Photo-realistic style transfer aims at migrating the artistic style from an exemplar style image to a content image, producing a result image without spatial distortions or unrealistic artifacts. Impressive results have been achieved by recent deep models. However, deep neural network based methods are too expensive to run in real-time. Meanwhile, bilateral grid based methods are much faster but still contain artifacts like overexposure. In this work, we propose the Adaptive ColorMLP (AdaCM), an effective and efficient framework for universal photo-realistic style transfer. First, we find the complex non-linear color mapping between input and target domain can be efficiently modeled by a small multi-layer perceptron (ColorMLP) model. Then, in AdaCM, we adopt a CNN encoder to adaptively predict all parameters for the ColorMLP conditioned on each input content and style image pair. Experimental results demonstrate that AdaCM can generate vivid and high-quality stylization results. Meanwhile, our AdaCM is ultrafast and can process a 4K resolution image in 6ms on one V100 GPU.

While progress has been made in the field of portrait reenactment, the problem of how to produce high-fidelity and robust videos remains. Recent studies normally find it challenging to handle rarely seen target poses due to the limitation of source data. This paper proposes the Video Portrait via Non-local Quantization Modeling (VPNQ) framework, which produces pose- and disturbance-robust reenactable video portraits. Our key insight is to learn position-invariant quantized local patch representations and build a mapping between simple driving signals and local textures with non-local spatial-temporal modeling. Specifically, instead of learning a universal quantized codebook, we identify that a personalized one can be trained to preserve desired position-invariant local details better. Then, a simple representation of projected landmarks can be used as sufficient driving signals to avoid 3D rendering. Following, we employ a carefully designed Spatio-Temporal Transformer to predict reasonable and temporally consistent quantized tokens from the driving signal. The predicted codes can be decoded back to robust and high-quality videos. Comprehensive experiments have been conducted to validate the effectiveness of our approach.

Despite recent advances in syncing lip movements with any audio waves, current methods still struggle to balance generation quality and the model's generalization ability. Previous studies either require long-term data for training or produce a similar movement pattern on all subjects with low quality. In this paper, we propose StyleSync, an effective framework that enables high-fidelity lip synchronization. We identify that a style-based generator would sufficiently enable such a charming property on both one-shot and few-shot scenarios. Specifically, we design a mask-guided spatial information encoding module that preserves the details of the given face. The mouth shapes are accurately modified by audio through modulated convolutions. Moreover, our design also enables personalized lip-sync by introducing style space and generator refinement on only limited frames. Thus the identity and talking style of a target person could be accurately preserved. Extensive experiments demonstrate the effectiveness of our method in producing high-fidelity results on a variety of scenes. Resources can be found at https:/hangz-nju-cuhk.github.io/projects/StyleSync.

Transformer-based models achieve favorable performance in artistic style transfer recently thanks to its global receptive field and powerful multi-head/layer attention operations. Nevertheless, the over-paramerized multi-layer structure increases parameters significantly and thus presents a heavy burden for training. Moreover, for the task of style transfer, vanilla Transformer that fuses content and style features by residual connections is prone to content-wise distortion. In this paper, we devise a novel Transformer model termed as Master specifically for style transfer. On the one hand, in the proposed model, different Transformer layers share a common group of parameters, which (1) reduces the total number of parameters, (2) leads to more robust training convergence, and (3) is readily to control the degree of stylization via tuning the number of stacked layers freely during inference. On the other hand, different from the vanilla version, we adopt a learnable scaling operation on content features before content-style feature interaction, which better preserves the original similarity between a pair of content features while ensuring the stylization quality. We also propose a novel meta learning scheme for the proposed model so that it can not only work in the typical setting of arbitrary style transfer, but also adaptable to the few-shot setting, by only fine-tuning the Transformer encoder layer in the few-shot stage for one specific style. Text-guided few-shot style transfer is firstly achieved with the proposed framework. Extensive experiments demonstrate the superiority of Master under both zero-shot and few-shot style transfer settings.

It is widely agreed that reference-based super-resolution (RefSR) achieves superior results by referring to similar high quality images, compared to single image super-resolution (SISR). Intuitively, the more references, the better performance. However, previous RefSR methods have all focused on single-reference image training, while multiple reference images are often available in testing or practical applications. The root cause of such training-testing mismatch is the absence of publicly available multi-reference SR training datasets, which greatly hinders research efforts on multi-reference super-resolution. To this end, we construct a large-scale, multi-reference super-resolution dataset, named LMR. It contains 112, 142 groups of 300×300 training images, which is 10× of the existing largest RefSR dataset. The image size is also some times larger. More importantly, each group is equipped with 5 reference images with different similarity levels. Furthermore, we propose a new baseline method for multi-reference super-resolution: MRefSR, including a Multi-Reference Attention Module (MAM) for feature fusion of an arbitrary number of reference images, and a Spatial Aware Filtering Module (SAFM) for the fused feature selection. The proposed MRefSR achieves significant improvements over state-of-the-art approaches on both quantitative and qualitative evaluations. Our code and data are available at: https://github.com/wdmwhh/MRefSR.

Great successes have been achieved using deep learning techniques for image super-resolution (SR) with fixed scales. To increase its real world applicability, numerous models have also been proposed to restore SR images with arbitrary scale factors, including asymmetric ones where images are resized to different scales along horizontal and vertical directions. Though most models are only optimized for the unidirectional upscaling task while assuming a predefined downscaling kernel for low-resolution (LR) inputs, recent models based on Invertible Neural Networks (INN) are able to increase upscaling accuracy significantly by optimizing the downscaling and upscaling cycle jointly. However, limited by the INN architecture, it is constrained to fixed integer scale factors and requires one model for each scale. Without increasing model complexity, a simple and effective invertible arbitrary rescaling network (IARN) is proposed to achieve arbitrary image rescaling by training only one model in this work. Using innovative components like position-aware scale encoding and preemptive channel splitting, the network is optimized to convert the non-invertible rescaling cycle to an effectively invertible process. It is shown to achieve a state-of-the-art (SOTA) performance in bidirectional arbitrary rescaling without compromising perceptual quality in LR outputs. It is also demonstrated to perform well on tests with asymmetric scales using the same network architecture.

We address the problem of face modeling, which is still challenging in achieving high-quality reconstruction results efficiently. Neither previous regression-based nor optimization-based frameworks could well balance between the facial reconstruction fidelity and efficiency. We notice that the large amount of in-the-wild facial images contain diverse appearance information, however, their underlying knowledge is not fully exploited for face modeling. To this end, we propose our Reconstruction by Encoding Facial Priors (ReEnFP) pipeline to exploit the potential of unconstrained facial images for further improvement. Our key is to encode generative priors learned by a style-based texture generator on unconstrained data for fast and detail-preserving face reconstruction. With our texture generator pre-trained using a differentiable renderer, faces could be encoded to its latent space as opposed to the time-consuming optimization-based inversion. Our generative prior encoding is further enhanced with a pyramid fusion block for adaptive integration of input spatial information. Extensive experiments show that our method reconstructs photo-realistic facial textures and geometric details with precise identity recovery.

A common challenge posed to robust semantic segmentation is the expensive data annotation cost. Existing semi-supervised solutions show great potential for solving this problem. Their key idea is constructing consistency regularization with unsupervised data augmentation from unlabeled data for model training. The perturbations for unlabeled data enable the consistency training loss, which benefits semi-supervised semantic segmentation. However, these perturbations destroy image context and introduce unnatural boundaries, which is harmful for semantic segmentation. Besides, the widely adopted semi-supervised learning framework, i.e. mean-teacher, suffers performance limitation since the student model finally converges to the teacher model. In this paper, first of all, we propose a context friendly differentiable geometric warping to conduct unsupervised data augmentation; secondly, a novel adversarial dual-student framework is proposed to improve the Mean-Teacher from the following two aspects: (1) dual student models are learned independently except for a stabilization constraint to encourage exploiting model diversities; (2) adversarial training scheme is applied to both students and the discriminators are resorted to distinguish reliable pseudo-label of unlabeled data for self-training. Effectiveness is validated via extensive experiments on PASCAL VOC2012 and Cityscapes. Our solution significantly improves the performance and state-of-the-art results are achieved on both datasets. Remarkably, compared with fully supervision, our solution achieves comparable mIoU of 73.4% using only 12.5% annotated data on PASCAL VOC2012. Our codes and models are available athttps://github.com/cao-cong/ADS-SemiSeg.

Self-supervised denoising frameworks have recently been proposed to learn denoising models without noisy-clean image pairs, showing great potential in various applications. The denoising model is expected to produce visually pleasant images without noise patterns. However, it is non-trivial to achieve this goal using self-supervised methods because 1) the self-supervised model is difficult to restore the perceptual information due to the lack of clean supervision, and 2) perceptual quality is relatively subjective to users’ preferences. In this paper, we make the first attempt to build an interactive self-supervised denoising model to tackle the aforementioned problems. Specifically, we propose an interactive two-branch network to effectively restore perceptual information. The network consists of a denoising branch and an interactive branch, where the former focuses on efficient denoising, and the latter modulates the denoising branch. Based on the delicate architecture design, our network can produce various denoising outputs, allowing the user to easily select the most appealing outcome for satisfying the perceptual requirement. Moreover, to optimize the network with only noisy images, we propose a novel two-stage training strategy in a self-supervised way. Once the network is optimized, it can be interactively changed between noise reduction and texture restoration, providing more denoising choices for users. Existing self-supervised denoising methods can be integrated into our method to be user-friendly with interaction. Extensive experiments and comprehensive analyses are conducted to validate the effectiveness of the proposed method.

With the popularization of ultra high definition (UHD) high dynamic range (HDR) displays, recent works focus onupgradinghigh definition (HD) standard dynamic range (SDR) videos to UHD-HDR versions, aiming to provides richer details and higher contrasts on advanced modern displays. However, joint considering theupgrading&downgradingtranslations between two types of videos, which is practical in real applications, is generally neglected. On the one hand,downgradingtranslation is the key to showing UHD-HDR videos on HD-SDR displays. On the other hand, considering both translations enables joint optimization and results in high quality translation. To this end, we propose the bidirectional translation network (BiT-Net), which jointly considers two translations in one network for the first time. In brief, BiT-Net is elaborately designed in aninvertiblefashion that can be efficiently inferred along forward and backward directions fordowngradingandupgradingtasks, respectively. Based on this framework, we divide each direction into three sub-tasks,i.e., decomposition, structure-guided translation, and synthesis, to effectively translate the dynamic range and the high-frequency details. Benefiting from the dedicated architecture, our BiT-Net can work on 1) downgrading UHD-HDR videos, 2) upgrading existing HD-SDR videos, and 3) synthesizing UHD-HDR versions from the downgraded HD-SDR videos. Experiments show that the proposed method achieves state-of-the-art performances on all these three tasks.

Image style transfer aims at synthesizing an image with the content from one image and the style from another. User studies have revealed that the semantic correspondence between style and content greatly affects subjective perception of style transfer results. While current studies have made great progress in improving the visual quality of stylized images, most methods directly transfer global style statistics without considering semantic alignment. Current semantic style transfer approaches still work in an iterative optimization fashion, which is impractically computationally expensive. Addressing these issues, we introduce a novel dual-affinity style embedding network (DaseNet) to synthesize images with style aligned at semantic region granularity. In the dual-affinity module, feature correlation and semantic correspondence between content and style images are modeled jointly for embedding local style patterns according to semantic distribution. Furthermore, the semantic-weighted style loss and the region-consistency loss are introduced to ensure semantic alignment and content preservation. With the end-to-end network architecture, DaseNet can well balance visual quality and inference efficiency for semantic style transfer. Experimental results on different scene categories have demonstrated the effectiveness of the proposed method.

Deep learning based single image super-resolution models have been widely studied and superb results are achieved in upscaling low-resolution images with fixed scale factor and downscaling degradation kernel. To improve real world applicability of such models, there are growing interests to develop models optimized for arbitrary upscaling factors. Our proposed method is the first to treat arbitrary rescaling, both upscaling and downscaling, as one unified process. Using joint optimization of both directions, the proposed model is able to learn upscaling and downscaling simultaneously and achieve bidirectional arbitrary image rescaling. It improves the performance of current arbitrary upscaling models by a large margin while at the same time learns to maintain visual perception quality in downscaled images. The proposed model is further shown to be robust in cycle idempotence test, free of severe degradations in reconstruction accuracy when the downscaling-to-upscaling cycle is applied repetitively. This robustness is beneficial for image rescaling in the wild when this cycle could be applied to one image for multiple times. It also performs well on tests with arbitrary large scales and asymmetric scales, even when the model is not trained with such tasks. Extensive experiments are conducted to demonstrate the superior performance of our model.

To achieve disentangled image manipulation, previous works depend heavily on manual annotation. Meanwhile, the available manipulations are limited to a pre-defined set the models were trainedfor. We propose a novelframework, i.e., Predict, Prevent, and Evaluate (PPE), for disentangled text-driven image manipulation that requires little manual annotation while being applicable to a wide variety of ma-nipulations. Our method approaches the targets by deeply exploiting the power of the large-scale pre-trained vision-language model CLIP [32]. Concretely, we firstly Predict the possibly entangled attributes for a given text command. Then, based on the predicted attributes, we introduce an entanglement loss to Prevent entanglements during training. Finally, we propose a new evaluation metric to Evaluate the disentangled image manipulation. We verify the effectiveness of our method on the challenging face editing task. Extensive experiments show that the proposed PPE frame-work achieves much better quantitative and qualitative re-sults than the up-to-date StyleCLIP [31] baseline. Code is available at https://github.com/zipengxuc/PPE.

Contrastive self-supervised learning (CSL) has remarkably promoted the progress of visual representation learning. However, existing video CSL methods mainly focus on clip-level temporal semantic consistency. The temporal and spatial semantic correspondence across different granularities, i.e., video, clip, and frame levels, is typically overlooked. To tackle this issue, we propose a self-supervised Macro-to-Micro Semantic Correspondence (MaMiCo) learning framework, pursuing fine-grained spatiotemporal representations from a macro-to-micro perspective. Specifically, MaMiCo constructs a multiple branch architecture of T-MaMiCo and S-MaMiCo on a temporally-nested clip pyramid (video-to-frame). On the pyramid, T-MaMiCo aims at temporal correspondence by simultaneously assimilating semantic invariance representations and retaining appearance dynamics in long temporal ranges. For spatial correspondence, S-MaMiCo perceives subtle motion cues via ameliorating dense CSL for videos where stationary clips are applied for stably dense contrasting reference to alleviate semantic inconsistency caused by ''mismatching''. Extensive experiments justify that MaMiCo learns rich general video representations and works well on various downstream tasks, e.g., (fine-grained) action recognition, action localization, and video retrieval.

Video-text retrieval (VTR) is an attractive yet challenging task for multi-modal understanding, which aims to search for relevant video (text) given a query (video). Existing methods typically employ completely heterogeneous visual-textual information to align video and text, whilst lacking the awareness of homogeneous high-level semantic information residing in both modalities. To fill this gap, in this work, we propose a novel visual-linguistic aligning model named HiSE for VTR, which improves the cross-modal representation by incorporating explicit high-level semantics. First, we explore the hierarchical property of explicit high-level semantics, and further decompose it into two levels, i.e. discrete semantics and holistic semantics. Specifically, for visual branch, we exploit an off-the-shelf semantic entity predictor to generate discrete high-level semantics. In parallel, a trained video captioning model is employed to output holistic high-level semantics. As for the textual modality, we parse the text into three parts including occurrence, action and entity. In particular, the occurrence corresponds to the holistic high-level semantics, meanwhile both action and entity represent the discrete ones. Then, different graph reasoning techniques are utilized to promote the interaction between holistic and discrete high-level semantics. Extensive experiments demonstrate that, with the aid of explicit high-level semantics, our method achieves the superior performance over state-of-the-art methods on three benchmark datasets, including MSR-VTT, MSVD and DiDeMo.

Recently, substantial research effort has focused on how to apply CNNs or RNNs to better capture temporal patterns in videos, so as to improve the accuracy of video classification. In this paper, we investigate the potential of a purely attention based local feature integration. Accounting for the characteristics of such features in video classification, we first propose Basic Attention Clusters (BAC), which concatenates the output of multiple attention units applied in parallel, and introduce a shifting operation to capture more diverse signals. Experiments show that BAC can achieve excellent results on multiple datasets. However, BAC treats all feature channels as an indivisible whole, which is suboptimal for achieving a finer-grained local feature integration over the channel dimension. Additionally, it treats the entire local feature sequence as an unordered set, thus ignoring the sequential relationships. To improve over BAC, we further propose the channel pyramid attention schema by splitting features into sub-features at multiple scales for coarse-to-fine sub-feature interaction modeling, and propose the temporal pyramid attention schema by dividing the feature sequences into ordered sub-sequences of multiple lengths to account for the sequential order. Our final model pyramid×pyramid attention clusters (PPAC) combines both channel pyramid attention and temporal pyramid attention to focus on the most important sub-features, while also preserving the temporal information of the video. We demonstrate the effectiveness of PPAC on seven real-world video classification datasets. Our model achieves competitive results across all of these, showing that our proposed framework can consistently outperform the existing local feature integration methods across a range of different scenarios.

Temporal action proposal generation aims to generate temporal video segments containing human actions in untrimmed videos, which is always a preliminary for such video understanding tasks as action localization and temporally description grounding,etc. Fully-supervised solutions, though proven to be effective, suffer much from heavy data annotation overhead. To address this problem, this paper focuses on a rarely investigated yet practical problem of semi-supervised learning for temporal action proposal generation. Firstly, we propose aProposal Map oriented Mean-Teacher(PM-MT) model, which can use both labeled and unlabeled data for end-to-end model training. Secondly, aSuppression-and-Re-Generation(SRG) strategy is designed to generate high-quality pseudo labels for unlabeled data, which are then used to finetune the model. Extensive experiments demonstrate the effectiveness of our proposed method, by achieving the state-of-the-art results on two public benchmark datatsets on the task of semi-supervised action proposal generation and outperforming fully-supervised learning methods with only a portion of labeled data.

We study unsupervised video representation learning that seeks to learn both motion and appearance features from unlabeled video only, which can be reused for downstream tasks such as action recognition. This task, however, is extremely challenging due to 1) the highly complex spatial-temporal information in videos and 2) the lack of labeled data for training. Unlike representation learning for static images, it is difficult to construct a suitable self-supervised task to effectively model both motion and appearance features. More recently, several attempts have been made to learn video representation through video playback speed prediction. However, it is non-trivial to obtain precise speed labels for the videos. More critically, the learned models may tend to focus on motion patterns and thus may not learn appearance features well. In this paper, we observe that the relative playback speed is more consistent with motion patterns and thus provides more effective and stable supervision for representation learning. Therefore, we propose a new way to perceive the playback speed and exploit the relative speed between two video clips as labels. In this way, we are able to effectively perceive speed and learn better motion features. Moreover, to ensure the learning of appearance features, we further propose an appearance-focused task, where we enforce the model to perceive the appearance difference between two video clips. We show that jointly optimizing the two tasks consistently improves the performance on two downstream tasks (namely, action recognition and video retrieval) w.r.t the increasing pre-training epochs. Remarkably, for action recognition on the UCF101 dataset, we achieve 93.7% accuracy without the use of labeled data for pre-training, which outperforms the ImageNet supervised pre-trained model. Our code, pre-trained models, and supplementary materials can be found at https://github.com/PeihaoChen/RSPNet.

Conventionally, spatiotemporal modeling network and its complexity are the two most concentrated research topics in video action recognition. Existing state-of-the-art methods have achieved excellent accuracy regardless of the complexity meanwhile efficient spatiotemporal modeling solutions are slightly inferior in performance. In this paper, we attempt to acquire both efficiency and effectiveness simultaneously. First of all, besides traditionally treating H x W x T video frames as space-time signal (viewing from the Height-Width spatial plane), we propose to also model video from the other two Height-Time and Width-Time planes, to capture the dynamics of video thoroughly. Secondly, our model is designed based on 2D CNN backbones and model complexity is well kept in mind by design. Specifically, we introduce a novel multi-view fusion (MVF) module to exploit video dynamics using separable convolution for efficiency. It is a plug-and-play module and can be inserted into off-the-shelf 2D CNNs to form a simple yet effective model called MVFNet. Moreover, MVFNet can be thought of as a generalized video modeling framework and it can specialize to be existing methods such as C2D, SlowOnly, and TSM under different settings. Extensive experiments are conducted on popular benchmarks (i.e., Something-Something V1 & V2, Kinetics, UCF-101, and HMDB-51) to show its superiority. The proposed MVFNet can achieve state-of-the-art performance with 2D CNN's complexity.

Artistic style transfer aims at migrating the style from an example image to a content image. Currently, optimization-based methods have achieved great stylization quality, but expensive time cost restricts their practical applications. Meanwhile, feed-forward methods still fail to synthesize complex style, especially when holistic global and local patterns exist. Inspired by the common painting process of drawing a draft and revising the details, we introduce a novel feed-forward method named Laplacian Pyramid Network (LapStyle). LapStyle first transfers global style patterns in low-resolution via a Drafting Network. It then revises the local details in high-resolution via a Revision Network, which hallucinates a residual image according to the draft and the image textures extracted by Laplacian filtering. Higher resolution details can be easily generated by stacking Revision Networks with multiple Laplacian pyramid levels. The final stylized image is obtained by aggregating outputs of all pyramid levels. Experiments demonstrate that our method can synthesize high quality stylized images in real time, where holistic style patterns are properly transferred.

Human pose transfer has received great attention due to its wide applications, yet is still a challenging task that is not well solved. Recent works have achieved great success to transfer the person image from the source to the target pose. However, most of them cannot well capture the semantic appearance, resulting in inconsistent and less realistic textures on the reconstructed results. To address this issue, we propose a new two-stage framework to handle the pose and appearance translation. In the first stage, we predict the target semantic parsing maps to eliminate the difficulties of pose transfer and further benefit the latter translation of per-region appearance style. In the second one, with the predicted target semantic maps, we suggest a new person image generation method by incorporating the region-adaptive normalization, in which it takes the per-region styles to guide the target appearance generation. Extensive experiments show that our proposed SPGNet can generate more semantic, consistent, and photorealistic results and perform favorably against the state of the art methods in terms of quantitative and qualitative evaluation. The source code and model are available at https://github.com/cszy98/SPGNet.git.

We study self-supervised video representation learning, which is a challenging task due to 1) lack of labels for explicit supervision; 2) unstructured and noisy visual information. Existing methods mainly use contrastive loss with video clips as the instances and learn visual representation by discriminating instances from each other, but they need a careful treatment of negative pairs by either relying on large batch sizes, memory banks, extra modalities or customized mining strategies, which inevitably includes noisy data. In this paper, we observe that the consistency between positive samples is the key to learn robust video representation. Specifically, we propose two tasks to learn appearance and speed consistency, respectively. The appearance consistency task aims to maximize the similarity between two clips of the same video with different playback speeds. The speed consistency task aims to maximize the similarity between two clips with the same playback speed but different appearance information. We show that optimizing the two tasks jointly consistently improves the performance on downstream tasks, e.g., action recognition and video retrieval. Remarkably, for action recognition on the UCF-101 dataset, we achieve 90.8% accuracy without using any extra modalities or negative pairs for unsupervised pretraining, which outperforms the ImageNet supervised pretrained model. Codes and models will be available.

Neural painting refers to the procedure of producing a series of strokes for a given image and non-photo-realistically recreating it using neural networks. While reinforcement learning (RL) based agents can generate a stroke sequence step by step for this task, it is not easy to train a stable RL agent. On the other hand, stroke optimization methods search for a set of stroke parameters iteratively in a large search space; such low efficiency significantly limits their prevalence and practicality. Different from previous methods, in this paper, we formulate the task as a set prediction problem and propose a novel Transformer-based framework, dubbed Paint Transformer, to predict the parameters of a stroke set with a feed forward network. This way, our model can generate a set of strokes in parallel and obtain the final painting of size 512 × 512 in near real time. More importantly, since there is no dataset available for training the Paint Transformer, we devise a self-training pipeline such that it can be trained without any off-the-shelf dataset while still achieving excellent generalization capability. Experiments demonstrate that our method achieves better painting performance than previous ones with cheaper training and inference costs. Codes and models are available on https://github.com/wzmsltw/PaintTransformer.

Fast arbitrary neural style transfer has attracted widespread attention from academic, industrial and art communities due to its flexibility in enabling various applications. Existing solutions either attentively fuse deep style feature into deep content feature without considering feature distributions, or adaptively normalize deep content feature according to the style such that their global statistics are matched. Although effective, leaving shallow feature unexplored and without locally considering feature statistics, they are prone to unnatural output with unpleasing local distortions. To alleviate this problem, in this paper, we propose a novel attention and normalization module, named Adaptive Attention Normalization (AdaAttN), to adaptively perform attentive normalization on per-point basis. Specifically, spatial attention score is learnt from both shallow and deep features of content and style images. Then perpoint weighted statistics are calculated by regarding a style feature point as a distribution of attention-weighted output of all style feature points. Finally, the content feature is normalized so that they demonstrate the same local feature statistics as the calculated per-point weighted style feature statistics. Besides, a novel local feature loss is derived based on AdaAttN to enhance local visual quality. We also extend AdaAttN to be ready for video style transfer with slight modifications. Experiments demonstrate that our method achieves state-of-the-art arbitrary image/video style transfer. Codes and models are available on https://github.com/wzmsltw/AdaAttN.

Image Retrieval is a fundamental task of obtaining images similar to the query one from a database. A common image retrieval practice is to firstly retrieve candidate images via similarity search using global image features and then re-rank the candidates by leveraging their local features. Previous learning-based studies mainly focus on either global or local image representation learning to tackle the retrieval task. In this paper, we abandon the two-stage paradigm and seek to design an effective single-stage solution by integrating local and global information inside images into compact image representations. Specifically, we propose a Deep Orthogonal Local and Global (DOLG) information fusion framework for end-to-end image retrieval. It attentively extracts representative local information with multi-atrous convolutions and self-attention at first. Components orthogonal to the global image representation are then extracted from the local information. At last, the orthogonal components are concatenated with the global representation as a complementary, and then aggregation is performed to generate the final representation. The whole framework is end-to-end differentiable and can be trained with image-level labels. Extensive experimental results validate the effectiveness of our solution and show that our model achieves state-of-the-art image retrieval performances on Revisited Oxford and Paris datasets.1

Long-range and short-range temporal modeling are two complementary and crucial aspects of video recognition. Most of the state-of-the-arts focus on short-range spatio-temporal modeling and then average multiple snippet-level predictions to yield the final video-level prediction. Thus, their video-level prediction does not consider spatio-temporal features of how video evolves along the temporal dimension. In this paper, we introduce a novel Dynamic Segment Aggregation (DSA) module to capture relationship among snippets. To be more specific, we attempt to generate a dynamic kernel for a convolutional operation to aggregate long-range temporal information among adjacent snippets adaptively. The DSA module is an efficient plug-and-play module and can be combined with the off-the-shelf clip-based models (i.e., TSM, I3D) to perform powerful long-range modeling with minimal overhead. The final video architecture, coined as DSANet. We conduct extensive experiments on several video recognition benchmarks (i.e., Mini-Kinetics-200, Kinetics-400, Something-Something V1 and ActivityNet) to show its superiority. Our proposed DSA module is shown to benefit various video recognition models significantly. For example, equipped with DSA modules, the top-1 accuracy of I3D ResNet-50 is improved from 74.9% to 78.2% on Kinetics-400. Codes are available at https://github.com/whwu95/DSANet.

Inpainting arbitrary missing regions is challenging because learning valid features for various masked regions is nontrivial. Though U-shaped encoder-decoder frameworks have been witnessed to be successful, most of them share a common drawback of mask unawareness in feature extraction because all convolution windows (or regions), including those with various shapes of missing pixels, are treated equally and filtered with fixed learned kernels. To this end, we propose our novel mask-aware inpainting solution. Firstly, a Mask-Aware Dynamic Filtering (MADF) module is designed to effectively learn multi-scale features for missing regions in the encoding phase. Specifically, filters for each convolution window are generated from features of the corresponding region of the mask. The second fold of mask awareness is achieved by adopting Point-wise Normalization (PN) in our decoding phase, considering that statistical natures of features at masked points differentiate from those of unmasked points. The proposed PN can tackle this issue by dynamically assigning point-wise scaling factor and bias. Lastly, our model is designed to be an end-to-end cascaded refinement one. Supervision information such as reconstruction loss, perceptual loss and total variation loss is incrementally leveraged to boost the inpainting results from coarse to fine. Effectiveness of the proposed framework is validated both quantitatively and qualitatively via extensive experiments on three public datasets including Places2, CelebA and Paris StreetView.

Images or videos always contain multiple objects or actions. Multi-label recognition has been witnessed to achieve pretty performance attribute to the rapid development of deep learning technologies. Recently, graph convolution network (GCN) is leveraged to boost the performance of multi-label recognition. However, what is the best way for label correlation modeling and how feature learning can be improved with label system awareness are still unclear. In this paper, we propose a label graph superimposing framework to improve the conventional GCN+CNN framework developed for multi-label recognition in the following two aspects. Firstly, we model the label correlations by superimposing label graph built from statistical co-occurrence information into the graph constructed from knowledge priors of labels, and then multi-layer graph convolutions are applied on the final superimposed graph for label embedding abstraction. Secondly, we propose to leverage embedding of the whole label system for better representation learning. In detail, lateral connections between GCN and CNN are added at shallow, middle and deep layers to inject information of label system into backbone CNN for label-awareness in the feature learning process. Extensive experiments are carried out on MS-COCO and Charades datasets, showing that our proposed solution can greatly improve the recognition performance and achieves new state-of-the-art recognition performance.

Existing action localization approaches adopt shallow temporal convolutional networks (i.e., TCN) on 1D feature map extracted from video frames. In this paper, we empirically find that stacking more conventional temporal convolution layers actually deteriorates action classification performance, possibly ascribing to that all channels of 1D feature map, which generally are highly abstract and can be regarded as latent concepts, are excessively recombined in temporal convolution. To address this issue, we introduce a novel concept-wise temporal convolutional network (C-TCN) as an alternative to TCN for training deeper action localization networks. To address this issue, we introduce a novel concept-wise temporal convolution (CTC) layer as an alternative to conventional temporal convolution layer for training deeper action localization networks. Instead of recombining latent concepts, CTC layer deploys a number of temporal filters to each concept separately with shared filter parameters across concepts. Thus can capture common temporal patterns of different concepts and significantly enrich representation ability. Via stacking CTC layers, we proposed a deep concept-wise temporal convolutional network (C-TCN), which boosts the state-of-the-art action localization performance on THUMOS'14 from 42.8 to 52.1 in terms of mAP(%), achieving a relative improvement of 21.7%. Favorable result is also obtained on ActivityNet.

Despite the success of deep learning for static image understanding, it remains unclear what are the most effective network architectures for spatial-temporal modeling in videos. In this paper, in contrast to the existing CNN+RNN or pure 3D convolution based approaches, we explore a novel spatialtemporal network (StNet) architecture for both local and global modeling in videos. Particularly, StNet stacks N successive video frames into a super-image which has 3N channels and applies 2D convolution on super-images to capture local spatial-temporal relationship. To model global spatialtemporal structure, we apply temporal convolution on the local spatial-temporal feature maps. Specifically, a novel temporal Xception block is proposed in StNet, which employs a separate channel-wise and temporal-wise convolution over the feature sequence of a video. Extensive experiments on the Kinetics dataset demonstrate that our framework outperforms several state-of-the-art approaches in action recognition and can strike a satisfying trade-off between recognition accuracy and model complexity. We further demonstrate the generalization performance of the leaned video representations on the UCF101 dataset.

The task of video grounding, which temporally localizes a natural language description in a video, plays an important role in understanding videos. Existing studies have adopted strategies of sliding window over the entire video or exhaustively ranking all possible clip-sentence pairs in a presegmented video, which inevitably suffer from exhaustively enumerated candidates. To alleviate this problem, we formulate this task as a problem of sequential decision making by learning an agent which regulates the temporal grounding boundaries progressively based on its policy. Specifically, we propose a reinforcement learning based framework improved by multi-task learning and it shows steady performance gains by considering additional supervised boundary information during training. Our proposed framework achieves state-of-the-art performance on ActivityNet’18 DenseCaption dataset (Krishna et al. 2017) and Charades-STA dataset (Sigurdsson et al. 2016; Gao et al. 2017) while observing only 10 or less clips per video.

Video Recognition has drawn great research interest and great progress has been made. A suitable frame sampling strategy can improve the accuracy and efficiency of recognition. However, mainstream solutions generally adopt hand-crafted frame sampling strategies for recognition. It could degrade the performance, especially in untrimmed videos, due to the variation of frame-level saliency. To this end, we concentrate on improving untrimmed video classification via developing a learning-based frame sampling strategy. We intuitively formulate the frame sampling procedure as multiple parallel Markov decision processes, each of which aims at picking out a frame/clip by gradually adjusting an initial sampling. Then we propose to solve the problems with multi-agent reinforcement learning (MARL). Our MARL framework is composed of a novel RNN-based context-aware observation network which jointly models context information among nearby agents and historical states of a specific agent, a policy network which generates the probability distribution over a predefined action space at each step and a classification network for reward calculation as well as final recognition. Extensive experimental results show that our MARL-based scheme remarkably outperforms hand-crafted strategies with various 2D and 3D baseline methods. Our single RGB model achieves a comparable performance of ActivityNet v1.3 champion submission with multi-modal multi-model fusion and new state-of-the-art results on YouTube Birds and YouTube Cars.

Rate Control (RC) plays an important role in video encoding. Traditional solutions are using fixed rate or fixed quantization parameters as the unified rate-control targets for all videos in one given video application. However, unified rate-control targets tend to have some bad encoding cases because of applying wrong rate for the video content. In this paper, we propose one content-adaptive rate control solution. We employ one neural-network based model which can end-to-end learn the optimal rate-control target appropriate to the content characteristics. The experimental results show that the proposed model can predict the optimal rate-factor value with the accuracy up to 77.637%. With this model, the proposed video-encoding method can significantly decrease the encoding quality fluctuation.

We propose a progressive pseudo-analog video transmission scheme that simultaneously handles SNR and bandwidth variations with graceful quality degradation for mobile video streaming. With the inherited SNR-adaptability from pseudo-analog transmission, the proposed progressive solution acquires bandwidth adaptability through an innovative scheduling algorithm with optimal power allocation. The basic idea is to aggressively transmit or retransmit important coefficients so that distortion is minimized at the receiver after each received packet. We derive the closed-form expression of reduced distortion for each packet under given transmission power and known channel conditions, and show that the optimal solution can be obtained with a water-filling algorithm. We also illustrate through analyses and simulations that a near-optimal solution can be found through approximation when only statistical channel information is available. Simulations show that our solution approaches the performance upper bound of pseudo-analog transmission in an additive white Gaussian noise channel and significantly outperforms existing pseudo-analog solutions in a fast Rayleigh fading channel. Trace-driven emulations are also carried out to demonstrate the advantage of the proposed solution over the state-of-the-art digital and pseudo-analog solutions under a real dramatically varying wireless environment.

Efficient and robust wireless stereo video delivery is an enabling technology for various mobile 3D applications. Existing digital solutions have high source coding efficiency but are not robust to channel variations, while analog solutions have the opposite characteristics. In this paper, we design a novel hybrid digital-analog (HDA) solution to embrace the advantages of both solutions and avoid their drawbacks. Basically, in each pair of stereo frames, one frame is digitally encoded to ensure basic quality and the other is analogly processed to opportunistically utilize good channels for better quality. To improve the system efficiency, we design a zigzag coding structure such that both intra-view and inter-view correlations can be explored through prediction in the frames to be analogly coded. A reference selection mechanism is proposed to further improve the coding efficiency. In addition, we address the problem of optimal power and bandwidth allocation between digital and analog streams. We implement a system, named Swift, and perform extensive trace-driven evaluations based on a software-defined radio platform. We show that Swift outperforms an omniscient digital scheme under the same bandwidth and power constraints, or can have around 2x power saving in order to achieve comparable performance. Subjective quality assessment evidences that Swift provides significantly better visual quality than a straightforward HDA extension of SoftCast.

Mobile video live streaming is facing great challenges in offering high quality of experience (QoE) under varying channel conditions. In this paper, we propose a progressive pseudo-analog transmission scheme in which the received video quality gracefully adapts to both SNR and bandwidth variations. Building upon the emerging pseudoanalog video transmission, the proposed scheme further adopts a greedy approach to improve the received video quality with each allocated bandwidth share. The optimal scheduling and power allocation are derived under the mean squared error (MSE) criterion. Testbed evaluations show that the proposed scheme outperforms the state-of-the-art digital and analog transmission schemes by a notable margin.

Hybrid digital-analog (HDA) transmission has gained increasing attention recently in the context of wireless video delivery , for its ability to simultaneously achieve high transmission efficiency and smooth quality adaptation. However, previous systems are optimized solely based on the mean squared error criterion without taking the perceptual video quality into consideration. In this work, we propose a structure-preserving HDA video delivery system, named SharpCast, to improve both the objective and subjective visual quality. SharpCast decomposes a video into a content part and structure part. The latter is important to the human perception and therefore is protected with a robust digital transmission scheme. Then, the energy-intensive part in the content information is extracted and transmitted in digital for energy efficiency while the residual is transmitted in analog to achieve the desired smooth adaptation. We formulate the resource (power and bandwidth) allocation problem in SharpCast and solve the problem with a greedy strategy. Evaluations over nine standard 720p video sequences show that the proposed SharpCast system outperforms the state-of-the-art digital, analog, and HDA schemes by a notable margin in both peak signal-to-noise ratio (PSNR) and structural similarity (SSIM).