Anurag Ranjan, J. Janai, Andreas Geiger, Michael J. Black
Deep neural nets achieve state-of-the-art performance on the problem of optical flow estimation. Since optical flow is used in several safety-critical applications like self-driving cars, it is important to gain insights into the robustness of those techniques. Recently, it has been shown that adversarial attacks easily fool deep neural networks to misclassify objects. The robustness of optical flow networks to adversarial attacks, however, has not been studied so far. In this paper, we extend adversarial patch attacks to optical flow networks and show that such attacks can compromise their performance. We show that corrupting a small patch of less than 1% of the image size can significantly affect optical flow estimates. Our attacks lead to noisy flow estimates that extend significantly beyond the region of the attack, in many cases even completely erasing the motion of objects in the scene. While networks using an encoder-decoder architecture are very sensitive to these attacks, we found that networks using a spatial pyramid architecture are less affected. We analyse the success and failure of attacking both architectures by visualizing their feature maps and comparing them to classical optical flow techniques which are robust to these attacks. We also demonstrate that such attacks are practical by placing a printed pattern into real scenes.
{"title":"Attacking Optical Flow","authors":"Anurag Ranjan, J. Janai, Andreas Geiger, Michael J. Black","doi":"10.1109/ICCV.2019.00249","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00249","url":null,"abstract":"Deep neural nets achieve state-of-the-art performance on the problem of optical flow estimation. Since optical flow is used in several safety-critical applications like self-driving cars, it is important to gain insights into the robustness of those techniques. Recently, it has been shown that adversarial attacks easily fool deep neural networks to misclassify objects. The robustness of optical flow networks to adversarial attacks, however, has not been studied so far. In this paper, we extend adversarial patch attacks to optical flow networks and show that such attacks can compromise their performance. We show that corrupting a small patch of less than 1% of the image size can significantly affect optical flow estimates. Our attacks lead to noisy flow estimates that extend significantly beyond the region of the attack, in many cases even completely erasing the motion of objects in the scene. While networks using an encoder-decoder architecture are very sensitive to these attacks, we found that networks using a spatial pyramid architecture are less affected. We analyse the success and failure of attacking both architectures by visualizing their feature maps and comparing them to classical optical flow techniques which are robust to these attacks. We also demonstrate that such attacks are practical by placing a printed pattern into real scenes.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"7 1","pages":"2404-2413"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82552863","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Daiqian Ma, Renjie Wan, Boxin Shi, A. Kot, Ling-yu Duan
Existing learning-based single image reflection removal methods using paired training data have fundamental limitations about the generalization capability on real-world reflections due to the limited variations in training pairs. In this work, we propose to jointly generate and separate reflections within a weakly-supervised learning framework, aiming to model the reflection image formation more comprehensively with abundant unpaired supervision. By imposing the adversarial losses and combinable mapping mechanism in a multi-task structure, the proposed framework elegantly integrates the two separate stages of reflection generation and separation into a unified model. The gradient constraint is incorporated into the concurrent training process of the multi-task learning as well. In particular, we built up an unpaired reflection dataset with 4,027 images, which is useful for facilitating the weakly-supervised learning of reflection removal model. Extensive experiments on a public benchmark dataset show that our framework performs favorably against state-of-the-art methods and consistently produces visually appealing results.
{"title":"Learning to Jointly Generate and Separate Reflections","authors":"Daiqian Ma, Renjie Wan, Boxin Shi, A. Kot, Ling-yu Duan","doi":"10.1109/ICCV.2019.00253","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00253","url":null,"abstract":"Existing learning-based single image reflection removal methods using paired training data have fundamental limitations about the generalization capability on real-world reflections due to the limited variations in training pairs. In this work, we propose to jointly generate and separate reflections within a weakly-supervised learning framework, aiming to model the reflection image formation more comprehensively with abundant unpaired supervision. By imposing the adversarial losses and combinable mapping mechanism in a multi-task structure, the proposed framework elegantly integrates the two separate stages of reflection generation and separation into a unified model. The gradient constraint is incorporated into the concurrent training process of the multi-task learning as well. In particular, we built up an unpaired reflection dataset with 4,027 images, which is useful for facilitating the weakly-supervised learning of reflection removal model. Extensive experiments on a public benchmark dataset show that our framework performs favorably against state-of-the-art methods and consistently produces visually appealing results.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"453 1","pages":"2444-2452"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82932267","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
H. Ge, Zehang Yan, Kai Zhang, Mingde Zhao, Liang Sun
Image captioning is a research hotspot where encoder-decoder models combining convolutional neural network (CNN) and long short-term memory (LSTM) achieve promising results. Despite significant progress, these models generate sentences differently from human cognitive styles. Existing models often generate a complete sentence from the first word to the end, without considering the influence of the following words on the whole sentence generation. In this paper, we explore the utilization of a human-like cognitive style, i.e., building overall cognition for the image to be described and the sentence to be constructed, for enhancing computer image understanding. This paper first proposes a Mutual-aid network structure with Bidirectional LSTMs (MaBi-LSTMs) for acquiring overall contextual information. In the training process, the forward and backward LSTMs encode the succeeding and preceding words into their respective hidden states by simultaneously constructing the whole sentence in a complementary manner. In the captioning process, the LSTM implicitly utilizes the subsequent semantic information contained in its hidden states. In fact, MaBi-LSTMs can generate two sentences in forward and backward directions. To bridge the gap between cross-domain models and generate a sentence with higher quality, we further develop a cross-modal attention mechanism to retouch the two sentences by fusing their salient parts as well as the salient areas of the image. Experimental results on the Microsoft COCO dataset show that the proposed model improves the performance of encoder-decoder models and achieves state-of-the-art results.
{"title":"Exploring Overall Contextual Information for Image Captioning in Human-Like Cognitive Style","authors":"H. Ge, Zehang Yan, Kai Zhang, Mingde Zhao, Liang Sun","doi":"10.1109/ICCV.2019.00184","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00184","url":null,"abstract":"Image captioning is a research hotspot where encoder-decoder models combining convolutional neural network (CNN) and long short-term memory (LSTM) achieve promising results. Despite significant progress, these models generate sentences differently from human cognitive styles. Existing models often generate a complete sentence from the first word to the end, without considering the influence of the following words on the whole sentence generation. In this paper, we explore the utilization of a human-like cognitive style, i.e., building overall cognition for the image to be described and the sentence to be constructed, for enhancing computer image understanding. This paper first proposes a Mutual-aid network structure with Bidirectional LSTMs (MaBi-LSTMs) for acquiring overall contextual information. In the training process, the forward and backward LSTMs encode the succeeding and preceding words into their respective hidden states by simultaneously constructing the whole sentence in a complementary manner. In the captioning process, the LSTM implicitly utilizes the subsequent semantic information contained in its hidden states. In fact, MaBi-LSTMs can generate two sentences in forward and backward directions. To bridge the gap between cross-domain models and generate a sentence with higher quality, we further develop a cross-modal attention mechanism to retouch the two sentences by fusing their salient parts as well as the salient areas of the image. Experimental results on the Microsoft COCO dataset show that the proposed model improves the performance of encoder-decoder models and achieves state-of-the-art results.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"1 1","pages":"1754-1763"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91257552","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Chi Zhan, Dongyu She, Sicheng Zhao, Ming-Ming Cheng, Jufeng Yang
Image emotion recognition attracts much attention in recent years due to its wide applications. It aims to classify the emotional response of humans, where candidate emotion categories are generally defined by specific psychological theories, such as Ekman’s six basic emotions. However, with the development of psychological theories, emotion categories become increasingly diverse, fine-grained, and difficult to collect samples. In this paper, we investigate zero-shot learning (ZSL) problem in the emotion recognition task, which tries to recognize the new unseen emotions. Specifically, we propose a novel affective-structural embedding framework, utilizing mid-level semantic representation, i.e., adjective-noun pairs (ANP) features, to construct an affective embedding space. By doing this, the learned intermediate space can narrow the semantic gap between low-level visual and high-level semantic features. In addition, we introduce an affective adversarial constraint to retain the discriminative capacity of visual features and the affective structural information of semantic features during training process. Our method is evaluated on five widely used affective datasets and the perimental results show the proposed algorithm outperforms the state-of-the-art approaches.
{"title":"Zero-Shot Emotion Recognition via Affective Structural Embedding","authors":"Chi Zhan, Dongyu She, Sicheng Zhao, Ming-Ming Cheng, Jufeng Yang","doi":"10.1109/ICCV.2019.00124","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00124","url":null,"abstract":"Image emotion recognition attracts much attention in recent years due to its wide applications. It aims to classify the emotional response of humans, where candidate emotion categories are generally defined by specific psychological theories, such as Ekman’s six basic emotions. However, with the development of psychological theories, emotion categories become increasingly diverse, fine-grained, and difficult to collect samples. In this paper, we investigate zero-shot learning (ZSL) problem in the emotion recognition task, which tries to recognize the new unseen emotions. Specifically, we propose a novel affective-structural embedding framework, utilizing mid-level semantic representation, i.e., adjective-noun pairs (ANP) features, to construct an affective embedding space. By doing this, the learned intermediate space can narrow the semantic gap between low-level visual and high-level semantic features. In addition, we introduce an affective adversarial constraint to retain the discriminative capacity of visual features and the affective structural information of semantic features during training process. Our method is evaluated on five widely used affective datasets and the perimental results show the proposed algorithm outperforms the state-of-the-art approaches.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"30 1","pages":"1151-1160"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90481512","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zi-yi Liu, Le Wang, Qilin Zhang, Zhanning Gao, Zhenxing Niu, N. Zheng, G. Hua
Weakly-supervised temporal action localization (WS-TAL) is a promising but challenging task with only video-level action categorical labels available during training. Without requiring temporal action boundary annotations in training data, WS-TAL could possibly exploit automatically retrieved video tags as video-level labels. However, such coarse video-level supervision inevitably incurs confusions, especially in untrimmed videos containing multiple action instances. To address this challenge, we propose the Contrast-based Localization EvaluAtioN Network (CleanNet) with our new action proposal evaluator, which provides pseudo-supervision by leveraging the temporal contrast in snippet-level action classification predictions. Essentially, the new action proposal evaluator enforces an additional temporal contrast constraint so that high-evaluation-score action proposals are more likely to coincide with true action instances. Moreover, the new action localization module is an integral part of CleanNet which enables end-to-end training. This is in contrast to many existing WS-TAL methods where action localization is merely a post-processing step. Experiments on THUMOS14 and ActivityNet datasets validate the efficacy of CleanNet against existing state-ofthe- art WS-TAL algorithms.
{"title":"Weakly Supervised Temporal Action Localization Through Contrast Based Evaluation Networks","authors":"Zi-yi Liu, Le Wang, Qilin Zhang, Zhanning Gao, Zhenxing Niu, N. Zheng, G. Hua","doi":"10.1109/ICCV.2019.00400","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00400","url":null,"abstract":"Weakly-supervised temporal action localization (WS-TAL) is a promising but challenging task with only video-level action categorical labels available during training. Without requiring temporal action boundary annotations in training data, WS-TAL could possibly exploit automatically retrieved video tags as video-level labels. However, such coarse video-level supervision inevitably incurs confusions, especially in untrimmed videos containing multiple action instances. To address this challenge, we propose the Contrast-based Localization EvaluAtioN Network (CleanNet) with our new action proposal evaluator, which provides pseudo-supervision by leveraging the temporal contrast in snippet-level action classification predictions. Essentially, the new action proposal evaluator enforces an additional temporal contrast constraint so that high-evaluation-score action proposals are more likely to coincide with true action instances. Moreover, the new action localization module is an integral part of CleanNet which enables end-to-end training. This is in contrast to many existing WS-TAL methods where action localization is merely a post-processing step. Experiments on THUMOS14 and ActivityNet datasets validate the efficacy of CleanNet against existing state-ofthe- art WS-TAL algorithms.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"106 1","pages":"3898-3907"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88059842","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
When describing images with natural language, descriptions can be made more informative if tuned for downstream tasks. This can be achieved by training two networks: a "speaker" that generates sentences given an image and a "listener" that uses them to perform a task. Unfortunately, training multiple networks jointly to communicate, faces two major challenges. First, the descriptions generated by a speaker network are discrete and stochastic, making optimization very hard and inefficient. Second, joint training usually causes the vocabulary used during communication to drift and diverge from natural language. To address these challenges, we present an effective optimization technique based on partial-sampling from a multinomial distribution combined with straight-through gradient updates, which we name PSST for Partial-Sampling Straight-Through. We then show that the generated descriptions can be kept close to natural by constraining them to be similar to human descriptions. Together, this approach creates descriptions that are both more discriminative and more natural than previous approaches. Evaluations on the COCO benchmark show that PSST improve the recall@10 from 60% to 86% maintaining comparable language naturalness. Human evaluations show that it also increases naturalness while keeping the discriminative power of generated captions.
{"title":"Joint Optimization for Cooperative Image Captioning","authors":"Gilad Vered, Gal Oren, Y. Atzmon, Gal Chechik","doi":"10.1109/ICCV.2019.00899","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00899","url":null,"abstract":"When describing images with natural language, descriptions can be made more informative if tuned for downstream tasks. This can be achieved by training two networks: a \"speaker\" that generates sentences given an image and a \"listener\" that uses them to perform a task. Unfortunately, training multiple networks jointly to communicate, faces two major challenges. First, the descriptions generated by a speaker network are discrete and stochastic, making optimization very hard and inefficient. Second, joint training usually causes the vocabulary used during communication to drift and diverge from natural language. To address these challenges, we present an effective optimization technique based on partial-sampling from a multinomial distribution combined with straight-through gradient updates, which we name PSST for Partial-Sampling Straight-Through. We then show that the generated descriptions can be kept close to natural by constraining them to be similar to human descriptions. Together, this approach creates descriptions that are both more discriminative and more natural than previous approaches. Evaluations on the COCO benchmark show that PSST improve the recall@10 from 60% to 86% maintaining comparable language naturalness. Human evaluations show that it also increases naturalness while keeping the discriminative power of generated captions.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"19 1","pages":"8897-8906"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85797483","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Human pose and shape are two important components of 2D human body. However, how to efficiently represent both of them in images is still an open question. In this paper, we propose the Triplet Representation for Body (TRB) --- a compact 2D human body representation, with skeleton keypoints capturing human pose information and contour keypoints containing human shape information. TRB not only preserves the flexibility of skeleton keypoint representation, but also contains rich pose and human shape information. Therefore, it promises broader application areas, such as human shape editing and conditional image generation. We further introduce the challenging problem of TRB estimation, where joint learning of human pose and shape is required. We construct several large-scale TRB estimation datasets, based on the popular 2D pose datasets LSP, MPII and COCO. To effectively solve TRB estimation, we propose a two-branch network (TRB-net) with three novel techniques, namely X-structure (Xs), Directional Convolution (DC) and Pairwise mapping (PM), to enforce multi-level message passing for joint feature learning. We evaluate our proposed TRB-net and several leading approaches on our proposed TRB datasets, and demonstrate the superiority of our method through extensive evaluations.
{"title":"TRB: A Novel Triplet Representation for Understanding 2D Human Body","authors":"Haodong Duan, Kwan-Yee Lin, Sheng Jin, Wentao Liu, C. Qian, Wanli Ouyang","doi":"10.1109/ICCV.2019.00957","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00957","url":null,"abstract":"Human pose and shape are two important components of 2D human body. However, how to efficiently represent both of them in images is still an open question. In this paper, we propose the Triplet Representation for Body (TRB) --- a compact 2D human body representation, with skeleton keypoints capturing human pose information and contour keypoints containing human shape information. TRB not only preserves the flexibility of skeleton keypoint representation, but also contains rich pose and human shape information. Therefore, it promises broader application areas, such as human shape editing and conditional image generation. We further introduce the challenging problem of TRB estimation, where joint learning of human pose and shape is required. We construct several large-scale TRB estimation datasets, based on the popular 2D pose datasets LSP, MPII and COCO. To effectively solve TRB estimation, we propose a two-branch network (TRB-net) with three novel techniques, namely X-structure (Xs), Directional Convolution (DC) and Pairwise mapping (PM), to enforce multi-level message passing for joint feature learning. We evaluate our proposed TRB-net and several leading approaches on our proposed TRB datasets, and demonstrate the superiority of our method through extensive evaluations.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"70 1","pages":"9478-9487"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86314319","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Wasserstein GANs are increasingly used in Computer Vision applications as they are easier to train. Previous WGAN variants mainly use the $l_1$ transport cost to compute the Wasserstein distance between the real and synthetic data distributions. The $l_1$ transport cost restricts the discriminator to be 1-Lipschitz. However, WGANs with $l_1$ transport cost were recently shown to not always converge. In this paper, we propose WGAN-QC, a WGAN with quadratic transport cost. Based on the quadratic transport cost, we propose an Optimal Transport Regularizer (OTR) to stabilize the training process of WGAN-QC. We prove that the objective of the discriminator during each generator update computes the exact quadratic Wasserstein distance between real and synthetic data distributions. We also prove that WGAN-QC converges to a local equilibrium point with finite discriminator updates per generator update. We show experimentally on a Dirac distribution that WGAN-QC converges, when many of the $l_1$ cost WGANs fail to [22]. Qualitative and quantitative results on the CelebA, CelebA-HQ, LSUN and the ImageNet dog datasets show that WGAN-QC is better than state-of-art GAN methods. WGAN-QC has much faster runtime than other WGAN variants.
{"title":"Wasserstein GAN With Quadratic Transport Cost","authors":"Huidong Liu, X. Gu, D. Samaras","doi":"10.1109/ICCV.2019.00493","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00493","url":null,"abstract":"Wasserstein GANs are increasingly used in Computer Vision applications as they are easier to train. Previous WGAN variants mainly use the $l_1$ transport cost to compute the Wasserstein distance between the real and synthetic data distributions. The $l_1$ transport cost restricts the discriminator to be 1-Lipschitz. However, WGANs with $l_1$ transport cost were recently shown to not always converge. In this paper, we propose WGAN-QC, a WGAN with quadratic transport cost. Based on the quadratic transport cost, we propose an Optimal Transport Regularizer (OTR) to stabilize the training process of WGAN-QC. We prove that the objective of the discriminator during each generator update computes the exact quadratic Wasserstein distance between real and synthetic data distributions. We also prove that WGAN-QC converges to a local equilibrium point with finite discriminator updates per generator update. We show experimentally on a Dirac distribution that WGAN-QC converges, when many of the $l_1$ cost WGANs fail to [22]. Qualitative and quantitative results on the CelebA, CelebA-HQ, LSUN and the ImageNet dog datasets show that WGAN-QC is better than state-of-art GAN methods. WGAN-QC has much faster runtime than other WGAN variants.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"24 1","pages":"4831-4840"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87517106","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We propose a unified approach to three tasks of aesthetic score regression, binary aesthetic classification, and personalized aesthetics. First, we develop a comparator to estimate the ratio of aesthetic scores for two images. Then, we construct a pairwise comparison matrix for multiple reference images and an input image, and predict the aesthetic score of the input via the eigenvalue decomposition of the matrix. By varying the reference images, the proposed algorithm can be used for binary aesthetic classification and personalized aesthetics, as well as generic score regression. Experimental results demonstrate that the proposed unified algorithm provides the state-of-the-art performances in all three tasks of image aesthetics.
{"title":"Image Aesthetic Assessment Based on Pairwise Comparison A Unified Approach to Score Regression, Binary Classification, and Personalization","authors":"Jun-Tae Lee, Chang-Su Kim","doi":"10.1109/ICCV.2019.00128","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00128","url":null,"abstract":"We propose a unified approach to three tasks of aesthetic score regression, binary aesthetic classification, and personalized aesthetics. First, we develop a comparator to estimate the ratio of aesthetic scores for two images. Then, we construct a pairwise comparison matrix for multiple reference images and an input image, and predict the aesthetic score of the input via the eigenvalue decomposition of the matrix. By varying the reference images, the proposed algorithm can be used for binary aesthetic classification and personalized aesthetics, as well as generic score regression. Experimental results demonstrate that the proposed unified algorithm provides the state-of-the-art performances in all three tasks of image aesthetics.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"80 1","pages":"1191-1200"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89162507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
6-DoF object pose estimation from a single RGB image is a fundamental and long-standing problem in computer vision. Current leading approaches solve it by training deep networks to either regress both rotation and translation from image directly or to construct 2D-3D correspondences and further solve them via PnP indirectly. We argue that rotation and translation should be treated differently for their significant difference. In this work, we propose a novel 6-DoF pose estimation approach: Coordinates-based Disentangled Pose Network (CDPN), which disentangles the pose to predict rotation and translation separately to achieve highly accurate and robust pose estimation. Our method is flexible, efficient, highly accurate and can deal with texture-less and occluded objects. Extensive experiments on LINEMOD and Occlusion datasets are conducted and demonstrate the superiority of our approach. Concretely, our approach significantly exceeds the state-of-the- art RGB-based methods on commonly used metrics.
{"title":"CDPN: Coordinates-Based Disentangled Pose Network for Real-Time RGB-Based 6-DoF Object Pose Estimation","authors":"Zhigang Li, Gu Wang, Xiangyang Ji","doi":"10.1109/ICCV.2019.00777","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00777","url":null,"abstract":"6-DoF object pose estimation from a single RGB image is a fundamental and long-standing problem in computer vision. Current leading approaches solve it by training deep networks to either regress both rotation and translation from image directly or to construct 2D-3D correspondences and further solve them via PnP indirectly. We argue that rotation and translation should be treated differently for their significant difference. In this work, we propose a novel 6-DoF pose estimation approach: Coordinates-based Disentangled Pose Network (CDPN), which disentangles the pose to predict rotation and translation separately to achieve highly accurate and robust pose estimation. Our method is flexible, efficient, highly accurate and can deal with texture-less and occluded objects. Extensive experiments on LINEMOD and Occlusion datasets are conducted and demonstrate the superiority of our approach. Concretely, our approach significantly exceeds the state-of-the- art RGB-based methods on commonly used metrics.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"19 1","pages":"7677-7686"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86200063","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：