Generating stylized talking head with diverse head motions is crucial for achieving natural-looking videos but still remains challenging. Previous works either adopt a regressive method to capture the speaking style, resulting in a coarse style that is averaged across all training data, or employ a universal network to synthesize videos with different styles which causes suboptimal performance. To address these, we propose a novel dynamic-weight method, namely Say Anything with Any Style (SAAS), which queries the discrete style representation via a generative model with a learned style codebook. Specifically, we develop a multi-task VQ-VAE that incorporates three closely related tasks to learn a style codebook as a prior for style extraction. This discrete prior, along with the generative model, enhances the precision and robustness when extracting the speaking styles of the given style clips. By utilizing the extracted style, a residual architecture comprising a canonical branch and style-specific branch is employed to predict the mouth shapes conditioned on any driving audio while transferring the speaking style from the source to any desired one. To adapt to different speaking styles, we steer clear of employing a universal network by exploring an elaborate HyperStyle to produce the style-specific weights offset for the style branch. Furthermore, we construct a pose generator and a pose codebook to store the quantized pose representation, allowing us to sample diverse head motions aligned with the audio and the extracted style. Experiments demonstrate that our approach surpasses state-of-the-art methods in terms of both lip-synchronization and stylized expression. Besides, we extend our SAAS to video-driven style editing field and achieve satisfactory performance as well.
论文检索
输入标题、作者或关键词，从 2,866 篇学术成果中精准定位
Although automatically animating audio-driven talking heads has recently received growing interest, previous efforts have mainly concentrated on achieving lip synchronization with the audio, neglecting two crucial elements for generating expressive videos: emotion style and art style. In this paper, we present an innovative audio-driven talking face generation method called Style2Talker. It involves two stylized stages, namely Style-E and Style-A, which integrate text-controlled emotion style and picture-controlled art style into the final output. In order to prepare the scarce emotional text descriptions corresponding to the videos, we propose a labor-free paradigm that employs large-scale pretrained models to automatically annotate emotional text labels for existing audio-visual datasets. Incorporating the synthetic emotion texts, the Style-E stage utilizes a large-scale CLIP model to extract emotion representations, which are combined with the audio, serving as the condition for an efficient latent diffusion model designed to produce emotional motion coefficients of a 3DMM model. Moving on to the Style-A stage, we develop a coefficient-driven motion generator and an art-specific style path embedded in the well-known StyleGAN. This allows us to synthesize high-resolution artistically stylized talking head videos using the generated emotional motion coefficients and an art style source picture. Moreover, to better preserve image details and avoid artifacts, we provide StyleGAN with the multi-scale content features extracted from the identity image and refine its intermediate feature maps by the designed content encoder and refinement network, respectively. Extensive experimental results demonstrate our method outperforms existing state-of-the-art methods in terms of audio-lip synchronization and performance of both emotion style and art style.
While generic person re-identification has made remarkable improvement in recent years, these methods are designed under the assumption that the entire body of the person is available. This assumption brings about a significant performance degradation when suffering from occlusion caused by various obstacles in real-world applications. To address this issue, data-driven strategies have emerged to enhance the model's robustness to occlusion. Following the random erasing paradigm, these strategies typically employ randomly generated noise to supersede randomly selected image regions to simulate obstacles. However, the random strategy is not sensitive to location and content, meaning they cannot mimic real-world occlusion cases in application scenarios. To overcome this limitation and fully exploit the real scene information in datasets, this paper proposes a more intuitive and effective data-driven strategy named Saliency-Guided Patch Transfer (SPT). Combined with the vision transformer, SPT divides person instances and background obstacles using salient patch selection. By transferring person instances to different background obstacles, SPT can easily generate photo-realistic occluded samples. Furthermore, we propose an occlusion-aware Intersection over Union (OIoU) with mask-rolling to filter the more suitable combination and a class-ignoring strategy to achieve more stable processing. Extensive experimental evaluations conducted on occluded and holistic person re-identification benchmarks demonstrate that SPT provides a significant performance gain among different ViT-based ReID algorithms on occluded ReID.
Vision-Language Models (VLMs) such as CLIP have demonstrated remarkable generalization capabilities to downstream tasks. However, existing prompt tuning based frameworks need to parallelize learnable textual inputs for all categories, suffering from massive GPU memory consumption when there is a large number of categories in the target dataset. Moreover, previous works require to include category names within prompts, exhibiting subpar performance when dealing with ambiguous category names. To address these shortcomings, we propose Compound Text-Guided Prompt Tuning (TGP-T) that significantly reduces resource demand while achieving superior performance. We introduce text supervision to the optimization of prompts, which enables two benefits: 1) releasing the model reliance on the pre-defined category names during inference, thereby enabling more flexible prompt generation; 2) reducing the number of inputs to the text encoder, which decreases GPU memory consumption significantly. Specifically, we found that compound text supervisions, i.e., category-wise and content-wise, is highly effective, since they provide inter-class separability and capture intra-class variations, respectively. Moreover, we condition the prompt generation on visual features through a module called Bonder, which facilitates the alignment between prompts and visual features. Extensive experiments on few-shot recognition and domain generalization demonstrate that TGP-T achieves superior performance with consistently lower training costs. It reduces GPU memory usage by 93% and attains a 2.5% performance gain on 16-shot ImageNet. The code is available at https://github.com/EricTan7/TGP-T.
Frequency-Aware Deepfake Detection: Improving Generalizability through Frequency Space Domain Learning
PDF ↗This research addresses the challenge of developing a universal deepfake detector that can effectively identify unseen deepfake images despite limited training data. Existing frequency-based paradigms have relied on frequency-level artifacts introduced during the up-sampling in GAN pipelines to detect forgeries. However, the rapid advancements in synthesis technology have led to specific artifacts for each generation model. Consequently, these detectors have exhibited a lack of proficiency in learning the frequency domain and tend to overfit to the artifacts present in the training data, leading to suboptimal performance on unseen sources. To address this issue, we introduce a novel frequency-aware approach called FreqNet, centered around frequency domain learning, specifically designed to enhance the generalizability of deepfake detectors. Our method forces the detector to continuously focus on high-frequency information, exploiting high-frequency representation of features across spatial and channel dimensions. Additionally, we incorporate a straightforward frequency domain learning module to learn source-agnostic features. It involves convolutional layers applied to both the phase spectrum and amplitude spectrum between the Fast Fourier Transform (FFT) and Inverse Fast Fourier Transform (iFFT). Extensive experimentation involving 17 GANs demonstrates the effectiveness of our proposed method, showcasing state-of-the-art performance (+9.8\%) while requiring fewer parameters. The code is available at https://github.com/chuangchuangtan/FreqNet-DeepfakeDetection.
Although deep generative models have greatly improved one-shot video-driven talking head generation, few studies address fine-grained controllable facial expression editing, which is crucial for practical applications. Existing methods rely on a fixed set of predefined discrete emotion labels or simply copy expressions from input videos. This is limiting as expressions are complex, and methods using only emotion labels cannot generate fine-grained, accurate or mixed expressions. Generating talking head video with precise expressions is also difficult using 3D model-based approaches, as 3DMM only models facial movements and tends to produce deviations. In this paper, we propose a novel framework enabling fine-grained facial expression editing in talking face generation. Our goal is to achieve expression control by manipulating the intensities of individual facial Action Units (AUs) or groups. First, compared with existing methods which decouple the face into pose and expression, we propose a disentanglement scheme to isolates three components from the human face, namely, appearance, pose, and expression. Second, we propose to use input AUs to control muscle group intensities in the generated face, and integrate the AUs features with the disentangled expression latent code. Finally, we present a self-supervised training strategy with well-designed constraints. Experiments show our method achieves fine-grained expression control, produces high-quality talking head videos and outperforms baseline methods.
PathAsst: A Generative Foundation AI Assistant towards Artificial General Intelligence of Pathology
PDF ↗As advances in large language models (LLMs) and multimodal techniques continue to mature, the development of general-purpose multimodal large language models (MLLMs) has surged, offering significant applications in interpreting natural images. However, the field of pathology has largely remained untapped, particularly in gathering high-quality data and designing comprehensive model frameworks. To bridge the gap in pathology MLLMs, we present PathAsst, a multimodal generative foundation AI assistant to revolutionize diagnostic and predictive analytics in pathology. The development of PathAsst involves three pivotal steps: data acquisition, CLIP model adaptation, and the training of PathAsst's multimodal generative capabilities. Firstly, we collect over 207K high-quality pathology image-text pairs from authoritative sources. Leveraging the advanced power of ChatGPT, we generate over 180K instruction-following samples. Furthermore, we devise additional instruction-following data specifically tailored for invoking eight pathology-specific sub-models we prepared, allowing the PathAsst to effectively collaborate with these models, enhancing its diagnostic ability. Secondly, by leveraging the collected data, we construct PathCLIP, a pathology-dedicated CLIP, to enhance PathAsst's capabilities in interpreting pathology images. Finally, we integrate PathCLIP with the Vicuna-13b and utilize pathology-specific instruction-tuning data to enhance the multimodal generation capacity of PathAsst and bolster its synergistic interactions with sub-models. The experimental results of PathAsst show the potential of harnessing AI-powered generative foundation model to improve pathology diagnosis and treatment processes. We open-source our dataset, as well as a comprehensive toolkit for extensive pathology data collection and preprocessing at https://github.com/superjamessyx/Generative-Foundation-AI-Assistant-for-Pathology.
Hardware image signal processing (ISP), aiming at converting RAW inputs to RGB images, consists of a series of processing blocks, each with multiple parameters. Traditionally, ISP parameters are manually tuned in isolation by imaging experts according to application-specific quality and performance metrics, which is time-consuming and biased towards human perception due to complex interaction with the output image. Since the relationship between any single parameter’s variation and the output performance metric is a complex, non-linear function, optimizing such a large number of ISP parameters is challenging. To address this challenge, we propose a novel Sequential ISP parameter optimization model, called the RL-SeqISP model, which utilizes deep reinforcement learning to jointly optimize all ISP parameters for a variety of imaging applications. Concretely, inspired by the sequential tuning process of human experts, the proposed model can progressively enhance image quality by seamlessly integrating information from both the image feature space and the parameter space. Furthermore, a dynamic parameter optimization module is introduced to avoid ISP parameters getting stuck into local optima, which is able to more effectively guarantee the optimal parameters resulting from the sequential learning strategy. These merits of the RL-SeqISP model as well as its high efficiency are substantiated by comprehensive experiments on a wide range of downstream tasks, including two visual analysis tasks (instance segmentation and object detection), and image quality assessment (IQA), as compared with representative methods both quantitatively and qualitatively. In particular, even using only 10% of the training data, our model outperforms other SOTA methods by an average of 7% mAP on two visual analysis tasks.
CFR-ICL: Cascade-Forward Refinement with Iterative Click Loss for Interactive Image Segmentation
PDF ↗The click-based interactive segmentation aims to extract the object of interest from an image with the guidance of user clicks. Recent work has achieved great overall performance by employing feedback from the output. However, in most state-of-the-art approaches, 1) the inference stage involves inflexible heuristic rules and requires a separate refinement model, and 2) the number of user clicks and model performance cannot be balanced. To address the challenges, we propose a click-based and mask-guided interactive image segmentation framework containing three novel components: Cascade-Forward Refinement (CFR), Iterative Click Loss (ICL), and SUEM image augmentation. The CFR offers a unified inference framework to generate segmentation results in a coarse-to-fine manner. The proposed ICL allows model training to improve segmentation and reduce user interactions simultaneously. The proposed SUEM augmentation is a comprehensive way to create large and diverse training sets for interactive image segmentation. Extensive experiments demonstrate the state-of-the-art performance of the proposed approach on five public datasets. Remarkably, our model reduces by 33.2%, and 15.5% the number of clicks required to surpass an IoU of 0.95 in the previous state-of-the-art approach on the Berkeley and DAVIS sets, respectively.
Animal visual perception is an important technique for automatically monitoring animal health, understanding animal behaviors, and assisting animal-related research. However, it is challenging to design a deep learning-based perception model that can freely adapt to different animals across various perception tasks, due to the varying poses of a large diversity of animals, lacking data on rare species, and the semantic inconsistency of different tasks. We introduce UniAP, a novel Universal Animal Perception model that leverages few-shot learning to enable cross-species perception among various visual tasks. Our proposed model takes support images and labels as prompt guidance for a query image. Images and labels are processed through a Transformer-based encoder and a lightweight label encoder, respectively. Then a matching module is designed for aggregating information between prompt guidance and the query image, followed by a multi-head label decoder to generate outputs for various tasks. By capitalizing on the shared visual characteristics among different animals and tasks, UniAP enables the transfer of knowledge from well-studied species to those with limited labeled data or even unseen species. We demonstrate the effectiveness of UniAP through comprehensive experiments in pose estimation, segmentation, and classification tasks on diverse animal species, showcasing its ability to generalize and adapt to new classes with minimal labeled examples.
Video moment retrieval (MR) and highlight detection (HD) based on natural language queries are two highly related tasks, which aim to obtain relevant moments within videos and highlight scores of each video clip. Recently, several methods have been devoted to building DETR-based networks to solve both MR and HD jointly. These methods simply add two separate task heads after multi-modal feature extraction and feature interaction, achieving good performance. Nevertheless, these approaches underutilize the reciprocal relationship between two tasks. In this paper, we propose a task-reciprocal transformer based on DETR (TR-DETR) that focuses on exploring the inherent reciprocity between MR and HD. Specifically, a local-global multi-modal alignment module is first built to align features from diverse modalities into a shared latent space. Subsequently, a visual feature refinement is designed to eliminate query-irrelevant information from visual features for modal interaction. Finally, a task cooperation module is constructed to refine the retrieval pipeline and the highlight score prediction process by utilizing the reciprocity between MR and HD. Comprehensive experiments on QVHighlights, Charades-STA and TVSum datasets demonstrate that TR-DETR outperforms existing state-of-the-art methods. Codes are available at https://github.com/mingyao1120/TR-DETR.
A large amount of User Generated Content (UGC) is uploaded to the Internet daily and displayed to people world-widely through the client side (mobile and PC). This requires the cropping algorithms to produce the aesthetic thumbnail within a specific aspect ratio on different devices. However, existing image cropping works mainly focus on landmark or landscape images, which fail to model the relations among the multi-objects with the complex background in UGC. Besides, previous methods merely consider the aesthetics of the cropped images while ignoring the content integrity, which is crucial for UGC cropping. In this paper, we propose a Spatial-Semantic Collaborative cropping network (S2CNet) for arbitrary user generated content accompanied by a new cropping benchmark. Specifically, we first mine the visual genes of the potential objects. Then, the suggested adaptive attention graph recasts this task as a procedure of information association over visual nodes. The underlying spatial and semantic relations are ultimately centralized to the crop candidate through differentiable message passing, which helps our network efficiently to preserve both the aesthetics and the content integrity. Extensive experiments on the proposed UGCrop5K and other public datasets demonstrate the superiority of our approach over state-of-the-art counterparts.
LRANet: Towards Accurate and Efficient Scene Text Detection with Low-Rank Approximation Network
PDF ↗Recently, regression-based methods, which predict parameterized text shapes for text localization, have gained popularity in scene text detection. However, the existing parameterized text shape methods still have limitations in modeling arbitrary-shaped texts due to ignoring the utilization of text-specific shape information. Moreover, the time consumption of the entire pipeline has been largely overlooked, leading to a suboptimal overall inference speed. To address these issues, we first propose a novel parameterized text shape method based on low-rank approximation. Unlike other shape representation methods that employ data-irrelevant parameterization, our approach utilizes singular value decomposition and reconstructs the text shape using a few eigenvectors learned from labeled text contours. By exploring the shape correlation among different text contours, our method achieves consistency, compactness, simplicity, and robustness in shape representation. Next, we propose a dual assignment scheme for speed acceleration. It adopts a sparse assignment branch to accelerate the inference speed, and meanwhile, provides ample supervised signals for training through a dense assignment branch. Building upon these designs, we implement an accurate and efficient arbitrary-shaped text detector named LRANet. Extensive experiments are conducted on several challenging benchmarks, demonstrating the superior accuracy and efficiency of LRANet compared to state-of-the-art methods. Code is available at: https://github.com/ychensu/LRANet.git
Accurately predicting pedestrian movements in complex environments is challenging due to social interactions, scene constraints, and pedestrians' multimodal behaviors. Sequential models like long short-term memory fail to effectively integrate scene features to make predicted trajectories comply with scene constraints due to disparate feature modalities of scene and trajectory. Though existing convolution neural network (CNN) models can extract scene features, they are ineffective in mapping these features into scene constraints for pedestrians and struggle to model pedestrian interactions due to the loss of target pedestrian information. To address these issues, we propose a unified environmental network based on CNN for pedestrian trajectory prediction. We introduce a polar-based method to reflect the distance and direction relationship between any position in the environment and the target pedestrian. This enables us to simultaneously model scene constraints and pedestrian social interactions in the form of feature maps. Additionally, we capture essential local features in the feature map, characterizing potential multimodal movements of pedestrians at each time step to prevent redundant predicted trajectories. We verify the performance of our proposed model on four trajectory prediction datasets, encompassing both short-term and long-term predictions. The experimental results demonstrate the superiority of our approach over existing methods.
F³-Pruning: A Training-Free and Generalized Pruning Strategy towards Faster and Finer Text-to-Video Synthesis
PDF ↗Recently Text-to-Video (T2V) synthesis has undergone a breakthrough by training transformers or diffusion models on large-scale datasets. Nevertheless, inferring such large models incurs huge costs. Previous inference acceleration works either require costly retraining or are model-specific. To address this issue, instead of retraining we explore the inference process of two mainstream T2V models using transformers and diffusion models. The exploration reveals the redundancy in temporal attention modules of both models, which are commonly utilized to establish temporal relations among frames. Consequently, we propose a training-free and generalized pruning strategy called F3-Pruning to prune redundant temporal attention weights. Specifically, when aggregate temporal attention values are ranked below a certain ratio, corresponding weights will be pruned. Extensive experiments on three datasets using a classic transformer-based model CogVideo and a typical diffusion-based model Tune-A-Video verify the effectiveness of F3-Pruning in inference acceleration, quality assurance and broad applicability.
Video-to-music generation demands both a temporally localized high-quality listening experience and globally aligned video-acoustic signatures. While recent music generation models excel at the former through advanced audio codecs, the exploration of video-acoustic signatures has been confined to specific visual scenarios. In contrast, our research confronts the challenge of learning globally aligned signatures between video and music directly from paired music and videos, without explicitly modeling domain-specific rhythmic or semantic relationships. We propose V2Meow, a video-to-music generation system capable of producing high-quality music audio for a diverse range of video input types using a multi-stage autoregressive model. Trained on 5k hours of music audio clips paired with video frames mined from in-the-wild music videos, V2Meow is competitive with previous domain-specific models when evaluated in a zero-shot manner. It synthesizes high-fidelity music audio waveforms solely by conditioning on pre-trained general-purpose visual features extracted from video frames, with optional style control via text prompts. Through both qualitative and quantitative evaluations, we demonstrate that our model outperforms various existing music generation systems in terms of visual-audio correspondence and audio quality. Music samples are available at tinyurl.com/v2meow.
Text-based person search is a challenging task aimed at locating specific target pedestrians through text descriptions. Recent advancements have been made in this field, but there remains a deficiency in datasets tailored for text-based person search. The creation of new, real-world datasets is hindered by concerns such as the risk of pedestrian privacy leakage and the substantial costs of annotation. In this paper, we introduce a framework, named Diverse Person (DP), to achieve efficient and high-quality text-based person search data generation without involving privacy concerns. Specifically, we propose to leverage available images of clothing and accessories as reference attribute images to edit the original dataset images through diffusion models. Additionally, we employ a Large Language Model (LLM) to produce annotations that are both high in quality and stylistically consistent with those found in real-world datasets. Extensive experimental results demonstrate that the baseline models trained with our DP can achieve new state-of-the-art results on three public datasets, with performance improvements up to 4.82%, 2.15%, and 2.28% on CUHK-PEDES, ICFG-PEDES, and RSTPReid in terms of Rank-1 accuracy, respectively.
Few-shot learning poses a formidable challenge as it necessitates effective recognition of novel classes based on a limited set of examples. Recent studies have sought to address the challenge of rare samples by tuning visual features through the utilization of external text prompts. However, the performance of these methods is constrained due to the inherent modality gap between the prompt text and image features. Instead of naively utilizing the external semantic information generated from text to guide the training of the image encoder, we propose a novel self-prompt mechanism (SPM) to adaptively adjust the neural network according to unseen data. Specifically, SPM involves a systematic selection of intrinsic semantic features generated by the image encoder across spatial and channel dimensions, thereby engendering self-prompt information. Subsequently, upon backpropagation of this self-prompt information to the deeper layers of the neural network, it effectively steers the network toward the learning and adaptation of new samples. Meanwhile, we propose a novel parameter-efficient tuning method that exclusively fine-tunes the parameters relevant to self-prompt (prompts are no more than 2% of the total parameters), and the incorporation of additional learnable parameters as self-prompt ensures the retention of prior knowledge through frozen encoder weights. Therefore, our method is highly suited for few-shot recognition tasks that require both information retention and adaptive adjustment of network parameters with limited labeling data constraints. Extensive experiments demonstrate the effectiveness of the proposed SPM in both 5-way 1-shot and 5-way 5-shot settings for standard single-domain and cross-domain few-shot recognition datasets, respectively. Our code is available at https://github.com/codeshop715/SPM.
The development of autoregressive modeling (AM) in computer vision lags behind natural language processing (NLP) in self-supervised pre-training. This is mainly caused by the challenge that images are not sequential signals and lack a natural order when applying autoregressive modeling. In this study, inspired by human beings’ way of grasping an image, i.e., focusing on the main object first, we present a semantic-aware autoregressive image modeling (SemAIM) method to tackle this challenge. The key insight of SemAIM is to autoregressively model images from the semantic patches to the less semantic patches. To this end, we first calculate a semantic-aware permutation of patches according to their feature similarities and then perform the autoregression procedure based on the permutation. In addition, considering that the raw pixels of patches are low-level signals and are not ideal prediction targets for learning high-level semantic representation, we also explore utilizing the patch features as the prediction targets. Extensive experiments are conducted on a broad range of downstream tasks, including image classification, object detection, and instance/semantic segmentation, to evaluate the performance of SemAIM. The results demonstrate SemAIM achieves state-of-the-art performance compared with other self-supervised methods. Specifically, with ViT-B, SemAIM achieves 84.1% top-1 accuracy for fine-tuning on ImageNet, 51.3% AP and 45.4% AP for object detection and instance segmentation on COCO, which outperforms the vanilla MAE by 0.5%, 1.0%, and 0.5%, respectively. Code is available at https://github.com/skyoux/SemAIM.
The performance of existing unsupervised video object segmentation methods typically suffers from severe performance degradation on test videos when tested in out-of-distribution scenarios. The primary reason is that the test data in real- world may not follow the independent and identically distribution (i.i.d.) assumption, leading to domain shift. In this paper, we propose a generalizable fourier augmentation method during training to improve the generalization ability of the model. To achieve this, we perform Fast Fourier Transform (FFT) over the intermediate spatial domain features in each layer to yield corresponding frequency representations, including amplitude components (encoding scene-aware styles such as texture, color, contrast of the scene) and phase components (encoding rich semantics). We produce a variety of style features via Gaussian sampling to augment the training data, thereby improving the generalization capability of the model. To further improve the cross-domain generalization performance of the model, we design a phase feature update strategy via exponential moving average using phase features from past frames in an online update manner, which could help the model to learn cross-domain-invariant features. Extensive experiments show that our proposed method achieves the state-of-the-art performance on popular benchmarks.