We examine online art challenges and their role in encouraging creative practice within online creative communities. While social media platforms often prioritize performance and visibility over unpolished creative work, online art challenge communities persist as community-driven practices that provide structure and connection. Through a qualitative analysis of 17 semi-structured interviews with artists, we explore the motivations, tensions, and practices that shape participation in online art challenge communities. We establish a design space for online art challenges and highlight the value of its different dimensions. Our findings show the importance of supporting sustainable creative practice, as well as the tensions artists face when sharing on large social media platforms. Based on these insights, we identify design directions to better support sustainable creative practice in online art challenges and similar creative communities.

In recent years, adaptive optimization methods for deep learning have attracted considerable attention. AMSGRAD indicates that the adaptive methods may be hard to converge to optimal solutions of some convex problems due to the divergence of its adaptive learning rate as in ADAM. However, we find that AMSGRAD may generalize worse than ADAM for some deep learning tasks. We first show that AMSGRAD may not find a flat minimum. So how can we design an optimization method to find a flat minimum with low training loss? Few works focus on this important problem. We propose a novel progressive weighted adaptive optimization algorithm, called PWPROP, with fewer hyperparameters than its counterparts such as ADAM. By intuitively constructing a “sharp-flat minima” model, we show that how different second-order estimates affect the ability to escape a sharp minimum. Moreover, we also prove that PWPROP can address the non-convergence issue of ADAM and has a sublinear convergence rate for non-convex problems. Extensive experimental results show that PWPROP is effective and suitable for various deep learning architectures such as Transformer, and achieves state-of-the-art results.

Video-based person re-identification (Re-ID) aims at retrieving the person through the video sequences across non-overlapping cameras. Some characteristics of pedestrians are not consecutive across frames due to the variations of viewpoints, postures, and occlusions over time. However, existing methods ignore such data peculiarity and the networks tend to only learn those salient consecutive characteristics among frames in video sequences. As a result, the learned representations fail to cover all the characteristics of pedestrians, thus lacking integrity and discrimination. To tackle this problem, we present a novel deep architecture termed Hierarchical Mining Network (HMN), which mines as many pedestrians’ characteristics by referring to the temporal and intra-class knowledge. It consists of a novel Attentive Temporal Module (ATM) and a Dynamic Supervising Branch (DSB), with a Balancing Triplet Loss (BTL) assisting the training. The proposed ATM, with pedestrian perceiving capacity, is capable of evaluating each activation of features through temporal analysis, so that the temporally scattered characteristics of pedestrians can be better aggregated and the contaminated ones can be eliminated. Then, the DSB along with the BTL further enhances the integrity of representations by multiple supervision. Specifically, the DSB perceives the diversities of intra-class samples in each mini-batch and generates targeted supervising signals for them, in which process the BTL guarantees the signals with smaller intra-class variations and larger inter-class variations. Comprehensive experiments on two video-based datasets, i.e., MARS, and DukeMTMC-VideoReID, demonstrate the contribution of each component and the superiority of the proposed HMN over the state-of-the-arts. Benchmarking our model on three popular image-based datasets, i.e., Market1501, DukeMTMC-Reid, and MSMT17 additionally verifies the promising generalizability of the proposed DSB and BTL.

We consider weakly-supervised video anomaly detection in this work. This task aims to learn to localize video frames containing anomaly events with only binary video-level annotation,i.e., anomaly vs. normal. Traditional approaches usually formulate it as a multiple instance learning problem, which ignore the intrinsic data imbalance issue that positive samples are very scarce compared to negative ones. In this paper, we focus on addressing this issue to boost detection performance further. We develop a new light-weight anomaly detection model that fully utilizes enough normal videos to train a classifier with a good discriminative ability for normal videos, and we employ it to improve the selectivity for anomalous segments and filter out normal segments. Specifically, in addition to boosting anomalous prediction, a novel contrastive attention module additionally produces a converted normal feature from anomalous video to refined anomalous predictions by maximizing the classifier making a mistake. Moreover, to remove the stubborn normal segments selected by the attention module, we also design an attention consistency loss to employ the classifier with high confidence for normal features to guide the attention module. Extensive experiments on two large-scale datasets, UCF-Crime, ShanghaiTech and XD-Violence, clearly demonstrate that our model largely improves frame-level AUC over the state-of-the-art. Code is released athttps://github.com/changsn/Contrastive-Attention-for-Video-Anomaly-Detection.

This article presents a modular lightweight network model for road objects detection, such as car, pedestrian, and cyclist, especially when they are far away from the camera and their sizes are small. Great advances have been made for the deep networks, but small objects detection is still a challenging task. In order to solve this problem, a majority of existing methods utilize complicated network or bigger image size, which generally leads to higher computation cost. The proposed network model is referred to as modular feature fusion detector (MFFD), using a fast and efficient network architecture for detecting small objects. The contribution lies in the following aspects: 1) two base modules have been designed for efficient computation: a) Front module reduces the information loss from raw input images and b) Tinier module decreases the model size and computation cost, while ensuring the detection accuracy; 2) by stacking the base modules, we design a context features fusion framework for multiscale object detection; and 3) the proposed method is efficient in terms of model size and computation cost, which is applicable for resource-limited devices, such as embedded systems for advanced driver-assistance systems (ADASs). Comparisons with the state-of-the-art on the challenging KITTI dataset reveal the superiority of the proposed method. Especially, 100 ft/s can be achieved on the embedded GPUs such as Jetson TX2.

In this paper, we study a novel technique that exploits the interaction between speaker traits and linguistic content to improve both speaker verification and utterance verification performance. We implement an idea of speaker-utterance dual attention (SUDA) in a unified neural network. The dual attention refers to an attention mechanism for the two tasks of speaker and utterance verification. The proposed SUDA features an attention mask mechanism to learn the interaction between the speaker and utterance information streams. This helps to focus only on the required information for respective task by masking the irrelevant counterparts. The studies conducted on RSR2015 corpus confirm that the proposed SUDA outperforms the framework without attention mask as well as several competitive systems for both speaker and utterance verification.

Three‐dimensional (3D) driver pose estimation is a promising and challenging problem for computer–human interaction. Recently convolutional neural networks have been introduced into 3D pose estimation, but these methods have the problem of slow running speed and are not suitable for driving scenario. In this study, the proposed method is based on two types of inputs, infrared image and point cloud obtained from time‐of‐flight camera. The authors propose a joint 2D–3D network incorporating image‐based and point‐based feature to promote the performance of 3D human pose estimation and run on a high speed. For point cloud with invalid points, the authors first do preprocess and then design a denoising module to handle this problem. Experiments on private driver data set and public Invariant‐Top View data set show that the proposed method achieves efficient and competitive performance on 3D human pose estimation.

3D driver pose estimation is a promising and challenging problem for computer-human interaction. Recently convolutional neural networks (CNNs) have been introduced into 3D pose estimation, but these methods have the problem of slow running speed and are not suitable for driving scenario. In this paper, our method is based on two type of inputs, IR image and point cloud obtained from TOF camera. We propose a Joint 2D-3D network incorporating image-based and point-based feature to promote the performance of 3D human pose estimation and run in a high speed. For point cloud with invalid points, we firstly do preprocess and then design a denoising module to handle this problem. Experiments on private Driver dataset and public ITOP dataset show that our method achieves efficient and competitive performance on 3D human pose estimation.

This paper introduces our submission to the Grand Challenges on Vehicle Re-Identification (ReID) held in the VCIP 2019. Vehicle Re-Identification, which aims to retrieve images of a query vehicle from a large-scale vehicle database, is of great significance to the urban security and city management. Although significant progress has been made in the last decade, vehicle ReID in the wild remains a very challenging problem due to the large intra-class variations of one vehicle instance from viewpoint, illumination, occlusion patterns, and the possibly small inter-class differentiation of different vehicle instances (e.g., two different vehicles of the same model and color). To deal with these challenges, we in this work present a vehicle ReID framework that integrates both the global visual cues along with the local part-based cues to learn discriminative feature representations. In addition, the proposed framework also makes use of the extra information such as brands, models and colors to further improve the performance. Experimental results are performed on the VCIP 2019 VehicleReID dataset and the proposed framework achieved the second place in the competition.

Driver poses recognition contains three tasks such as body joint, head angle, and face landmark estimation, which is of paramount interest for the advanced driver assistance systems (ADAS). Recently proposed methods intend to use deeper and more complicated networks to achieve better performance, which leads to heavy models that are not feasible for the resource limited applications such as ADAS. To resolve this issue, we have worked on the following aspects: 1) a lightweight network model, which is referred to as recurrent multi-task thin net (RM-ThinNet), has been proposed which was especially designed for the computationally and memory limited devices; 2) a recurrent structure has been introduced to handle the scale difference and dependency between different tasks, and this recurrence ensures the different tasks are accomplished at different stages and their outputs can augment each other; and 3) a virtual data synthesization pipeline and a couple transfer learning method have been presented, by which network can be learnt effectively by relatively a small number of real data. Comparisons with the state-of-the-art methods reveal the superiority of the proposed method and competitive performance can be achieved with smaller model size and faster speed.

Pose variation is one key challenge in face recognition. As opposed to current techniques for pose invariant face recognition, which either directly extract pose invariant features for recognition, or first normalize profile face images to frontal pose before feature extraction, we argue that it is more desirable to perform both tasks jointly to allow them to benefit from each other. To this end, we propose a Pose Invariant Model (PIM) for face recognition in the wild, with three distinct novelties. First, PIM is a novel and unified deep architecture, containing a Face Frontalization sub-Net (FFN) and a Discriminative Learning sub-Net (DLN), which are jointly learned from end to end. Second, FFN is a well-designed dual-path Generative Adversarial Network (GAN) which simultaneously perceives global structures and local details, incorporated with an unsupervised cross-domain adversarial training and a "learning to learn" strategy for high-fidelity and identity-preserving frontal view synthesis. Third, DLN is a generic Convolutional Neural Network (CNN) for face recognition with our enforced cross-entropy optimization strategy for learning discriminative yet generalized feature representation. Qualitative and quantitative experiments on both controlled and in-the-wild benchmarks demonstrate the superiority of the proposed model over the state-of-the-arts.

Great advances have been made for the deep networks, but relatively high memory and computation requirements limit their applications in the embedded device. In this paper, we introduce a class of efficient network architecture named ThinNet mainly for object detection applications on memory and computation limited platforms. The new architecture is based on two proposed modules: Front module and Tinier module. The Front module reduce the information loss from raw input images by utilizing more convolution layers with small size filters. The Tinier module use pointwise convolution layers before conventional convolution layer to decrease model size and computation, while ensuring the detection accuracy. Experimental evaluations on ImageNet classification and PASCAL VOC object detection datasets demonstrate the superior performance of ThinNet over other popular models. Our pretrained classification model(ThinNet_C) attains the same top-l and top-5 performance as the classic AlexNet but only with 1/50th the parameters. The detection model also obtains significant improvements over other detection methods, while requiring smaller model size to achieve high performance.

Learning from synthetic faces, though perhaps appealing for high data efficiency, may not bring satisfactory performance due to the distribution discrepancy of the synthetic and real face images. To mitigate this gap, we propose a 3D-Aided Deep Pose-Invariant Face Recognition Model (3D-PIM), which automatically recovers realistic frontal faces from arbitrary poses through a 3D face model in a novel way. Specifically, 3D-PIM incorporates a simulator with the aid of a 3D Morphable Model (3D MM) to obtain shape and appearance prior for accelerating face normalization learning, requiring less training data. It further leverages a global-local Generative Adversarial Network (GAN) with multiple critical improvements as a refiner to enhance the realism of both global structures and local details of the face simulator’s output using unlabelled real data only, while preserving the identity information. Qualitative and quantitative experiments on both controlled and in-the-wild benchmarks clearly demonstrate superiority of the proposed model over state-of-the-arts.

In this paper, we consider the problem of pedestrian detection in natural scenes. Intuitively, instances of pedestrians with different spatial scales may exhibit dramatically different features. Thus, large variance in instance scales, which results in undesirable large intracategory variance in features, may severely hurt the performance of modern object instance detection methods. We argue that this issue can be substantially alleviated by the divide-and-conquer philosophy. Taking pedestrian detection as an example, we illustrate how we can leverage this philosophy to develop a Scale-Aware Fast R-CNN (SAF R-CNN) framework. The model introduces multiple built-in subnetworks which detect pedestrians with scales from disjoint ranges. Outputs from all of the subnetworks are then adaptively combined to generate the final detection results that are shown to be robust to large variance in instance scales, via a gate function defined over the sizes of object proposals. Extensive evaluations on several challenging pedestrian detection datasets well demonstrate the effectiveness of the proposed SAF R-CNN. Particularly, our method achieves state-of-the-art performance on Caltech, and obtains competitive results on INRIA, ETH, and KITTI.

This paper presents the techniques used in our contribution to Emotion Recognition in the Wild 2017 video based sub-challenge. The purpose of the sub-challenge is to classify the six basic emotions (angry, sad, happy, surprise, fear and disgust) and neutral. Our proposed solution utilizes three state-of-the-arts techniques to overcome the challenges for the wild emotion recognition. Deep network transfer learning is used for feature extraction. Spatial-temporal model fusion is to make full use of the complementary of different networks. Semi-auto reinforcement learning is for the optimization of fusion strategy based on dynamic outside feedbacks given by challenge organizers. The overall accuracy of the proposed approach on the challenge test dataset is 57.2%, which is better than the challenge baseline of 40.47% .

Synthesizing realistic profile faces is promising for more efficiently training deep pose-invariant models for large-scale unconstrained face recognition, by populating samples with extreme poses and avoiding tedious annotations. However, learning from synthetic faces may not achieve the desired performance due to the discrepancy between distributions of the synthetic and real face images. To narrow this gap, we propose a Dual-Agent Generative Adversarial Network (DA-GAN) model, which can improve the realism of a face simulator's output using unlabeled real faces, while preserving the identity information during the realism refinement. The dual agents are specifically designed for distinguishing real v.s. fake and identities simultaneously. In particular, we employ an off-the-shelf 3D face model as a simulator to generate profile face images with varying poses. DA-GAN leverages a fully convolutional network as the generator to generate high-resolution images and an auto-encoder as the discriminator with the dual agents. Besides the novel architecture, we make several key modifications to the standard GAN to preserve pose and texture, preserve identity and stabilize training process: (i) a pose perception loss; (ii) an identity perception loss; (iii) an adversarial loss with a boundary equilibrium regularization term. Experimental results show that DA-GAN not only presents compelling perceptual results but also significantly outperforms state-of-the-arts on the large-scale and challenging NIST IJB-A unconstrained face recognition benchmark. In addition, the proposed DA-GAN is also promising as a new approach for solving generic transfer learning problems more effectively.

This paper describes our proposed method targeting at the MSR Image Recognition Challenge MS-Celeb-1M. The challenge is to recognize one million celebrities from their face images captured in the real world. The challenge provides a large scale dataset crawled from the Web, which contains a large number of celebrities with many images for each subject. Given a new testing image, the challenge requires an identify for the image and the corresponding confidence score. To complete the challenge, we propose a two-stage approach consisting of data cleaning and multi-view deep representation learning. The data cleaning can effectively reduce the noise level of training data and thus improves the performance of deep learning based face recognition models. The multi-view representation learning enables the learned face representations to be more specific and discriminative. Thus the difficulties of recognizing faces out of a huge number of subjects are substantially relieved. Our proposed method achieves a coverage of 46.1% at 95% precision on the random set and a coverage of 33.0% at 95% precision on the hard set of this challenge.