Suiyi Ling

Suiyi Ling, Andreas Pastor, Junle Wang et al.

How to robustly rank the aesthetic quality of given images has been a long-standing ill-posed topic. Such challenge stems mainly from the diverse subjective opinions of different observers about the varied types of content. There is a growing interest in estimating the user agreement by considering the standard deviation of the scores, instead of only predicting the mean aesthetic opinion score. Nevertheless, when comparing a pair of contents, few studies consider how confident are we regarding the difference in the aesthetic scores. In this paper, we thus propose (1) a re-adapted multi-task attention network to predict both the mean opinion score and the standard deviation in an end-to-end manner; (2) a brand-new confidence interval ranking loss that encourages the model to focus on image-pairs that are less certain about the difference of their aesthetic scores. With such loss, the model is encouraged to learn the uncertainty of the content that is relevant to the diversity of observers' opinions, i.e., user disagreement. Extensive experiments have demonstrated that the proposed multi-task aesthetic model achieves state-of-the-art performance on two different types of aesthetic datasets, i.e., AVA and TMGA.

Tristan Gomez, Suiyi Ling, Thomas Fréour et al.

The prevalence of employing attention mechanisms has brought along concerns on the interpretability of attention distributions. Although it provides insights about how a model is operating, utilizing attention as the explanation of model predictions is still highly dubious. The community is still seeking more interpretable strategies for better identifying local active regions that contribute the most to the final decision. To improve the interpretability of existing attention models, we propose a novel Bilinear Representative Non-Parametric Attention (BR-NPA) strategy that captures the task-relevant human-interpretable information. The target model is first distilled to have higher-resolution intermediate feature maps. From which, representative features are then grouped based on local pairwise feature similarity, to produce finer-grained, more precise attention maps highlighting task-relevant parts of the input. The obtained attention maps are ranked according to the activity level of the compound feature, which provides information regarding the important level of the highlighted regions. The proposed model can be easily adapted in a wide variety of modern deep models, where classification is involved. Extensive quantitative and qualitative experiments showcase more comprehensive and accurate visual explanations compared to state-of-the-art attention models and visualizations methods across multiple tasks including fine-grained image classification, few-shot classification, and person re-identification, without compromising the classification accuracy. The proposed visualization model sheds imperative light on how neural networks `pay their attention' differently in different tasks.

Kevin Riou, Suiyi Ling, Guillaume Gallot et al.

Human is able to conduct 3D recognition by a limited number of haptic contacts between the target object and his/her fingers without seeing the object. This capability is defined as `haptic glance' in cognitive neuroscience. Most of the existing 3D recognition models were developed based on dense 3D data. Nonetheless, in many real-life use cases, where robots are used to collect 3D data by haptic exploration, only a limited number of 3D points could be collected. In this study, we thus focus on solving the intractable problem of how to obtain cognitively representative 3D key-points of a target object with limited interactions between the robot and the object. A novel reinforcement learning based framework is proposed, where the haptic exploration procedure (the agent iteratively predicts the next position for the robot to explore) is optimized simultaneously with the objective 3D recognition with actively collected 3D points. As the model is rewarded only when the 3D object is accurately recognized, it is driven to find the sparse yet efficient haptic-perceptual 3D representation of the object. Experimental results show that our proposed model outperforms the state of the art models.

Zhenyu Lei, Yejing Xie, Suiyi Ling et al.

With the proliferation of various gaming technology, services, game styles, and platforms, multi-dimensional aesthetic assessment of the gaming contents is becoming more and more important for the gaming industry. Depending on the diverse needs of diversified game players, game designers, graphical developers, etc. in particular conditions, multi-modal aesthetic assessment is required to consider different aesthetic dimensions/perspectives. Since there are different underlying relationships between different aesthetic dimensions, e.g., between the `Colorfulness' and `Color Harmony', it could be advantageous to leverage effective information attached in multiple relevant dimensions. To this end, we solve this problem via multi-task learning. Our inclination is to seek and learn the correlations between different aesthetic relevant dimensions to further boost the generalization performance in predicting all the aesthetic dimensions. Therefore, the `bottleneck' of obtaining good predictions with limited labeled data for one individual dimension could be unplugged by harnessing complementary sources of other dimensions, i.e., augment the training data indirectly by sharing training information across dimensions. According to experimental results, the proposed model outperforms state-of-the-art aesthetic metrics significantly in predicting four gaming aesthetic dimensions.

Shaoguo Wen, Suiyi Ling, Junle Wang et al.

Nowadays, with the vigorous expansion and development of gaming video streaming techniques and services, the expectation of users, especially the mobile phone users, for higher quality of experience is also growing swiftly. As most of the existing research focuses on traditional video streaming, there is a clear lack of both subjective study and objective quality models that are tailored for quality assessment of mobile gaming content. To this end, in this study, we first present a brand new Tencent Gaming Video dataset containing 1293 mobile gaming sequences encoded with three different codecs. Second, we propose an objective quality framework, namely Efficient hard-RAnk Quality Estimator (ERAQUE), that is equipped with (1) a novel hard pairwise ranking loss, which forces the model to put more emphasis on differentiating similar pairs; (2) an adapted model distillation strategy, which could be utilized to compress the proposed model efficiently without causing significant performance drop. Extensive experiments demonstrate the efficiency and robustness of our model.

Kevin Riou, Jingwen Zhu, Suiyi Ling et al.

Confinement during COVID-19 has caused serious effects on agriculture all over the world. As one of the efficient solutions, mechanical harvest/auto-harvest that is based on object detection and robotic harvester becomes an urgent need. Within the auto-harvest system, robust few-shot object detection model is one of the bottlenecks, since the system is required to deal with new vegetable/fruit categories and the collection of large-scale annotated datasets for all the novel categories is expensive. There are many few-shot object detection models that were developed by the community. Yet whether they could be employed directly for real life agricultural applications is still questionable, as there is a context-gap between the commonly used training datasets and the images collected in real life agricultural scenarios. To this end, in this study, we present a novel cucumber dataset and propose two data augmentation strategies that help to bridge the context-gap. Experimental results show that 1) the state-of-the-art few-shot object detection model performs poorly on the novel `cucumber' category; and 2) the proposed augmentation strategies outperform the commonly used ones.

Suiyi Ling, Jing Li, Anne Flore Perrin et al.

The development of rigorous quality assessment model relies on the collection of reliable subjective data, where the perceived quality of visual multimedia is rated by the human observers. Different subjective assessment protocols can be used according to the objectives, which determine the discriminability and accuracy of the subjective data. Single stimulus methodology, e.g., the Absolute Category Rating (ACR) has been widely adopted due to its simplicity and efficiency. However, Pair Comparison (PC) is of significant advantage over ACR in terms of discriminability. In addition, PC avoids the influence of observers' bias regarding their understanding of the quality scale. Nevertheless, full pair comparison is much more time-consuming. In this study, we therefore 1) employ a generic model to bridge the pair comparison data and ACR data, where the variance term could be recovered and the obtained information is more complete; 2) propose a fusion strategy to boost pair comparisons by utilizing the ACR results as initialization information; 3) develop a novel active batch sampling strategy based on Minimum Spanning Tree (MST) for PC. In such a way, the proposed methodology could achieve the same accuracy of pair comparison but with the compelxity as low as ACR. Extensive experimental results demonstrate the efficiency and accuracy of the proposed approach, which outperforms the state of the art approaches.

Jing Li, Suiyi Ling, Junle Wang et al.

In the big data era, data labeling can be obtained through crowdsourcing. Nevertheless, the obtained labels are generally noisy, unreliable or even adversarial. In this paper, we propose a probabilistic graphical annotation model to infer the underlying ground truth and annotator's behavior. To accommodate both discrete and continuous application scenarios (e.g., classifying scenes vs. rating videos on a Likert scale), the underlying ground truth is considered following a distribution rather than a single value. In this way, the reliable but potentially divergent opinions from "good" annotators can be recovered. The proposed model is able to identify whether an annotator has worked diligently towards the task during the labeling procedure, which could be used for further selection of qualified annotators. Our model has been tested on both simulated data and real-world data, where it always shows superior performance than the other state-of-the-art models in terms of accuracy and robustness.

Zhaohui Che, Ali Borji, Guangtao Zhai et al.

Deep neural networks are vulnerable to adversarial attacks.

Jiahua Xu, Wei Zhou, Zhibo Chen et al.

Stereoscopic image quality measurement (SIQM) has become increasingly important for guiding stereo image processing and commutation systems due to the widespread usage of 3D contents. Compared with conventional methods which are relied on hand-crafted features, deep learning oriented measurements have achieved remarkable performance in recent years. However, most existing deep SIQM evaluators are not specifically built for stereoscopic contents and consider little prior domain knowledge of the 3D human visual system (HVS) in network design. In this paper, we develop a Predictive Auto-encoDing Network (PAD-Net) for blind/No-Reference stereoscopic image quality measurement. In the first stage, inspired by the predictive coding theory that the cognition system tries to match bottom-up visual signal with top-down predictions, we adopt the encoder-decoder architecture to reconstruct the distorted inputs. Besides, motivated by the binocular rivalry phenomenon, we leverage the likelihood and prior maps generated from the predictive coding process in the Siamese framework for assisting SIQM. In the second stage, quality regression network is applied to the fusion image for acquiring the perceptual quality prediction. The performance of PAD-Net has been extensively evaluated on three benchmark databases and the superiority has been well validated on both symmetrically and asymmetrically distorted stereoscopic images under various distortion types.

Zhaohui Che, Ali Borji, Guangtao Zhai et al.

Currently, a plethora of saliency models based on deep neural networks have led great breakthroughs in many complex high-level vision tasks (e.g. scene description, object detection). The robustness of these models, however, has not yet been studied. In this paper, we propose a sparse feature-space adversarial attack method against deep saliency models for the first time. The proposed attack only requires a part of the model information, and is able to generate a sparser and more insidious adversarial perturbation, compared to traditional image-space attacks. These adversarial perturbations are so subtle that a human observer cannot notice their presences, but the model outputs will be revolutionized. This phenomenon raises security threats to deep saliency models in practical applications. We also explore some intriguing properties of the feature-space attack, e.g. 1) the hidden layers with bigger receptive fields generate sparser perturbations, 2) the deeper hidden layers achieve higher attack success rates, and 3) different loss functions and different attacked layers will result in diverse perturbations. Experiments indicate that the proposed method is able to successfully attack different model architectures across various image scenes.

Suiyi Ling, Jing Li, Zhaohui Che et al.

Virtual viewpoints synthesis is an essential process for many immersive applications including Free-viewpoint TV (FTV). A widely used technique for viewpoints synthesis is Depth-Image-Based-Rendering (DIBR) technique. However, such techniques may introduce challenging non-uniform spatial-temporal structure-related distortions. Most of the existing state-of-the-art quality metrics fail to handle these distortions, especially the temporal structure inconsistencies observed during the switch of different viewpoints. To tackle this problem, an elastic metric and multi-scale trajectory based video quality metric (EM-VQM) is proposed in this paper. Dense motion trajectory is first used as a proxy for selecting temporal sensitive regions, where local geometric distortions might significantly diminish the perceived quality. Afterwards, the amount of temporal structure inconsistencies and unsmooth viewpoints transitions are quantified by calculating 1) the amount of motion trajectory deformations with elastic metric and, 2) the spatial-temporal structural dissimilarity. According to the comprehensive experimental results on two FTV video datasets, the proposed metric outperforms the state-of-the-art metrics designed for free-viewpoint videos significantly and achieves a gain of 12.86% and 16.75% in terms of median Pearson linear correlation coefficient values on the two datasets compared to the best one, respectively.

Suiyi Ling, Jing Li, Junle Wang et al.

In this paper, we proposed a no-reference (NR) quality metric for RGB plus image-depth (RGB-D) synthesis images based on Generative Adversarial Networks (GANs), namely GANs-NQM. Due to the failure of the inpainting on dis-occluded regions in RGB-D synthesis process, to capture the non-uniformly distributed local distortions and to learn their impact on perceptual quality are challenging tasks for objective quality metrics. In our study, based on the characteristics of GANs, we proposed i) a novel training strategy of GANs for RGB-D synthesis images using existing large-scale computer vision datasets rather than RGB-D dataset; ii) a referenceless quality metric based on the trained discriminator by learning a `Bag of Distortion Word' (BDW) codebook and a local distortion regions selector; iii) a hole filling inpainter, i.e., the generator of the trained GANs, for RGB-D dis-occluded regions as a side outcome. According to the experimental results on IRCCyN/IVC DIBR database, the proposed model outperforms the state-of-the-art quality metrics, in addition, is more applicable in real scenarios. The corresponding context inpainter also shows appealing results over other inpainting algorithms.

Jing Li, Rafal K. Mantiuk, Junle Wang et al.

In this paper we present a hybrid active sampling strategy for pairwise preference aggregation, which aims at recovering the underlying rating of the test candidates from sparse and noisy pairwise labelling. Our method employs Bayesian optimization framework and Bradley-Terry model to construct the utility function, then to obtain the Expected Information Gain (EIG) of each pair. For computational efficiency, Gaussian-Hermite quadrature is used for estimation of EIG. In this work, a hybrid active sampling strategy is proposed, either using Global Maximum (GM) EIG sampling or Minimum Spanning Tree (MST) sampling in each trial, which is determined by the test budget. The proposed method has been validated on both simulated and real-world datasets, where it shows higher preference aggregation ability than the state-of-the-art methods.

Suiyi Ling, Jesús Gutiérrez, Gu Ke et al.

Free-Viewpoint Video (FVV) systems allow the viewers to freely change the viewpoints of the scene. In such systems, view synthesis and compression are the two main sources of artifacts influencing the perceived quality. To assess this influence, quality evaluation studies are often carried out using conventional displays and generating predefined navigation trajectories mimicking the possible movement of the viewers when exploring the content. Nevertheless, as different trajectories may lead to different conclusions in terms of visual quality when benchmarking the performance of the systems, methods to identify critical trajectories are needed. This paper aims at exploring the impact of exploration trajectories (defined as Hypothetical Rendering Trajectories: HRT) on perceived quality of FVV subjectively and objectively, providing two main contributions. Firstly, a subjective assessment test including different HRTs was carried out and analyzed. The results demonstrate and quantify the influence of HRT in the perceived quality. Secondly, we propose a new objective video quality assessment measure to objectively predict the impact of HRT. This measure, based on Sketch-Token representation, models how the categories of the contours change spatially and temporally from a higher semantic level. Performance in comparison with existing quality metrics for FVV, highlight promising results for automatic detection of most critical HRTs for the benchmark of immersive systems.