Conversational Speech Synthesis (CSS) aims to express a target utterance with the proper speaking style in a user-agent conversation setting. Existing CSS methods employ effective multi-modal context modeling techniques to achieve empathy understanding and expression. However, they often need to design complex network architectures and meticulously optimize the modules within them. In addition, due to the limitations of small-scale datasets containing scripted recording styles, they often fail to simulate real natural conversational styles. To address the above issues, we propose a novel generative expressive CSS system, termed GPT-Talker.We transform the multimodal information of the multi-turn dialogue history into discrete token sequences and seamlessly integrate them to form a comprehensive user-agent dialogue context. Leveraging the power of GPT, we predict the token sequence, that includes both semantic and style knowledge, of response for the agent. After that, the expressive conversational speech is synthesized by the conversation-enriched VITS to deliver feedback to the user.Furthermore, we propose a large-scale Natural CSS Dataset called NCSSD, that includes both naturally recorded conversational speech in improvised styles and dialogues extracted from TV shows. It encompasses both Chinese and English languages, with a total duration of 236 hours. We conducted comprehensive experiments on the reliability of the NCSSD and the effectiveness of our GPT-Talker. Both subjective and objective evaluations demonstrate that our model outperforms other state-of-the-art CSS systems significantly in terms of naturalness and expressiveness. The Code, Dataset, and Pre-trained Model are available at: https://github.com/AI-S2-Lab/GPT-Talker.
论文检索
输入标题、作者或关键词，从 1,237 篇学术成果中精准定位
Visual grounding is a task of locating the object referred by a natural language description. To reduce annotation costs, recent researchers are devoted into one-stage weakly supervised methods for visual grounding, which typically adopt the anchor-text matching paradigm. Despite the efficiency, we identify that anchor representations are often noisy and insufficient to describe object information, which inevitably hinders the vision-language alignments. In this paper, we propose a novel query-based one-stage framework for weakly supervised visual grounding, namely QueryMatch. Different from previous work, QueryMatch represents candidate objects with a set of query features, which inherently establish accurate one-to-one associations with visual objects. In this case, QueryMatch re-formulates weakly supervised visual grounding as a query-text matching problem, which can be optimized via the query-based contrastive learning. Based on QueryMatch, we further propose an innovative strategy for effective weakly supervised learning, namely Active Query Selection (AQS). In particular, AQS aims to enhance the effectiveness of query-based contrastive learning by actively selecting high-quality query features. Through this strategy, AQS can greatly benefit the weakly supervised learning of QueryMatch. To validate our approach, we conduct extensive experiments on three benchmark datasets of two grounding tasks, i.e., referring expression comprehension (REC) and segmentation (RES). Experimental results not only show the state-of-art performance of QueryMatch in two tasks, e.g., over +5% IoU@0.5 on RefCOCO in REC and over +20% mIOU on RefCOCO in RES, but also confirm the effectiveness of AQS in weakly supervised learning. Source codes are available at https://github.com/TensorThinker/QueryMatch.
Although multi-view learning has achieved remarkable progress over the past decades, most existing methods implicitly assume that all views (or modalities) are well-aligned. In practice, however, collecting fully aligned views is challenging due to complexities and discordances in time and space, resulting in the Partially View-unaligned Problem (PVP), such as audio-video asynchrony caused by network congestion. While some methods are proposed to align the unaligned views by learning view-invariant representations, almost all of them overlook specific information across different views for complementarity, limiting performance improvement. To address these problems, we propose a robust framework, dubbed VariatIonal ConTrAstive Learning (VITAL), designed to learn both common and specific information simultaneously. To be specific, each data sample is first modeled as a Gaussian distribution in the latent space, where the mean estimates the most probable common information, while the variance indicates view-specific information. Second, by using variational inference, VITAL conducts intra- and inter-view contrastive learning to preserve common and specific semantics in the distribution representations, thereby achieving comprehensive perception. As a result, the common representation (mean) could be used to guide category-level realignment, while the specific representation (variance) complements sample semantic information, thereby boosting overall performance. Finally, considering the abundance of False Negative Pairs (FNPs) generated by unsupervised contrastive learning, we propose a robust loss function that seamlessly incorporates FNP rectification into the contrastive learning paradigm. Empirical evaluations on eight benchmark datasets reveal that VITAL outperforms ten state-of-the-art deep clustering baselines, demonstrating its efficacy in both partially and fully aligned scenarios. The Code is available at https://github.com/He-Changhao/2024-MM-VITAL.
Building on recent breakthroughs in diffusion-based text-to-image synthesis (TIS), training-free text-guided image editing (TIE) has emerged as an indispensable aspect of modern image editing practices. This technique involves the modification of features within attention layers to alter objects or their attributes within images during the generation process. Despite its utility, current image editing algorithms face challenges, particularly when editing multiple objects in an image. In this paper, we introduce VICTORIA, a novel approach that augments TIE by incorporating linguistic knowledge into the manipulation of attention maps during image generation. VICTORIA capitalizes on mechanisms within self-attention layers to ensure spatial consistency between source and target images. Further, we design a novel loss function that refines cross-attention maps, ensuring their alignment with linguistic constraints, thereby enhancing the editing precision of multiple target objects. We also present a linguistic mask blending technique that aids in the retention of information in regions not subjected to modification. Experimental results across seven diverse datasets show that VICTORIA achieves significant improvements over state-of-the-art methods. Our work underscores the critical role and effectiveness of linguistic analysis in elevating the performance of TIE, with a specific emphasis on multi-object scenarios. The code is available at https://github.com/alibaba/EasyNLP/tree/master/diffusion/VICTORIA.
Change captioning involves describing the subtle changes between a pair of similar images. Although existing efforts have achieved compelling success, they overlook the potential of multimodal large language models (MLLMs) in tackling this challenging task. In this work, we aim to empower MLLMs with the capability to perceive subtle differences between paired images and enhance their performance in generating change captions. Specifically, we present a diFferentIal-perceptive aNd rEtRieval-augmented MLLM (FINER-MLLM) tailored for this task. In particular, FINER-MLLM leverages LoRA fine-tuned MLLM's image encoder to extract image patch features, enabling the capture of detailed image information. Subsequently, within MLLM's feature extraction, typically Q-Former, FINER-MLLM incorporates dual constraints: the intra-image feature independence constraint and the inter-image feature alignment constraint. These constraints ensure that the features can comprehensively extract subtle visual information within each image and that corresponding features across images align effectively. Last, we introduced the retrieval augmentation to first retrieve the relevant corpus to facilitate the MLLM's decoder i.e., LLM, in generating accurate change captions. Extensive experiments on three benchmark datasets, i.e., CLEVR-Change, Spot-the-Diff, and Image-Editing-Request, demonstrate the superiority of our proposed method.
LiDAR-based 3D object detection has seen impressive advances in recent times. However, deploying trained 3D detectors in the real world often yields unsatisfactory performance when the distribution of the test data significantly deviates from the training data due to different weather conditions, object sizes, etc. A key factor in this performance degradation is the diminished generalizability of pre-trained models, which creates a sharp loss landscape during training. Such sharpness, when encountered during testing, can precipitate significant performance declines, even with minor data variations. To address the aforementioned challenges, we propose dual-perturbation optimization (DPO) for Test-time Adaptation in 3D Object Detection (TTA-3OD). We minimize the sharpness to cultivate a flat loss landscape to ensure model resiliency to minor data variations, thereby enhancing the generalization of the adaptation process. To fully capture the inherent variability of the test point clouds, we further introduce adversarial perturbation to the input BEV features to better simulate the noisy test environment. As the dual perturbation strategy relies on trustworthy supervision signals, we utilize a reliable Hungarian matcher to filter out pseudo-labels sensitive to perturbations. Additionally, we introduce early Hungarian cutoff to avoid error accumulation from incorrect pseudo-labels by halting the adaptation process. Extensive experiments across three types of transfer tasks demonstrate that the proposed DPO significantly surpasses previous state-of-the-art approaches, specifically on Waymo → KITTI, outperforming the most competitive baseline by 57.72% in AP3D and reaching 91% of the fully supervised upper bound. Our code is available at https://github.com/Jo-wang/DPO.
Recently, diffusion-based depth estimation methods have drawn widespread attention due to their elegant denoising patterns and promising performance. However, they are typically unreliable under adverse conditions prevalent in real-world scenarios, such as rainy, snowy, etc. In this paper, we propose a novel robust depth estimation method called D4RD, featuring a custom contrastive learning mode tailored for diffusion models to mitigate performance degradation in complex environments. Concretely, we integrate the strength of knowledge distillation into contrastive learning, building the 'trinity' contrastive scheme. This scheme utilizes the sampled noise of the forward diffusion process as a natural reference, guiding the predicted noise in diverse scenes toward a more stable and precise optimum. Moreover, we extend noise-level trinity to encompass more generic feature and image levels, establishing a multi-level contrast to distribute the burden of robust perception across the overall network. Before addressing complex scenarios, we enhance the stability of the baseline diffusion model with three straightforward yet effective improvements, which facilitate convergence and remove depth outliers. Extensive experiments demonstrate that D4RD surpasses existing state-of-the-art solutions on synthetic corruption datasets and real-world weather conditions. Source code and data are available at https://github.com/wangjiyuan9/D4RD.
Multi-relational graph clustering has demonstrated remarkable success in uncovering underlying patterns in complex networks. Representative methods manage to align different views motivated by advances in contrastive learning. Our empirical study finds the pervasive presence of imbalance in real-world graphs, which is in principle contradictory to the motivation of alignment. In this paper, we first propose a novel metric, the Aggregation Class Distance, to empirically quantify structural disparities among different graphs. To address the challenge of view imbalance, we propose Balanced Multi-Relational Graph Clustering (BMGC), comprising unsupervised dominant view mining and dual signals guided representation learning. It dynamically mines the dominant view throughout the training process, synergistically improving clustering performance with representation learning. Theoretical analysis ensures the effectiveness of dominant view mining. Extensive experiments and in-depth analysis on real-world and synthetic datasets showcase that BMGC achieves state-of-the-art performance, underscoring its superiority in addressing the view imbalance inherent in multi-relational graphs. The source code and datasets are available at https://github.com/zxlearningdeep/BMGC.
RGB-Thermal Salient Object Detection (RGBT-SOD) plays a critical role in complex scene recognition applications, such as autonomous driving. However, security research in this domain is still in its infancy. This paper presents the first backdoor attack on RGBT-SOD systems, generating saliency maps on triggered inputs that depict non-existent salient objects chosen by the attacker or falsely mark an entire image as fully salient or entirely non-salient. We uncover that triggers have an influence range for generating non-existent salient objects, supported by a theoretical analysis. Extensive experiments show the effectiveness of our attack in both digital and physical-world scenarios. Notably, our dual-modality backdoor attack achieves an Attack Success Rate (ASR) of 86.72% with only five pairs of poisoned images in model training. After investigating potential countermeasures, we find them inadequate in mitigating our attacks, highlighting the urgent need for robust defenses against sophisticated backdoor attacks in RGBT-SOD systems.
FBSDiff: Plug-and-Play Frequency Band Substitution of Diffusion Features for Highly Controllable Text-Driven Image Translation
PDF ↗Large-scale text-to-image diffusion models have been a revolutionary milestone in the evolution of generative AI, allowing wonderful image generation with natural-language text prompt. However, the issue of lacking controllability of such models restricts their practical applicability for real-life content creation. Thus, attention has been focused on leveraging a reference image to control text-to-image synthesis, which is also regarded as manipulating (or editing) a reference image as per a text prompt, namely, text-driven image-to-image translation. This paper contributes a novel, concise, and efficient approach that adapts pre-trained large-scale text-to-image (T2I) diffusion model to the image-to-image (I2I) paradigm in a plug-and-play manner, realizing high-quality and versatile text-driven I2I translation without model training, fine-tuning, or online optimization process. To guide T2I generation with a reference image, we propose to decompose diverse guiding factors with different frequency bands of diffusion features in the DCT spectral space, and accordingly devise a novel frequency band substitution layer which realizes dynamic control of the reference image to the T2I generation result in a plug-and-play manner. We demonstrate that our method allows flexible control over both guiding factor and guiding intensity of the reference image simply by tuning the type and bandwidth of the substituted frequency band, respectively. Extensive qualitative and quantitative experiments verify superiority of our approach over related methods in I2I translation visual quality, versatility, and controllability. Our project is publicly available at: https://xianggao1102.github.io/FBSDiff_webpage/.
Symbols play a pivotal role in the documentation and dissemination of art. For instance, we use musical scores and dance notation to document musical compositions and choreographic movements. Existing hand representations do not fit well with hand movement documentation since (1) data-oriented representations, e.g., coordinates of hand keypoints, are not intuitive and vulnerable to noise, and (2) the sign language, another widely adopted representation for hand movements, focuses solely on semantic interaction rather than action encoding. To balance intuitiveness and precision, we propose a novel notation system, named Hand Labanotation (HL), for hand movement documentation. We first introduce a new HL dataset comprising 4M annotated images. Thereon, we propose a novel multi-view transformer architecture for automatically translating hand movements to HL. Extensive experiments demonstrate the promising capacity of our method for representing hand movements. This makes our method a general tool for hand movement documentation, driving various downstream applications like using HL to control robotic hands.
Tracking by detection has been the prevailing paradigm in the field of Multi-object Tracking (MOT). These methods typically rely on the Kalman Filter to estimate the future locations of objects, assuming linear object motion. However, they fall short when tracking objects exhibiting nonlinear and diverse motion in scenarios like dancing and sports. In addition, there has been limited focus on utilizing learning-based motion predictors in MOT. To address these challenges, we resort to exploring data-driven motion prediction methods. Inspired by the great expectation of state space models (SSMs), such as Mamba, in long-term sequence modeling with near-linear complexity, we introduce a Mamba-based motion model named Mamba moTion Predictor (MTP). MTP is designed to model the complex motion patterns of objects like dancers and athletes. Specifically, MTP takes the spatial-temporal location dynamics of objects as input, captures the motion pattern using a bi-Mamba encoding layer, and predicts the next motion. In real-world scenarios, objects may be missed due to occlusion or motion blur, leading to premature termination of their trajectories. To tackle this challenge, we further expand the application of MTP. We employ it in an autoregressive way to compensate for missing observations by utilizing its own predictions as inputs, thereby contributing to more consistent trajectories. Our proposed tracker, MambaTrack, demonstrates advanced performance on benchmarks such as Dancetrack and SportsMOT, which are characterized by complex motion and severe occlusion.
Vision and Language Navigation (VLN) is a challenging task that requires agents to understand instructions and navigate to the destination in a visual environment. One of the key challenges in outdoor VLN is keeping track of which part of the instruction was completed. To alleviate this problem, previous works mainly focus on grounding the natural language to the visual input, but neglecting the crucial role of the agent's spatial position information in the grounding process. In this work, we first explore the substantial effect of spatial position locating on the grounding of outdoor VLN, drawing inspiration from human navigation. In real-world navigation scenarios, before planning a path to the destination, humans typically need to figure out their current location. This observation underscores the pivotal role of spatial localization in the navigation process. In this work, we introduce a novel framework, Locating before Planning (Loc4Plan), designed to incorporate spatial perception for action planning in outdoor VLN tasks. The main idea behind Loc4Plan is to perform the spatial localization before planning a decision action based on corresponding guidance, which comprises a block-aware spatial locating (BAL) module and a spatial-aware action planning (SAP) module. Specifically, to help the agent perceive its spatial location in the environment, we propose to learn a position predictor that measures how far the agent is from the next intersection for reflecting its position, which is achieved by the BAL module. After this locating process, we propose the PSA module to associate visual observations After the locating process, we propose the SAP module to incorporate spatial information to ground the corresponding guidance and enhance the precision of action planning. Extensive experiments on the Touchdown and map2seq datasets show that the proposed Loc4Plan outperforms the SOTA methods.
Cross-resolution person re-identification (CR-ReID) aims to match images of the same person with different resolutions in different scenarios. Existing CR-ReID methods achieve promising performance by relying on large-scale manually annotated identity labels. However, acquiring manual labels requires considerable human effort, greatly limiting the flexibility of existing CR-ReID methods. To address this issue, we propose a dual-resolution fusion modeling (DRFM) framework to tackle the CR-ReID problem in an unsupervised manner. Firstly, we design a cross-resolution pseudo-label generation (CPG) method, which initially clusters high-resolution images and then obtains reliable identity pseudo-labels by fusing class vectors in both resolution spaces. Subsequently, we develop a cross-resolution feature fusion (CRFF) module to fuse features from both high-resolution and low-resolution spaces. The fusion features have the potential to serve as a new form of resolution-invariant features. Finally, we introduce cross-resolution contrastive loss and probability sharpening loss in DRFM to facilitate resolution-invariant learning and effectively utilize ambiguous samples for optimization. Experimental results on multiple CR-ReID datasets demonstrate that the proposed DRFM not only outperforms existing unsupervised methods but also approaches the performance of early supervised methods.
Person re-identification (ReID) is crucial in video surveillance, aiming to match individuals across different camera views while cloth-changing person re-identification (CC-ReID) focuses on pedestrians changing attire. Many existing CC-ReID methods overlook generalization, crucial for universality across cloth-consistent and cloth-changing scenarios. This paper pioneers exploring the cloth-generalized person re-identification (CG-ReID) task and introduces the Cloth-aware Augmentation (CaAug) strategy. Comprising domain augmentation and feature augmentation, CaAug aims to learn identity-relevant features adaptable to both scenarios. Domain augmentation involves creating diverse fictitious domains and simulating various clothing scenarios. Supervising features from different cloth domains enhances robustness and generalization against clothing changes. Additionally, for feature augmentation, element exchange introduces diversity concerning clothing changes. Regularizing the model with these augmented features strengthens resilience against clothing change uncertainty. Extensive experiments on cloth-changing datasets demonstrate the efficacy of our approach, consistently outperforming state-of-the-art methods.
3D face recognition is subject to frequent spoofing attacks, in which 3D face presentation attack is one of the most notorious attacks. The attacker takes advantages of 3D scanning and printing techniques to generate masks of targets, which has found success in numerous real-life examples. The salient feature in such attacks is to obtain 3D face models through 3D scanning, though relatively more expensive and inconvenient when comparing with 2D photos. In this work, we propose a new method, DREAM, to recover 3D face models from single 2D image. Specifically, we adopt a black-box approach, which recovers 'sufficient' depths to defeat target recognition models (e.g., face identification and face authentication models) by accessing its output and the corresponding RGB photo. The key observation is that it is not necessary to restore the true value of depths, but only need to recover the essential features relevant to the target model. We used four public 3D face datasets to verify the effectiveness of DREAM. The experimental results show that DREAM can achieve a success rate of 94% on face authentication model, even in cross-dataset testing, and a success rate of 36% on face identification model.
Identifying social media posts that spread vaccine misinformation can inform emerging public health risks and aid in designing effective communication interventions. Existing studies, while promising, often rely on single user posts, potentially leading to flawed conclusions. This highlights the necessity to model users' historical posts for a comprehensive understanding of their stance towards vaccines. However, users' historical posts may contain a diverse range of content that adds noise and leads to low performance. To address this gap, in this study, we present VaxMine, a cooperative multi-agent reinforcement learning method that automatically selects relevant textual and visual content from a user's posts, reducing noise. To evaluate the performance of the proposed method, we create and release a new dataset of 2,072 users with historical posts due to the unavailability of publicly available datasets. The experimental results show that our approach outperforms state-of-the-art methods with an F1-Score of 0.94 (an absolute increase of 13%), demonstrating that extracting relevant content from users' historical posts and understanding both modalities are essential to detecting anti-vaccine users on social media. We further analyze the robustness and generalizability of VaxMine, showing that extracting relevant textual and visual content from a user's posts improves performance. We conclude with a discussion of the practical implications of our study by explaining how computational methods used in surveillance can benefit from our work, with flow-on effects on the design of health communication interventions to counter vaccine misinformation on social media.
In the domain of generative multimedia and interactive experiences, generating realistic and accurate full-body poses from sparse tracking is crucial for many real-world applications, while achieving sequence modeling and efficient motion generation remains challenging. Recently, state space models (SSMs) with efficient hardware-aware designs (i.e., Mamba) have shown great potential for sequence modeling, particularly in temporal contexts. However, processing motion data is still challenging for SSMs. Specifically, the sparsity of input conditions makes motion generation an ill-posed problem. Moreover, the complex structure of the human body further complicates this task. To address these issues, we present Motion Mamba Diffusion (MMD), a novel conditional diffusion model, which effectively utilizes the sequence modeling capability of SSMs and the robust generation ability of diffusion models to track full-body poses accurately. In particular, we design a bidirectional Temporal Mamba Module (TMM) to model motion sequence. Additionally, a Spatial Mamba Module (SMM) is further proposed for feature enhancement within a single frame. Extensive experiments on the large motion capture dataset (AMASS) demonstrate that our proposed approach outperforms the latest methods in terms of accuracy and smoothness, thus providing a crucial advancement for creating realistic virtual avatars in various applications.
The limited data availability and the low signal-to-noise ratio of fMRI signals lead to the challenging task of fMRI-to-image retrieval. State-of-the-art MindEye remarkably improves fMRI-to-image retrieval performance by leveraging a large model, i.e., a 996M MLP Backbone per subject, to align fMRI embeddings to the final hidden layer of CLIP's Vision Transformer (ViT). However, significant individual variations exist among subjects, even under identical experimental setups, mandating the training of large subject-specific models. The substantial parameters pose significant challenges in deploying fMRI decoding on practical devices. To this end, we propose Lite-Mind, a lightweight, efficient, and robust brain representation learning paradigm based on Discrete Fourier Transform (DFT), which efficiently aligns fMRI voxels to fine-grained information of CLIP. We elaborately design a DFT backbone with Spectrum Compression and Frequency Projector modules to learn informative and robust voxel embeddings. Our experiments demonstrate that Lite-Mind achieves an impressive 94.6% fMRI-to-image retrieval accuracy on the NSD dataset for Subject 1, with 98.7% fewer parameters than MindEye. Lite-Mind is also proven to be able to be migrated to smaller fMRI datasets and establishes a new state-of-the-art for zero-shot classification on the GOD dataset.
Sleep staging is crucial for sleep tracking and health assessment. Polysomnography (PSG), containing multiple modalities such as electroencephalography, electrooculography, electromyography, and electrocardiography, is the fundamental means of sleep staging. However, due to performance differences in both classification and domain discrimination across modalities in PSG, existing domain generalization methods face a dilemma of modal imbalance. To balance inter-modal differences and achieve highly accurate cross-domain sleep staging, we propose SleepMG, a Multimodal Generalizable Sleep staging method. SleepMG assesses the classification and domain discrimination performances of each modality and further defines the modal performance metrics by calculating the variance between the performance score and the average performance of each modality. Guided by these metrics, the gradients of the classifier and domain discriminator are adaptively adjusted, placing greater emphasis on poorly-balanced modalities while reducing emphasis on well-balanced modalities. Experimental results on public sleep staging datasets demonstrate that SleepMG outperforms state-of-the-art sleep staging methods, effectively balancing multiple modalities as evidenced by the visual experiment of modal imbalance degree.