Pub Date : 2021-06-01DOI: 10.1109/CVPR46437.2021.00523
Yohan Jun, Hyungseob Shin, Taejoon Eo, D. Hwang
Magnetic resonance imaging (MRI) can provide diagnostic information with high-resolution and high-contrast images. However, MRI requires a relatively long scan time compared to other medical imaging techniques, where long scan time might occur patient’s discomfort and limit the increase in resolution of magnetic resonance (MR) image. In this study, we propose a Joint Deep Model-based MR Image and Coil Sensitivity Reconstruction Network, called Joint-ICNet, which jointly reconstructs an MR image and coil sensitivity maps from undersampled multi-coil k-space data using deep learning networks combined with MR physical models. Joint-ICNet has two main blocks, where one is an MR image reconstruction block that reconstructs an MR image from undersampled multi-coil k-space data and the other is a coil sensitivity maps reconstruction block that estimates coil sensitivity maps from undersampled multi-coil k-space data. The desired MR image and coil sensitivity maps can be obtained by sequentially estimating them with two blocks based on the unrolled network architecture. To demonstrate the performance of Joint-ICNet, we performed experiments with a fastMRI brain dataset for two reduction factors (R = 4 and 8). With qualitative and quantitative results, we demonstrate that our proposed Joint-ICNet outperforms conventional parallel imaging and deep-learning-based methods in reconstructing MR images from undersampled multi-coil k-space data.
{"title":"Joint Deep Model-based MR Image and Coil Sensitivity Reconstruction Network (Joint-ICNet) for Fast MRI","authors":"Yohan Jun, Hyungseob Shin, Taejoon Eo, D. Hwang","doi":"10.1109/CVPR46437.2021.00523","DOIUrl":"https://doi.org/10.1109/CVPR46437.2021.00523","url":null,"abstract":"Magnetic resonance imaging (MRI) can provide diagnostic information with high-resolution and high-contrast images. However, MRI requires a relatively long scan time compared to other medical imaging techniques, where long scan time might occur patient’s discomfort and limit the increase in resolution of magnetic resonance (MR) image. In this study, we propose a Joint Deep Model-based MR Image and Coil Sensitivity Reconstruction Network, called Joint-ICNet, which jointly reconstructs an MR image and coil sensitivity maps from undersampled multi-coil k-space data using deep learning networks combined with MR physical models. Joint-ICNet has two main blocks, where one is an MR image reconstruction block that reconstructs an MR image from undersampled multi-coil k-space data and the other is a coil sensitivity maps reconstruction block that estimates coil sensitivity maps from undersampled multi-coil k-space data. The desired MR image and coil sensitivity maps can be obtained by sequentially estimating them with two blocks based on the unrolled network architecture. To demonstrate the performance of Joint-ICNet, we performed experiments with a fastMRI brain dataset for two reduction factors (R = 4 and 8). With qualitative and quantitative results, we demonstrate that our proposed Joint-ICNet outperforms conventional parallel imaging and deep-learning-based methods in reconstructing MR images from undersampled multi-coil k-space data.","PeriodicalId":339646,"journal":{"name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125962653","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}
In this paper, we diagnose deep neural networks for 3D point cloud processing to explore utilities of different intermediate-layer network architectures. We propose a number of hypotheses on the effects of specific intermediate-layer network architectures on the representation capacity of DNNs. In order to prove the hypotheses, we design five metrics to diagnose various types of DNNs from the following perspectives, information discarding, information concentration, rotation robustness, adversarial robustness, and neighborhood inconsistency. We conduct comparative studies based on such metrics to verify the hypotheses. We further use the verified hypotheses to revise intermediate-layer architectures of existing DNNs and improve their utilities. Experiments demonstrate the effectiveness of our method. The code will be released when this paper is accepted.
{"title":"Verifiability and Predictability: Interpreting Utilities of Network Architectures for Point Cloud Processing","authors":"Wen Shen, Zhihua Wei, Shikun Huang, Binbin Zhang, Panyue Chen, Ping Zhao, Quanshi Zhang","doi":"10.1109/CVPR46437.2021.01056","DOIUrl":"https://doi.org/10.1109/CVPR46437.2021.01056","url":null,"abstract":"In this paper, we diagnose deep neural networks for 3D point cloud processing to explore utilities of different intermediate-layer network architectures. We propose a number of hypotheses on the effects of specific intermediate-layer network architectures on the representation capacity of DNNs. In order to prove the hypotheses, we design five metrics to diagnose various types of DNNs from the following perspectives, information discarding, information concentration, rotation robustness, adversarial robustness, and neighborhood inconsistency. We conduct comparative studies based on such metrics to verify the hypotheses. We further use the verified hypotheses to revise intermediate-layer architectures of existing DNNs and improve their utilities. Experiments demonstrate the effectiveness of our method. The code will be released when this paper is accepted.","PeriodicalId":339646,"journal":{"name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124646197","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}
Pub Date : 2021-06-01DOI: 10.1109/CVPR46437.2021.01550
Yunhan Zhao, Shu Kong, Charless C. Fowlkes
Monocular depth predictors are typically trained on large-scale training sets which are naturally biased w.r.t the distribution of camera poses. As a result, trained predictors fail to make reliable depth predictions for testing examples captured under uncommon camera poses. To address this issue, we propose two novel techniques that exploit the camera pose during training and prediction. First, we introduce a simple perspective-aware data augmentation that synthesizes new training examples with more diverse views by perturbing the existing ones in a geometrically consistent manner. Second, we propose a conditional model that exploits the per-image camera pose as prior knowledge by encoding it as a part of the input. We show that jointly applying the two methods improves depth prediction on images captured under uncommon and even never-before-seen camera poses. We show that our methods improve performance when applied to a range of different predictor architectures. Lastly, we show that explicitly encoding the camera pose distribution improves the generalization performance of a synthetically trained depth predictor when evaluated on real images.
{"title":"Camera Pose Matters: Improving Depth Prediction by Mitigating Pose Distribution Bias","authors":"Yunhan Zhao, Shu Kong, Charless C. Fowlkes","doi":"10.1109/CVPR46437.2021.01550","DOIUrl":"https://doi.org/10.1109/CVPR46437.2021.01550","url":null,"abstract":"Monocular depth predictors are typically trained on large-scale training sets which are naturally biased w.r.t the distribution of camera poses. As a result, trained predictors fail to make reliable depth predictions for testing examples captured under uncommon camera poses. To address this issue, we propose two novel techniques that exploit the camera pose during training and prediction. First, we introduce a simple perspective-aware data augmentation that synthesizes new training examples with more diverse views by perturbing the existing ones in a geometrically consistent manner. Second, we propose a conditional model that exploits the per-image camera pose as prior knowledge by encoding it as a part of the input. We show that jointly applying the two methods improves depth prediction on images captured under uncommon and even never-before-seen camera poses. We show that our methods improve performance when applied to a range of different predictor architectures. Lastly, we show that explicitly encoding the camera pose distribution improves the generalization performance of a synthetically trained depth predictor when evaluated on real images.","PeriodicalId":339646,"journal":{"name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"13 10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128567942","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}
A deep facial attribute editing model strives to meet two requirements: (1) attribute correctness – the target attribute should correctly appear on the edited face image; (2) irrelevance preservation – any irrelevant information (e.g., identity) should not be changed after editing. Meeting both requirements challenges the state-of-the-art works which resort to either spatial attention or latent space factorization. Specifically, the former assume that each attribute has well-defined local support regions; they are often more effective for editing a local attribute than a global one. The latter factorize the latent space of a fixed pretrained GAN into different attribute-relevant parts, but they cannot be trained end-to-end with the GAN, leading to sub-optimal solutions. To overcome these limitations, we propose a novel latent space factorization model, called L2M-GAN, which is learned end-to-end and effective for editing both local and global attributes. The key novel components are: (1) A latent space vector of the GAN is factorized into an attribute-relevant and irrelevant codes with an orthogonality constraint imposed to ensure disentanglement. (2) An attribute-relevant code transformer is learned to manipulate the attribute value; crucially, the transformed code are subject to the same orthogonality constraint. By forcing both the original attribute-relevant latent code and the edited code to be disentangled from any attribute-irrelevant code, our model strikes the perfect balance between attribute correctness and irrelevance preservation. Extensive experiments on CelebA-HQ show that our L2M-GAN achieves significant improvements over the state-of-the-arts.
{"title":"L2M-GAN: Learning to Manipulate Latent Space Semantics for Facial Attribute Editing","authors":"Guoxing Yang, Nanyi Fei, Mingyu Ding, Guangzhen Liu, Zhiwu Lu, T. Xiang","doi":"10.1109/CVPR46437.2021.00297","DOIUrl":"https://doi.org/10.1109/CVPR46437.2021.00297","url":null,"abstract":"A deep facial attribute editing model strives to meet two requirements: (1) attribute correctness – the target attribute should correctly appear on the edited face image; (2) irrelevance preservation – any irrelevant information (e.g., identity) should not be changed after editing. Meeting both requirements challenges the state-of-the-art works which resort to either spatial attention or latent space factorization. Specifically, the former assume that each attribute has well-defined local support regions; they are often more effective for editing a local attribute than a global one. The latter factorize the latent space of a fixed pretrained GAN into different attribute-relevant parts, but they cannot be trained end-to-end with the GAN, leading to sub-optimal solutions. To overcome these limitations, we propose a novel latent space factorization model, called L2M-GAN, which is learned end-to-end and effective for editing both local and global attributes. The key novel components are: (1) A latent space vector of the GAN is factorized into an attribute-relevant and irrelevant codes with an orthogonality constraint imposed to ensure disentanglement. (2) An attribute-relevant code transformer is learned to manipulate the attribute value; crucially, the transformed code are subject to the same orthogonality constraint. By forcing both the original attribute-relevant latent code and the edited code to be disentangled from any attribute-irrelevant code, our model strikes the perfect balance between attribute correctness and irrelevance preservation. Extensive experiments on CelebA-HQ show that our L2M-GAN achieves significant improvements over the state-of-the-arts.","PeriodicalId":339646,"journal":{"name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128271246","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}
Pub Date : 2021-06-01DOI: 10.1109/CVPR46437.2021.00293
Yuval Bahat, T. Michaeli
The ever-growing amounts of visual contents captured on a daily basis necessitate the use of lossy compression methods in order to save storage space and transmission bandwidth. While extensive research efforts are devoted to improving compression techniques, every method inevitably discards information. Especially at low bit rates, this information often corresponds to semantically meaningful visual cues, so that decompression involves significant ambiguity. In spite of this fact, existing decompression algorithms typically produce only a single output, and do not allow the viewer to explore the set of images that map to the given compressed code. In this work we propose the first image decompression method to facilitate user-exploration of the diverse set of natural images that could have given rise to the compressed input code, thus granting users the ability to determine what could and what could not have been there in the original scene. Specifically, we develop a novel deep-network based decoder architecture for the ubiquitous JPEG standard, which allows traversing the set of decompressed images that are consistent with the compressed JPEG file. To allow for simple user interaction, we develop a graphical user interface comprising several intuitive exploration tools, including an automatic tool for examining specific solutions of interest. We exemplify our framework on graphical, medical and forensic use cases, demonstrating its wide range of potential applications.
{"title":"What’s in the Image? Explorable Decoding of Compressed Images","authors":"Yuval Bahat, T. Michaeli","doi":"10.1109/CVPR46437.2021.00293","DOIUrl":"https://doi.org/10.1109/CVPR46437.2021.00293","url":null,"abstract":"The ever-growing amounts of visual contents captured on a daily basis necessitate the use of lossy compression methods in order to save storage space and transmission bandwidth. While extensive research efforts are devoted to improving compression techniques, every method inevitably discards information. Especially at low bit rates, this information often corresponds to semantically meaningful visual cues, so that decompression involves significant ambiguity. In spite of this fact, existing decompression algorithms typically produce only a single output, and do not allow the viewer to explore the set of images that map to the given compressed code. In this work we propose the first image decompression method to facilitate user-exploration of the diverse set of natural images that could have given rise to the compressed input code, thus granting users the ability to determine what could and what could not have been there in the original scene. Specifically, we develop a novel deep-network based decoder architecture for the ubiquitous JPEG standard, which allows traversing the set of decompressed images that are consistent with the compressed JPEG file. To allow for simple user interaction, we develop a graphical user interface comprising several intuitive exploration tools, including an automatic tool for examining specific solutions of interest. We exemplify our framework on graphical, medical and forensic use cases, demonstrating its wide range of potential applications.","PeriodicalId":339646,"journal":{"name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128604088","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}
Pub Date : 2021-06-01DOI: 10.1109/CVPR46437.2021.00067
Lin Wang, Yujeong Chae, Sung-Hoon Yoon, Tae-Kyun Kim, Kuk-Jin Yoon
Event cameras sense per-pixel intensity changes and produce asynchronous event streams with high dynamic range and less motion blur, showing advantages over the conventional cameras. A hurdle of training event-based models is the lack of large qualitative labeled data. Prior works learning end-tasks mostly rely on labeled or pseudo-labeled datasets obtained from the active pixel sensor (APS) frames; however, such datasets’ quality is far from rivaling those based on the canonical images. In this paper, we propose a novel approach, called EvDistill, to learn a student network on the unlabeled and unpaired event data (target modality) via knowledge distillation (KD) from a teacher network trained with large-scale, labeled image data (source modality). To enable KD across the unpaired modalities, we first propose a bidirectional modality reconstruction (BMR) module to bridge both modalities and simultaneously exploit them to distill knowledge via the crafted pairs, causing no extra computation in the inference. The BMR is improved by the end-tasks and KD losses in an end-to-end manner. Second, we leverage the structural similarities of both modalities and adapt the knowledge by matching their distributions. Moreover, as most prior feature KD methods are uni-modality and less applicable to our problem, we propose an affinity graph KD loss to boost the distillation. Our extensive experiments on semantic segmentation and object recognition demonstrate that EvDistill achieves significantly better results than the prior works and KD with only events and APS frames.
{"title":"EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge Distillation","authors":"Lin Wang, Yujeong Chae, Sung-Hoon Yoon, Tae-Kyun Kim, Kuk-Jin Yoon","doi":"10.1109/CVPR46437.2021.00067","DOIUrl":"https://doi.org/10.1109/CVPR46437.2021.00067","url":null,"abstract":"Event cameras sense per-pixel intensity changes and produce asynchronous event streams with high dynamic range and less motion blur, showing advantages over the conventional cameras. A hurdle of training event-based models is the lack of large qualitative labeled data. Prior works learning end-tasks mostly rely on labeled or pseudo-labeled datasets obtained from the active pixel sensor (APS) frames; however, such datasets’ quality is far from rivaling those based on the canonical images. In this paper, we propose a novel approach, called EvDistill, to learn a student network on the unlabeled and unpaired event data (target modality) via knowledge distillation (KD) from a teacher network trained with large-scale, labeled image data (source modality). To enable KD across the unpaired modalities, we first propose a bidirectional modality reconstruction (BMR) module to bridge both modalities and simultaneously exploit them to distill knowledge via the crafted pairs, causing no extra computation in the inference. The BMR is improved by the end-tasks and KD losses in an end-to-end manner. Second, we leverage the structural similarities of both modalities and adapt the knowledge by matching their distributions. Moreover, as most prior feature KD methods are uni-modality and less applicable to our problem, we propose an affinity graph KD loss to boost the distillation. Our extensive experiments on semantic segmentation and object recognition demonstrate that EvDistill achieves significantly better results than the prior works and KD with only events and APS frames.","PeriodicalId":339646,"journal":{"name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129372184","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}
Pub Date : 2021-06-01DOI: 10.1109/CVPR46437.2021.01197
Navaneeth Bodla, G. Shrivastava, R. Chellappa, Abhinav Shrivastava
Learning to model and predict how humans interact with objects while performing an action is challenging, and most of the existing video prediction models are ineffective in modeling complicated human-object interactions. Our work builds on hierarchical video prediction models, which disentangle the video generation process into two stages: predicting a high-level representation, such as pose sequence, and then learning a pose-to-pixels translation model for pixel generation. An action sequence for a human-object interaction task is typically very complicated, involving the evolution of pose, person’s appearance, object locations, and object appearances over time. To this end, we propose a Hierarchical Video Prediction model using Relational Layouts. In the first stage, we learn to predict a sequence of layouts. A layout is a high-level representation of the video containing both pose and objects’ information for every frame. The layout sequence is learned by modeling the relationships between the pose and objects using relational reasoning and recurrent neural networks. The layout sequence acts as a strong structure prior to the second stage that learns to map the layouts into pixel space. Experimental evaluation of our method on two datasets, UMD-HOI and Bimanual, shows significant improvements in standard video evaluation metrics such as LPIPS, PSNR, and SSIM. We also perform a detailed qualitative analysis of our model to demonstrate various generalizations.
{"title":"Hierarchical Video Prediction using Relational Layouts for Human-Object Interactions","authors":"Navaneeth Bodla, G. Shrivastava, R. Chellappa, Abhinav Shrivastava","doi":"10.1109/CVPR46437.2021.01197","DOIUrl":"https://doi.org/10.1109/CVPR46437.2021.01197","url":null,"abstract":"Learning to model and predict how humans interact with objects while performing an action is challenging, and most of the existing video prediction models are ineffective in modeling complicated human-object interactions. Our work builds on hierarchical video prediction models, which disentangle the video generation process into two stages: predicting a high-level representation, such as pose sequence, and then learning a pose-to-pixels translation model for pixel generation. An action sequence for a human-object interaction task is typically very complicated, involving the evolution of pose, person’s appearance, object locations, and object appearances over time. To this end, we propose a Hierarchical Video Prediction model using Relational Layouts. In the first stage, we learn to predict a sequence of layouts. A layout is a high-level representation of the video containing both pose and objects’ information for every frame. The layout sequence is learned by modeling the relationships between the pose and objects using relational reasoning and recurrent neural networks. The layout sequence acts as a strong structure prior to the second stage that learns to map the layouts into pixel space. Experimental evaluation of our method on two datasets, UMD-HOI and Bimanual, shows significant improvements in standard video evaluation metrics such as LPIPS, PSNR, and SSIM. We also perform a detailed qualitative analysis of our model to demonstrate various generalizations.","PeriodicalId":339646,"journal":{"name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127144469","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}
Pub Date : 2021-06-01DOI: 10.1109/CVPR46437.2021.00898
Shaoxiong Zhang, Yunhong Wang, Annan Li
Gait is considered an attractive biometric identifier for its non-invasive and non-cooperative features compared with other biometric identifiers such as fingerprint and iris. At present, cross-view gait recognition methods always establish representations from various deep convolutional networks for recognition and ignore the potential dynamical information of the gait sequences. If assuming that pedestrians have different walking patterns, gait recognition can be performed by calculating their dynamical features from each view. This paper introduces the Koopman operator theory to gait recognition, which can find an embedding space for a global linear approximation of a nonlinear dynamical system. Furthermore, a novel framework based on convolutional variational autoencoder and deep Koopman embedding is proposed to approximate the Koopman operators, which is used as dynamical features from the linearized embedding space for cross-view gait recognition. It gives solid physical interpretability for a gait recognition system. Experiments on a large public dataset, OU-MVLP, prove the effectiveness of the proposed method.
{"title":"Cross-View Gait Recognition with Deep Universal Linear Embeddings","authors":"Shaoxiong Zhang, Yunhong Wang, Annan Li","doi":"10.1109/CVPR46437.2021.00898","DOIUrl":"https://doi.org/10.1109/CVPR46437.2021.00898","url":null,"abstract":"Gait is considered an attractive biometric identifier for its non-invasive and non-cooperative features compared with other biometric identifiers such as fingerprint and iris. At present, cross-view gait recognition methods always establish representations from various deep convolutional networks for recognition and ignore the potential dynamical information of the gait sequences. If assuming that pedestrians have different walking patterns, gait recognition can be performed by calculating their dynamical features from each view. This paper introduces the Koopman operator theory to gait recognition, which can find an embedding space for a global linear approximation of a nonlinear dynamical system. Furthermore, a novel framework based on convolutional variational autoencoder and deep Koopman embedding is proposed to approximate the Koopman operators, which is used as dynamical features from the linearized embedding space for cross-view gait recognition. It gives solid physical interpretability for a gait recognition system. Experiments on a large public dataset, OU-MVLP, prove the effectiveness of the proposed method.","PeriodicalId":339646,"journal":{"name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127276973","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}
Pub Date : 2021-06-01DOI: 10.1109/CVPR46437.2021.00279
Guoshun Nan, Rui Qiao, Yao Xiao, Jun Liu, Sicong Leng, H. Zhang, Wei Lu
Video grounding aims to localize a moment from an untrimmed video for a given textual query. Existing approaches focus more on the alignment of visual and language stimuli with various likelihood-based matching or regression strategies, i.e., P(Y |X). Consequently, these models may suffer from spurious correlations between the language and video features due to the selection bias of the dataset. 1) To uncover the causality behind the model and data, we first propose a novel paradigm from the perspective of the causal inference, i.e., interventional video grounding (IVG) that leverages backdoor adjustment to deconfound the selection bias based on structured causal model (SCM) and do-calculus P(Y |do(X)). Then, we present a simple yet effective method to approximate the unobserved confounder as it cannot be directly sampled from the dataset. 2) Meanwhile, we introduce a dual contrastive learning approach (DCL) to better align the text and video by maximizing the mutual information (MI) between query and video clips, and the MI between start/end frames of a target moment and the others within a video to learn more informative visual representations. Experiments on three standard benchmarks show the effectiveness of our approaches.
{"title":"Interventional Video Grounding with Dual Contrastive Learning","authors":"Guoshun Nan, Rui Qiao, Yao Xiao, Jun Liu, Sicong Leng, H. Zhang, Wei Lu","doi":"10.1109/CVPR46437.2021.00279","DOIUrl":"https://doi.org/10.1109/CVPR46437.2021.00279","url":null,"abstract":"Video grounding aims to localize a moment from an untrimmed video for a given textual query. Existing approaches focus more on the alignment of visual and language stimuli with various likelihood-based matching or regression strategies, i.e., P(Y |X). Consequently, these models may suffer from spurious correlations between the language and video features due to the selection bias of the dataset. 1) To uncover the causality behind the model and data, we first propose a novel paradigm from the perspective of the causal inference, i.e., interventional video grounding (IVG) that leverages backdoor adjustment to deconfound the selection bias based on structured causal model (SCM) and do-calculus P(Y |do(X)). Then, we present a simple yet effective method to approximate the unobserved confounder as it cannot be directly sampled from the dataset. 2) Meanwhile, we introduce a dual contrastive learning approach (DCL) to better align the text and video by maximizing the mutual information (MI) between query and video clips, and the MI between start/end frames of a target moment and the others within a video to learn more informative visual representations. Experiments on three standard benchmarks show the effectiveness of our approaches.","PeriodicalId":339646,"journal":{"name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127548886","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}
Pub Date : 2021-06-01DOI: 10.1109/CVPR46437.2021.00075
Younghyun Jo, Seon Joo Kim
A number of super-resolution (SR) algorithms from interpolation to deep neural networks (DNN) have emerged to restore or create missing details of the input low-resolution image. As mobile devices and display hardware develops, the demand for practical SR technology has increased. Current state-of-the-art SR methods are based on DNNs for better quality. However, they are feasible when executed by using a parallel computing module (e.g. GPUs), and have been difficult to apply to general uses such as end-user software, smartphones, and televisions. To this end, we propose an efficient and practical approach for the SR by adopting look-up table (LUT). We train a deep SR network with a small receptive field and transfer the output values of the learned deep model to the LUT. At test time, we retrieve the precomputed HR output values from the LUT for query LR input pixels. The proposed method can be performed very quickly because it does not require a large number of floating point operations. Experimental results show the efficiency and the effectiveness of our method. Especially, our method runs faster while showing better quality compared to bicubic interpolation.
{"title":"Practical Single-Image Super-Resolution Using Look-Up Table","authors":"Younghyun Jo, Seon Joo Kim","doi":"10.1109/CVPR46437.2021.00075","DOIUrl":"https://doi.org/10.1109/CVPR46437.2021.00075","url":null,"abstract":"A number of super-resolution (SR) algorithms from interpolation to deep neural networks (DNN) have emerged to restore or create missing details of the input low-resolution image. As mobile devices and display hardware develops, the demand for practical SR technology has increased. Current state-of-the-art SR methods are based on DNNs for better quality. However, they are feasible when executed by using a parallel computing module (e.g. GPUs), and have been difficult to apply to general uses such as end-user software, smartphones, and televisions. To this end, we propose an efficient and practical approach for the SR by adopting look-up table (LUT). We train a deep SR network with a small receptive field and transfer the output values of the learned deep model to the LUT. At test time, we retrieve the precomputed HR output values from the LUT for query LR input pixels. The proposed method can be performed very quickly because it does not require a large number of floating point operations. Experimental results show the efficiency and the effectiveness of our method. Especially, our method runs faster while showing better quality compared to bicubic interpolation.","PeriodicalId":339646,"journal":{"name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127470942","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：