoSV datasets, are applied to evaluate the proposed method. Extensive experiments demonstrate that the proposed model significantly outperforms state-of-the-art methods in terms of image anti-deformation, fine-grained feature synthesis and human perception based image quality evaluation.

Multistage Curvature-Guided Network for Progressive Single Image Reflection Removal

Thanks to the powerful learning capability, deep neural networks (DNNs) have acquired broad applications in single image reflection removal. The DNN-based algorithms relax the constraints of specific priors and learn to generate visually pleasant background layers from massive training data. However, most of them employ a single network structure to recover both the semantic information and local details of the background, which may lead to obvious reflection residue or even failure. To mitigate this deficiency, in this work, we propose a Multi-stage Curvature-guided De-Reflection Network (MCDRNet), which combines multiple network architectures in a unified framework to progressively reconstruct the background layer and refine the fine-grained details. Our framework consists of three stages, where the encoder-decoders are exploited in the first two stages to recover the semantic components of background layers with lower scales and a variant ResNet is applied in the last stage to refine the background details with the original input resolution. In the first two stages, to introduce the structural guidance for the reflection removal, we cascade another decoder branch to restore the curvature map of the background. In addition, at the end of the first two stages, instead of directly passing the intermediate estimates to the next stage, we propose a Non-local Attention Module (NAM) to augment and transmit the features from decoders. Extensive experimental results on several public datasets demonstrate that the proposed MCDRNet outperforms the state-of-the-art methods quantitatively and generates visually better reflection removal results. The source code and pre-trained models are available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/NamecantbeNULL/MCDRNet</uri> .

Local to Global Feature Learning for Salient Object Detection

• We present a novel Local to Global Feature (L2GF) Learning network for salient object detection. • We design a L-Net and a G-Net to learn local and global contexts from the low-level and high-level features, respectively. • For L-Net, it extracts coarse local context in the first stage and models the fine-grained details in the second stage. • For G-Net, the idea of modeling is from the perspective of sequence to sequence prediction to obtain global context. • We build a simple yet effective fusion branch (F-Net) to aggregate the local and global contexts for the final filtering. Existing works mainly focus on how to aggregate multi-level features for salient object detection, which may generate sub-optimal results due to interference with redundant details. To handle this problem, we aim to learn a local to global feature representation, so as to segment the detailed structures in a local perspective and locate the salient objects in a global perspective. In particular, we design a novel L2GF network which mainly consists of three modules, i.e., L-Net, G-Net, and F-Net. L-Net employs our enhanced auto-encoder structure to extract local contexts that provide rich boundary information of objects, which is able to learn rich local features in a certain receptive field. G-Net feeds the tokenized feature patches as input sequence, and leverages the well-known Transformer structure to extract global contexts which are helpful to derive the relationship between multiple salient regions and produce more complete salient results. F-Net is a coarse-to-fine process, which takes the features and maps of both local and global branches as inputs and calculate the final high-quality salient map. Extensive experiments on five benchmark datasets demonstrate that our L2GF network performs favorably against the state-of-the-art approaches.

Combining UNet 3+ and Transformer for Left Ventricle Segmentation via Signed Distance and Focal Loss

Left ventricle (LV) segmentation of cardiac magnetic resonance (MR) images is essential for evaluating cardiac function parameters and diagnosing cardiovascular diseases (CVDs). Accurate LV segmentation remains a challenge because of the large differences in cardiac structures in different research subjects. In this work, a network based on an encoder–decoder architecture for automatic LV segmentation of short-axis cardiac MR images is proposed. It combines UNet 3+ and Transformer to jointly predict the segmentation masks and signed distance maps (SDM). UNet 3+ can extract coarse-grained semantics and fine-grained details from full scales, while a Transformer is used to extract global features from cardiac MR images. It solves the problem of low segmentation accuracy caused by blurred LV edge information. Meanwhile, the SDM provides a shape-aware representation for segmentation. The performance of the proposed network is validated on the 2018 MICCAI Left Ventricle Segmentation Challenge dataset. The five-fold cross-validation evaluation was performed on 145 clinical subjects, and the average dice metric, Jaccard coefficient, accuracy, and positive predictive value reached 0.908, 0.834, 0.979, and 0.903, respectively, showing a better performance than that of other mainstream ones.

Automatic localization of target point for subthalamic nucleus-deep brain stimulation via hierarchical attention-UNet based MRI segmentation.

Deep brain stimulation of the subthalamic nucleus (STN-DBS) is an effective treatment for patients with advanced Parkinson's disease, the outcome of this surgery is highly dependent on the accurate placement of the electrode in the optimal target of STN. In this study, we aim to develop a target localization pipeline for DBS surgery, considering that the heart of this matter is to achieve the STN and red nucleus segmentation, a deep learning-based automatic segmentation approach is proposed to tackle this issue. To address the problems of ambiguous boundaries and variable shape of the segmentation targets, the hierarchical attention mechanism with two different attention strategies is integrated into an encoder-decoder network for mining both semantics and fine-grained details for segmentation. The hierarchical attention mechanism is utilized to suppress irrelevant regions in magnetic resonance (MR) images while build long-range dependency among segmentation targets. Specifically, the attention gate (AG) is integrated into low-level features to suppress irrelevant regions in an input image while highlighting the salient features useful for segmentation. Besides, the self-attention involved in the transformer block is integrated into high-level features to model the global context. Ninety-nine brain magnetic resonance imaging (MRI) studies were collected from 99 patients with Parkinson's disease undergoing STN-DBS surgery, among which 80 samples were randomly selected as the training datasets for deep learning training, and ground truths (segmentation masks) were manually generated by radiologists. We applied five-fold cross-validation on these data to train our model, the mean results on 19 test samples are used to conduct the comparison experiments, the Dice similarity coefficient (DSC), Jaccard (JA), sensitivity (SEN), and HD95 of the segmentation for STN are 88.20%, 80.32%, 90.13%, and 1.14mm, respectively, outperforming the state-of-the-art STN segmentation method with 2.82%, 4.52%, 2.56%, and 0.02mm respectively. The source code and trained models of this work have been released in the URL below: https://github.com/liuruiqiang/HAUNet/tree/master. In this study, we demonstrate the effectiveness of the hierarchical attention mechanism for building global dependency on high-level semantic features and enhancing the fine-grained details on low-level features, the experimental results show that our method has considerable superiority for STN and red nucleus segmentation, which can provide accurate target localization for STN-DBS.

Fast-HBNet: Hybrid Branch Network for Fast Lane Detection

As one of the fundamental visual tasks in the unmanned driving area, lane detection attracts increasing attention. In practical applications, lane points are very difficult to localize because they usually appear to be sparse and incomplete due to the influence of illumination and environment. Conventional lane detection methods rely on coarse features and carefully designed postprocessing to detect the lane lines. However, these methods are usually slow, and the stability and generalization ability are unsatisfactory. In this paper, we propose a novel lane detection network – Fast-HBNet(Fast-Hybrid Branch Network), which exploits both global semantic information and spatial contexts. To enlarge receptive fields and encode more detailed information, the compound transformation is employed and the proposed hybrid branch network extracts four diverse feature maps with different receptive fields and spatial contexts. Besides, we design a Hierarchical Feature Learning (HFL) module to learn lane features from the scale, channel, and spatial levels to enhance the generalization ability of our detector. These features are further selectively coalesced to generate unified lane feature maps with large receptive fields and rich detailed information. In other words, our network can encode the global semantic information from the high-resolution feature maps and the fine-grained details in the low-resolution feature maps. Experimental results conducted on the TuSimple (2017) and CULane [Pan <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">et al.</i> (2018)] datasets demonstrate that the proposed Fast-HBNet outperforms numerous state-of-the-art lane detectors in both speed and accuracy. Particularly, Fast-HBNet achieves an accuracy of 96.88% on the TuSimple dataset at a speed of 76 FPS.

Uncoupling Conceptual Understandings and Political Preferences: A Study of Democratic Attitudes among Singapore's Highly Educated Young People

Democracy is subject to constant and seemingly interminable contestation in academic and policy contexts, and yet, empirically and methodologically robust analysis of what the term means in practice for actual citizens has remained an area of relative lacuna. Admittedly, large-N surveys have attempted to address this research gap by examining attitudes to numerous components of democracy, but without the fine-grained detail required to overcome simply reproducing the focus on liberal procedural, Western precedent-based, top-down approaches to understanding such a complex and varied political system. This article proposes a methodological approach, based on the requirements of comparative political theory and research into how people view democracy. This allows us to explore political attitudes and the meaning of democracy with a bottom-up approach using the methods of repertory grid and in-depth interviews. Singapore is a particularly exciting case for comparative political science: although it has all the advantageous conditions that, according to classic modernization theory, promote the development of democracy, it is still not a democracy.&lt;br/&gt; To what extent will the conceptualization of democracy by citizens in a country like Singapore resemble theoretical definitions, and how suitable do they consider democracy to be for Singapore? What are their expectations for a good government or regime? This article examines what highly educated Singaporeans, ranging in age from their twenties to their forties, think about democracy. In doing so, the article also pursues the goal of comparing methods between repertory grid interviews and in-depth interviews in order to work out potential interfaces, and points of connection, between the two methods to allow for the most productive research outcomes. We find that, conceptually, these Singaporeans' perceptions of democracy appeared very similar to what is usually discussed as electoral democracy in established literature. When evaluating the performance of a government or a regime, however, liberal ideas of freedom and fairness competed with more pragmatic approaches that reflect the principles of progress and success as well as community and performance-focused orientations. As a result, our respondents did not prioritize democratic practices as much as other aspects of governance like e ciency. Our findings on the influence of state ideology on highly educated young people in Singapore strengthen the arguments of political myth as an integration and legitimization strategy in autocratic regimes and democratizing strong states or regimes with a particularly pronounced ideological hegemony.

Discourses of Indigenous Christian Elites in Colonial Societies in Asia and Africa around 1900: A Documentary Sourcebook from Selected Journals, edited by Klaus Koschorke et al.

For the period covered by the Sourcebook (effectively, 1885–1915), a good research library in Europe or North America will house at least a few missionary periodicals from the global South; of course, more in the digital age will be available online, making it relatively easy to read up on what it was that missionaries wanted the world to know about their work abroad. Whether they be British Anglican, American Presbyterian, or of some other denomination, home societies promoted missions through the mass distribution of foreign “intelligence” and news from the field. While it was occasionally possible to discern the voices of indigenous Christians between the lines, it was generally true that global South Christians had a hard time being heard in the missionary press.Thanks to the assiduous efforts of the chief editor, Klaus Koschorke, widely known for his advocacy of “polycentricity” as a decentered and less Eurocentric way of charting Christianity’s diffusion globally, and his team of specialist collaborators (Adrian Hermann, E. Phuti Mogase, and Ciprian Burlacioiu), we now have access to a variety of extramissionary periodicals initiated by indigenous Christians in South Asia (India), Africa (South Africa and West Africa), and Asia (the Philippines). While there are fewer than ten such periodicals, the coverage is extensive and organized by means of a helpful topical grid. Until such periodicals and others are digitized in a searchable database by the British Library or commercial providers like Proquest, this is as convenient as documentation without an index is ever going to get. As such, the volume is a welcome addition to Koschorke’s series, Documents on the History of Christianity in Asia, Africa and Latin America.In an era of world Christianity when scholarship tends to focus on disprivileged groups at the outer edges of society—due, say, to their caste or class or race or gender—the Sourcebook unabashedly amplifies the voices of a church cohort somehow perceived as “elite.” And while the qualifying criteria for meriting such a status could have been spelled out more clearly (given that perception is, of course, perspectival), it was perhaps unavoidable that such a volume would restrict itself to periodicals in the colonial lingua franca of the time (English for India, South Africa, and West Africa; Spanish for the Philippines) used in mission schools. There, graduates mastered new genres of writing, including periodicals of the kind that missionaries themselves wrote for and read, the difference being that now the voices were their own—uncensored. One might hope, as I do, that the periodicals being published concurrently in indigenous languages by traditional “elites” (the bilingual Tamil/English Morning Star, for instance, continuously published since the 1840s from Jaffna, Sri Lanka) will also find a place in a sourcebook similar to Koschorke’s. That, of course, would be a gargantuan translation project, and different from the one under review.Within its limitations, the Sourcebook opens a window widely onto the intrachurch and public square debates of a geographically diverse cohort of articulate Christians. Their aspirations (for political and ecclesiological equality, chiefly) and their vexations (mainly, but not exclusively, the racist attitudes of their missionary “superiors”) are indeed vocalized. On a whole host of collateral concerns having to do with gendered practices and the perceived clash between “tradition” and “modernity,” from marriage practices (monogamy versus polygamy, dowry versus bride-wealth) to the promotion of women’s education, one can squeeze out a great deal of fine-grained detail from the Sourcebook’s selection of periodicals.All in all, Koschorke and his collaborators brilliantly succeed in buttressing the argument for polycentricity, which necessarily entails the emergence of a “transregional ‘indigenous Christian public sphere’” (19), thus subverting the axiom that all change worth our time was missionary-initiated, North to South, instead of also South to South. Its chronological aperture may be small, but the slice of time it opens up was hardly insignificant, starting with the nascent independence struggles that colonial-era Christians endorsed and envisioned through the medium of print and ending with the global turmoil of WWI. Of the ever-widening webs of inter-Christian, global South connectivity, Koschorke rightly observes that “Africa could serve as a model for Asia” and “Asia for Africa” (19). Indian readers, for instance, yearned for bishops of their own like the Niger Delta Diocese’s Samuel Ajayi Crowther, while African readers were inspired by reading about India’s Pandita Ramabai and Japan’s Uchimura Kanzo, among other contemporaneous exemplars of faith. Overall, the Sourcebook gets us a step closer to its stated goal, that of liberating world Christianity from its captivity to Euro-dominated missionary-cum-colonial print material.

PCUNet: A Context-Aware Deep Network for Coarse-to-Fine Point Cloud Completion

Point cloud completion aims at predicting a complete 3D shape from an incomplete input. It has important applications in the fields of intelligent manufacturing, augmented reality, virtual reality, self-driving cars, and intelligent robotics. Although deep learning-based point cloud completion technology has developed rapidly in recent years, there are still unsolved problems. Previous approaches predict each point independently and ignore contextual information. And, they usually predict a complete 3D shape based on a global feature vector extracted from an incomplete input, which leads to missing of some fine-grained details. In this paper, motivated by the transposed convolution and the “UNet” structure in neural networks for image processing, we propose a context-aware deep network termed as PCUNet for coarse-to-fine point cloud completion. It adopts an encoder-decoder structure, in which the encoder follows the design of the relation-shape convolutional neural network (RS-CNN), and the decoder consists of fully-connected layers and two stacked decoder modules for predicting complete point clouds. The contributions are twofold. First, we design the decoder module as a coordinate-guided context-aware upsampling module, in which contextual information can be taken into full account by neighbor aggregation. Second, to preserve fine-grained details in the input, we propose attention-enhanced skip connections for effective information propagation from the encoder to the decoder. Experiments are conducted on the widely used PCN and KITTI datasets. The results show that our proposed approach achieves competitive performance compared to the existing state-of-the-art approaches in terms of the Chamfer distance and the computational complexity metrics.

Deeply-supervised pseudo learning with small class-imbalanced samples for hyperspectral image classification

Deep learning has been extensively applied in hyperspectral image (HSI) classification for its excellent representation ability. However, the existing training scheme generally adds a supervised classifier to the last layer of the network, so it is difficult to acquire full-scale fine-grained details and coarse-grained semantic information. Moreover, the robust performance of deep learning is commonly supported by numerous samples, so the effective discriminant features cannot be well learned with small class-imbalanced samples. To solve the above problems, a deeply-supervised pseudo learning framework (DSPL) is proposed, in which a deep supervision global learning network with pair-weighted loss is designed to achieve a stronger prediction on small class-imbalanced datasets, while this architecture of deep supervision can facilitate model generalization. To increase the diversity of samples, a semi-supervised learning method with confidence pseudo labels is proposed, capable of screening for more valid unlabeled samples and synthesizing some new mixed samples. To be more specific, the cost loss function consists of the supervised team (i.e., the labeled loss) and semi-supervised consistency regularization team (i.e., the unlabeled loss and the mixed loss), which can significantly enhance the generalization of the network by all useful samples. As revealed by the experimental results, the DSPL is better than other advanced methods on the Indian Pines (highest OA of 99.54% with 5% samples), the Pavia University (highest OA of 99.79% with 0.5% samples), as well as the Houston University 2013 (highest OA of 99.32% with 5% samples).

Discriminative Feature Mining and Enhancement Network for Low-Resolution Fine-Grained Image Recognition

Existing fine-grained image recognition methods are difficult to learn complete discriminative features from low-resolution (LR) data, because the original subtle inter-class distinctions become slimmer with the reduction of the image resolution. Besides, existing methods of LR fine-grained image recognition and general LR image recognition only consider the restoration and extraction of global discriminative features, ignoring unreliable local fine-grained details can be detrimental to final recognition. To address the above problems, we propose a multi-tasking framework, discriminative feature mining and enhancement network (DME-Net), for the LR fine-grained image recognition task, which aims to capture the reliable object descriptions from macro and micro perspectives, respectively. Macroscopically, we train the framework’s ability to recover and extract global discriminative features based on the whole images. Microscopically, we purposefully reinforce the framework’s ability to repair and capture the local discriminative details on the mined informative parts. To precisely excavate the most potential parts, we design an informative part mining (IPM) module, in which we firstly employ a part generation layer to predict several part masks that focus on different discriminative parts under the guidance of discrepancy loss and discriminant loss. Then we introduce a part selection (PS) submodule to further screen out a group of most informative parts from the predicted part masks according to their corresponding scores, which measure the semantic correlation degree of each part to the others. Experimental results on three benchmark datasets and one retail product dataset consistently show that our proposed framework can significantly boost the performance of the baseline model. Besides, extensive ablation studies are conducted, which further prove the effectiveness of each component of our designs.

Alternative Modes of Introgression-Mediated Selection Shaped Crop Adaptation to Novel Climates.

Recent plant genomic studies provide fine-grained details on the evolutionary consequences of adaptive introgression during crop domestication. Modern genomic approaches and analytical methods now make it possible to better separate the introgression signal from the demographic signal thus providing a more comprehensive and complex picture of the role of introgression in local adaptation. Adaptive introgression has been fundamental for crop expansion and has involved complex patterns of gene flow. In addition to providing new and more favorable alleles of large effect, introgression during the early stages of domestication also increased allelic diversity at adaptive loci. Previous studies have largely underestimated the effect of such increased diversity following introgression. Recent genomic studies in wheat, potato, maize, grapevine, and ryegrass show that introgression of multiple genes, of as yet unknown effect, increased the effectiveness of purifying selection, and promoted disruptive or fluctuating selection in early cultivars and landraces. Historical selection processes associated with introgression from crop wild relatives provide an instructive analog for adaptation to current climate change and offer new avenues for crop breeding research that are expected to be instrumental for strengthening food security in the coming years.

HVLM: Exploring Human-Like Visual Cognition and Language-Memory Network for Visual Dialog

Visual dialog, a visual-language task, enables an AI agent to engage in conversation with humans grounded in a given image. To generate appropriate answers for a series of questions in the dialog, the agent is required to understand the comprehensive visual content of an image and the fine-grained textual context of the dialog. However, previous studies typically utilized the object-level visual feature to represent a whole image, which only focuses on the local perspective of an image but ignores the importance of the global information in an image. In this paper, we proposed a novel model Human-Like Visual Cognitive and Language-Memory Network for Visual Dialog (HVLM), to simulate global and local dual-perspective cognitions in the human visual system and understand an image comprehensively. HVLM consists of two key modules, Local-to-Global Graph Convolutional Visual Cognition (LG-GCVC) and Question-guided Language Topic Memory (T-Mem). Specifically, in the LG-GCVC module, we design a question-guided dual-perspective reasoning to jointly learn visual contents from both local and global perspectives through a simple spectral graph convolution network. Furthermore, in the T-Mem module, we design an iterative learning strategy to gradually enhance fine-grained textual context details via an attention mechanism. Experimental results demonstrate the superiority of our proposed model, which obtains the comparable performance on benchmark datasets VisDial v1.0 and VisDial v0.9.

BIMS-PU: Bi-Directional and Multi-Scale Point Cloud Upsampling

The learning and aggregation of multi-scale features are essential in empowering neural networks to capture the fine-grained geometric details in the point cloud upsampling task. Most existing approaches extract multi-scale features from a point cloud of a fixed resolution, hence obtain only a limited level of details. Though an existing approach aggregates a feature hierarchy of different resolutions from a cascade of upsampling sub-network, the training is complex with expensive computation. To address these issues, we construct a new point cloud upsampling pipeline called BIMS-PU that integrates the feature pyramid architecture with a bi-directional up and downsampling path. Specifically, we decompose the up/downsampling procedure into several up/downsampling sub-steps by breaking the target sampling factor into smaller factors. The multi-scale features are naturally produced in a parallel manner and aggregated using a fast feature fusion method. Supervision signal is simultaneously applied to all upsampled point clouds of different scales. Moreover, we formulate a residual block to ease the training of our model. Extensive quantitative and qualitative experiments on different datasets show that our method achieves superior results to state-of-the-art approaches. Last but not least, we demonstrate that point cloud upsampling can improve robot perception by ameliorating the 3D data quality.

CACrowdGAN: Cascaded Attentional Generative Adversarial Network for Crowd Counting

Crowd counting is a valuable technology for extremely dense scenes in the transportation. Existing methods generally have higher-order inconsistencies between ground truth density maps and generated density maps. To address this issue, we incorporate an attentional discriminator to take charge of checking the density map between the generator and the ground truth. Thus, a Cascaded Attentional Generative Adversarial Network (CACrowdGAN) is proposed that enables the attentional-driven discriminator to distinguish implausible density maps and simultaneously to guide the generator to deliver fine-grained high quality density maps. The proposed CACrowdGAN consists of two components: an attentional generator and a cascaded attentional discriminator. The attentional generator has an attention module and a density module. The attention module is developed for the generator to focus on the crowd regions of the input images, while the density module is used to provide the attentional input of the discriminator. In addition, a cascaded attentional discriminator is proposed to synthesize attentional-driven fine-grained details at different crowd regions of the input image and compute a per-pixel fine-grained loss for training generator. The proposed CACrowdGAN achieves the state-of-the-art performance on five popular crowd counting datasets (ShanghaiTech, WorldEXPO’10, UCSD, UCF_CC_50 and UCF_QNRF), which demonstrates the effectiveness and robustness of the proposed approach in the complex scenes.

Approximate convex decomposition for 3D meshes with collision-aware concavity and tree search

Approximate convex decomposition aims to decompose a 3D shape into a set of almost convex components, whose convex hulls can then be used to represent the input shape. It thus enables efficient geometry processing algorithms specifically designed for convex shapes and has been widely used in game engines, physics simulations, and animation. While prior works can capture the global structure of input shapes, they may fail to preserve fine-grained details (e.g., filling a toaster's slots), which are critical for retaining the functionality of objects in interactive environments. In this paper, we propose a novel method that addresses the limitations of existing approaches from three perspectives: (a) We introduce a novel collision-aware concavity metric that examines the distance between a shape and its convex hull from both the boundary and the interior. The proposed concavity preserves collision conditions and is more robust to detect various approximation errors. (b) We decompose shapes by directly cutting meshes with 3D planes. It ensures generated convex hulls are intersection-free and avoids voxelization errors. (c) Instead of using a one-step greedy strategy, we propose employing a multi-step tree search to determine the cutting planes, which leads to a globally better solution and avoids unnecessary cuttings. Through extensive evaluation on a large-scale articulated object dataset, we show that our method generates decompositions closer to the original shape with fewer components. It thus supports delicate and efficient object interaction in downstream applications.

Cross-Species 3D Face Morphing via Alignment-Aware Controller

We address cross-species 3D face morphing (i.e., 3D face morphing from human to animal), a novel problem with promising applications in social media and movie industry. It remains challenging how to preserve target structural information and source fine-grained facial details simultaneously. To this end, we propose an Alignment-aware 3D Face Morphing (AFM) framework, which builds semantic-adaptive correspondence between source and target faces across species, via an alignment-aware controller mesh (Explicit Controller, EC) with explicit source/target mesh binding. Based on EC, we introduce Controller-Based Mapping (CBM), which builds semantic consistency between source and target faces according to the semantic importance of different face regions. Additionally, an inference-stage coarse-to-fine strategy is exploited to produce fine-grained meshes with rich facial details from rough meshes. Extensive experimental results in multiple people and animals demonstrate that our method produces high-quality deformation results.

How employees shape CSR transparency: A sensemaking perspective

Corporate Social Responsibility (CSR) transparency has predominantly been treated as an organizational outcome in previous literature. Drawing on rich qualitative data, we find that CSR transparency can emerge through sensemaking processes where employees are instrumental in exercising moral judgements, engaging with stakeholders, and creating shared narratives. The study contributes to our understanding of CSR transparency by showing that the phenomenon is reflected by social processes and should not be narrowly conceptualized as an outcome of information disclosure at the corporate level. The study also provides fine-grained details about the cognitive and organizational mechanisms at play in the shaping of CSR transparency. Specifically, we introduce a bottom-up model which explains how reserved and non-reserved approaches of CSR transparency are developed.