ACM MM 2024 论文列表

Ancient artifacts are an important medium for cultural preservation and restoration. However, many physical copies of artifacts are either damaged or lost, leaving a blank space in archaeological and historical studies that calls for techniques to re-visualize these artifacts. Despite the significant advancements in open-domain text-to-image synthesis, existing approaches fail to capture the important domain knowledge presented in the textual descriptions of artifacts, resulting in errors in recreated images such as incorrect shapes and patterns. In this paper, we propose a novel knowledge-aware artifact image synthesis approach that brings lost historical objects accurately into their visual forms. We use a pretrained diffusion model as backbone and introduce three key techniques to enhance the text-to-image generation framework: 1) we construct prompts with explicit archaeological knowledge elicited from large language models (LLMs); 2) we incorporate additional textual guidance to correlated historical expertise in a contrastive manner; 3) we introduce further visual-semantic constraints on edge and perceptual features that enable our model to learn more intricate visual details of the artifacts. Compared to existing approaches, our proposed model produces higher-quality artifact images that align better with the implicit details and historical knowledge contained within written documents, thus achieving significant improvements both across automatic metrics and in human evaluation.

Unsupervised domain adaptation (UDA) has been a crucial way for cross-domain semantic segmentation of remote sensing images and reached apparent advents. However, most existing efforts focus on single source single target domain adaptation, which don't explicitly consider the serious domain shift between multiple source and target domains in real applications, especially inter-domain shift between various target domains and intra-domain shift within each target domain. In this paper, to address simultaneous inter-domain shift and intra-domain shift for multiple target domains, we propose a novel unsupervised, multistage, multisource and multitarget domain adaptation network (MultiDAN), which involves multisource and multitarget domain adaptation (MSMTDA), entropy-based clustering (EC) and multistage domain adaptation (MDA). Specifically, MSMTDA learns feature-level multiple adversarial strategies to alleviate complex domain shift between multiple target and source domains. Then, EC clusters the various target domains into multiple subdomains based on entropy of target predictions of MSMTDA. Besides, we propose a new pseudo label update strategy (PLUS) to dynamically produce more accurate pseudo labels for MDA. Finally, MDA aligns the clean subdomains, including pseudo labels generated by PLUS, with other noisy subdomains in the output space via the proposed multistage adaptation algorithm (MAA). The extensive experiments on the benchmark remote sensing datasets highlight the superiority of our MultiDAN against recent state-of-the-art UDA methods.

Recently, automatic multi-domain fake news detection has attracted widespread attention. Many methods achieve domain adaptation by modeling domain category gate networks and domain-invariant features. However, existing multi-domain fake news detection faces three main challenges: (1) Inter-domain modal semantic deviation, where similar texts and images carry different meanings across various domains. (2) Inter-domain modal dependency deviation, where the dependence on different modalities varies across domains. (3) Inter-domain knowledge dependency deviation, where the reliance on cross-domain knowledge and domain-specific knowledge differs across domains. To address these issues, we propose a Multi-modal Multi-Domain Fake News Detection Model (MMDFND). MMDFND incorporates domain embeddings and attention mechanisms into a progressive hierarchical extraction network to achieve domain-adaptive domain-related knowledge extraction. Furthermore, MMDFND utilizes Stepwise Pivot Transformer networks and adaptive instance normalization to effectively utilize information from different modalities and domains. We validate the effectiveness of MMDFND through comprehensive comparative experiments on two real-world datasets and conduct ablation experiments to verify the effectiveness of each module, achieving state-of-the-art results on both datasets. The source code is available at https://github.com/yutchina/MMDFND.

Visual grounding aims to localize the object referred to in an image based on a natural language query. Although progress has been made recently, accurately localizing target objects within multiple-instance distractions (multiple objects of the same category as the target) remains a significant challenge. Existing methods demonstrate a significant performance drop when there are multiple distractions in an image, indicating an insufficient understanding of the fine-grained semantics and spatial relationships between objects. In this paper, we propose a novel approach, the Relation and Semantic-sensitive Visual Grounding (ResVG) model, to address this issue. Firstly, we enhance the model's understanding of fine-grained semantics by injecting semantic prior information derived from text queries into the model. This is achieved by leveraging text-to-image generation models to produce images representing the semantic attributes of target objects described in queries. Secondly, we tackle the lack of training samples with multiple distractions by introducing a relation-sensitive data augmentation method. This method generates additional training data by synthesizing images containing multiple objects of the same category and pseudo queries based on their spatial relationships. The proposed ReSVG model significantly improves the model's ability to comprehend both object semantics and spatial relations, leading to enhanced performance in visual grounding tasks, particularly in scenarios with multiple-instance distractions. We conduct extensive experiments to validate the effectiveness of our methods on five datasets. Code is available at https://github.com/minghangz/ResVG.

The key challenge of cross-modal domain-incremental learning (DIL) is to enable the learning model to continuously learn from novel data with different feature distributions under the same task without forgetting old ones. However, existing top-performing methods still cause high forgetting rates, by lacking intra-domain knowledge extraction and inter-domain common prompting strategy. In this paper, we propose a simple yet effective framework, CP-Prompt, by training limited parameters to instruct a pre-trained model to learn new domains and avoid forgetting existing feature distributions. CP-Prompt captures intra-domain knowledge by compositionally inserting personalized prompts on multi-head self-attention layers and then learns the inter-domain knowledge with a common prompting strategy. CP-Prompt shows superiority compared with state-of-the-art baselines among three widely evaluated DIL tasks. The source code is available at https://github.com/dannis97500/CP_Prompt.

Efficient visual perception using mobile systems is crucial, particularly in unknown environments such as search and rescue operations, where swift and comprehensive perception of objects of interest is essential. In such real-world applications, objects of interest are often situated in complex settings, making the selection of the 'Next Best' view based solely on maximizing visibility gain suboptimal. We argue that incorporating semantics-providing a higher-level interpretation of perception-can significantly contribute to the selection of viewpoints for various perception tasks. In this study, we formulate a novel information gain that integrates both visibility and semantic gain in a unified form to select the semantic-aware Next-Best-View. We also design an adaptive strategy with termination criterion to facilitate the two-stage search-and-acquisition manoeuvre on multiple objects of interest aided by a multi-degree-of-freedoms (Multi-DoFs) mobile system. To evaluate our approach, we introduce several semantically relevant reconstruction metrics, including perspective directivity and the region of interest (ROI)-to-full reconstruction volume ratio. Simulation experiments demonstrate that our approach outperforms the existing methods by up to 27.46% in the ROI-to-full reconstruction volume ratio and 0.88234 in average perspective directivity. Furthermore, the planned motion trajectory exhibits better perceiving coverage toward the target.

Multi-modality physiological signal-based emotion recognition has attracted increasing attention as its capacity to capture human affective states comprehensively. Due to multi-modality heterogeneity and cross-subject divergence, practical applications struggle with generalizing models across individuals. Effectively addressing both issues requires mitigating the gap between multimodal signals while acquiring generalizable representations across subjects. However, existing approaches often handle these dual challenges separately, resulting in suboptimal generalization. This study introduces a novel framework, termed Correlation-Driven Multi-Modality Graph Decomposition (CMMGD). The proposed CMMGD initially captures adaptive cross-modal correlations. It connects each unimodal graph to a multimodal mixed graph. To simultaneously address the dual challenges, it incorporates a correlation-driven graph decomposition module that decomposes the mixed graph into concordant and discrepant subgraphs based on the correlations. The decomposed concordant subgraph encompasses consistently activated features across modalities and subjects during emotion elicitation, unveiling a generalizable subspace. Additionally, we design a Multi-Modality Graph Regularized Transformer (MGRT) backbone specifically tailored for multimodal physiological signals. The MGRT can alleviate the over-smoothing issue and mitigate over-reliance on any single modality. Extensive experiments demonstrate that CMMGD outperforms the state-of-the-art methods by 1.79% and 2.65% on DEAP and MAHNOB-HCI datasets, respectively, under the leave-one-subject-out cross-validation strategy.

Adhesive adversarial patches have been common used in attacks against the computer vision task of monocular depth estimation (MDE). Compared to physical patches permanently attached to target objects, optical projection patches show great flexibility and have gained wide research attention. However, applying digital patches for direct projection may lead to partial blurring or omission of details in the captured patches, attributed to high information density, surface depth discrepancies, and non-uniform pixel distribution. To address these challenges, in this work we introduce DepthCloak, an adversarial optical patch designed to interfere with the MDE of vehicles. To this end, we first simplify the patch to a gray pattern because the projected ''black-and-white light'' has strong robustness to ambient light. We propose a generative adversarial network (GAN) based approach to simulate projections and deduce a projectable list. Then, we employ neighborhood averaging to fill sparse depth values, compress all depth values into a reduced dynamic range via nonlinear mapping, and use these values to adjust the Gaussian blur radius as weight parameters, thereby simulating depth variation effects. Finally, by integrating Moiré pattern and applying style transfer techniques, we customize adversarial patches featuring regularly arranged characteristics. We deploy DepthCloak in real driving scenarios, and extensive experiments demonstrate that DepthCloak can achieve an attack success rate of over 80% in the physical world.

Incremental Object Detection (IOD) simulates the dynamic data flow in real-world applications, which require detectors to learn new classes or adapt to new domains while retaining knowledge from previous tasks. Most existing IOD methods focus only on class incremental learning, assuming all data comes from the same domain. However, this is hardly achievable in practical applications, as images collected under different conditions often exhibit completely different characteristics, such as lighting, weather, style, etc. Class IOD methods suffer from performance degradation in these scenarios with domain shifts. To bridge domain shifts and category gaps in IOD, we propose Purified Distillation (PD), where we use a set of trainable queries to transfer the teacher's attention on old tasks to the student and adopt the gradient reversal layer to guide the student to learn the teacher's feature space structure from a micro perspective, which has not been extensively studied in previous works. Meanwhile, PD combines classification confidence with localization confidence to purify the most meaningful output nodes, so that the student model inherits a more comprehensive teacher knowledge. Extensive experiments across various IOD settings on six widely used datasets show that PD significantly outperforms state-of-the-art methods. Even after five steps of incremental learning, our method can preserve 60.6% mAP on the first task, while compared methods can only maintain up to 55.9%.

Sentiment analysis is rapidly advancing by utilizing various data modalities (e.g., text, image). However, most previous works relied on superficial information, neglecting the incorporation of contextual world knowledge (e.g., background information derived from but beyond the given image and text pairs) and thereby restricting their ability to achieve better multimodal sentiment analysis (MSA). In this paper, we proposed a plug-in framework named WisdoM, to leverage the contextual world knowledge induced from the large vision-language models (LVLMs) for enhanced MSA. WisdoM utilizes LVLMs to comprehensively analyze both images and corresponding texts, simultaneously generating pertinent context. To reduce the noise in the context, we also introduce a training-free contextual fusion mechanism. Experiments across diverse granularities of MSA tasks consistently demonstrate that our approach has substantial improvements (brings an average +1.96% F1 score among five advanced methods) over several state-of-the-art methods.

Recently, significant advancements have been made in supporting text-video retrieval by transferring large-scale image-text pre-training models through model adaptation, i.e., full fine-tuning, or prompt tuning, a parameter-efficient fine-tuning strategy. While full fine-tuning involves high computational costs, particularly with increasing model size, prompt tuning offers greater flexibility and efficiency by adjusting only a few learnable parameters. However, current prompt tuning methods rely on coarse visual and textual cues for text-video retrieval task, neglecting the domain-specific features when performing the adaptation. This approach may lead to sub-optimal performance due to the incorporation of irrelevant and indiscriminate knowledge. To address such an issue, we present a Multi-grained Prompt Tuning (MPT) for text-video retrieval, that designs a variety of specific prompts to effectively explore semantic interaction across different modalities with diverse granularity. Specifically, we devise a multi-grained video encoder that employs spatial, temporal, and global prompts to transfer the base-generic knowledge from the image-text pre-trained model while comprehensively excavating determinative video-specific characteristics. Meanwhile, we introduce a novel multi-grained text encoder aimed at capturing various levels of textual clues through the utilization of word and phrase prompts. Extensive experiments on four benchmark datasets, i.e., MSR-VTT, ActivityNet, DiDeMo, and LSMDC, demonstrate that MPT achieves outstanding performance, surpassing state-of-the-art methods with negligible computational cost. The codebase is publicly available at: https://github.com/zchoi/MPT.

Generic event boundary detection (GEBD), inspired by human visual cognitive behaviors of consistently segmenting videos into meaningful temporal chunks, finds utility in various applications such as video editing and. In this paper, we demonstrate that SOTA GEBD models often prioritize final performance over model complexity, resulting in low inference speed and hindering efficient deployment in real-world scenarios. We contribute to addressing this challenge by experimentally reexamining the architecture of GEBD models and uncovering several surprising findings. Firstly, we reveal that a concise GEBD baseline model already achieves promising performance without any sophisticated design. Secondly, we find that the widely applied image-domain backbones in GEBD models can contain plenty of architecture redundancy, motivating us to gradually ``modernize'' each component to enhance efficiency. Thirdly, we show that the GEBD models using image-domain backbones conducting the spatiotemporal learning in a spatial-then-temporal greedy manner can suffer from a distraction issue, which might be the inefficient villain for GEBD. Using a video-domain backbone to jointly conduct spatiotemporal modeling is an effective solution for this issue. The outcome of our exploration is a family of GEBD models, named EfficientGEBD, significantly outperforms the previous SOTA methods by up to 1.7\% performance gain and 280\% speedup under the same backbone. Our research prompts the community to design modern GEBD methods with the consideration of model complexity, particularly in resource-aware applications. The code is available at \url{https://github.com/Ziwei-Zheng/EfficientGEBD}.

Multimodal fusion, leveraging data like vision and language, is rapidly gaining traction. This enriched data representation improves performance across various tasks. Existing methods for out-of-distribution (OOD) detection, a critical area where AI models encounter unseen data in real-world scenarios, rely heavily on whole-image features. These image-level features can include irrelevant information that hinders the detection of OOD samples, ultimately limiting overall performance. In this paper, we propose \textbf{TagOOD}, a novel approach for OOD detection that leverages vision-language representations to achieve label-free object feature decoupling from whole images. This decomposition enables a more focused analysis of object semantics, enhancing OOD detection performance. Subsequently, TagOOD trains a lightweight network on the extracted object features to learn representative class centers. These centers capture the central tendencies of IND object classes, minimizing the influence of irrelevant image features during OOD detection. Finally, our approach efficiently detects OOD samples by calculating distance-based metrics as OOD scores between learned centers and test samples. We conduct extensive experiments to evaluate TagOOD on several benchmark datasets and demonstrate its superior performance compared to existing OOD detection methods. This work presents a novel perspective for further exploration of multimodal information utilization in OOD detection, with potential applications across various tasks.

In image fusion tasks, images from different sources possess distinct characteristics.This has driven the development of numerous methods to explore better ways of fusing them while preserving their respective characteristics.Mamba, as a state space model, has emerged in the field of natural language processing.Recently, many studies have attempted to extend Mamba to vision tasks.However, due to the nature of images different from causal language sequences, the limited state capacity of Mamba weakens its ability to model image information.Additionally, the sequence modeling ability of Mamba is only capable of spatial information and cannot effectively capture the rich spectral information in images.Motivated by these challenges, we customize and improve the vision Mamba network designed for the image fusion task.Specifically, we propose the local-enhanced vision Mamba block, dubbed as LEVM.The LEVM block can improve local information perception of the network and simultaneously learn local and global spatial information.Furthermore, we propose the state sharing technique to enhance spatial details and integrate spatial and spectral information.Finally, the overall network is a multi-scale structure based on vision Mamba, called LE-Mamba.Extensive experiments show the proposed methods achieve state-of-the-art results on multispectral pansharpening and multispectral and hyperspectral image fusion datasets, and demonstrate the effectiveness of the proposed approach.Code can be accessed at https://github.com/294coder/Efficient-MIF.

Recent advancements in text-to-image generative models have showcased remarkable capabilities across various tasks. However, these powerful models have revealed the inherent risks of social biases. Such biases can propagate distorted real-world perspectives and spread unforeseen prejudice and discrimination. Current debiasing methods are primarily designed for scenarios with a single individual in the image and exhibit homogenous race or gender when multiple individuals are involved, harming the diversity of social groups within the image. To address this problem, we consider the semantic consistency between text prompts and generated images in text-to-image diffusion models to identify how biases are generated. We propose a novel method to locate where the biases are based on different tokens and then mitigate them for each individual. Specifically, we introduce a Linguistic-aligned Attention Guidance module consisting of Block Voting and Linguistic Alignment, to effectively locate the semantic regions related to biases. Additionally, we employ Fair Inference in these regions to generate fair attributes across arbitrary distributions while preserving the original structural and semantic information. Extensive experiments and analyses demonstrate our method outperforms existing methods for debiasing with multiple individuals across various scenarios.

With the rise of new 3D representations like NeRF and 3D Gaussian splatting, creating realistic 3D scenes is easier than ever before. However, the incompatibility of these 3D representations with existing editing software has also introduced unprecedented challenges to 3D editing tasks. Although recent advances in text-to-image generative models have made some progress in 3D editing, these methods either lack precision or require users to manually specify the editing areas in 3D space, complicating the editing process. To overcome these issues, we propose Edit3D, an innovative 3D editing method designed to enhance editing quality. Specifically, we propose a multi-turn editing framework and introduce an attention-driven open-set segmentation (ADSS) technique within this framework. ADSS allows for more precise segmentation of parts, which enhances the editing precision and minimizes interference with pixels in areas that are not being edited. Additionally, we propose a fine-tuning phase, intended to further improve the overall editing quality without compromising the training efficiency. Experiments demonstrate that Edit3D effectively adjusts 3D scenes based on textual instructions. Through continuous and multiple turns of editing, it achieves more intricate combinations, enhancing the diversity of 3D editing effects. Code is available at https://github.com/PeterouZh/Edit3D.

Speech-language multi-modal learning presents a significant challenge due to the fine nuanced information inherent in speech styles. Therefore, a large-scale dataset providing elaborate comprehension of speech style is urgently needed to facilitate insightful interplay between speech audio and natural language. However, constructing such datasets presents a major trade-off between large-scale data collection and high-quality annotation. To tackle this challenge, we propose an automatic speech annotation system for expressiveness interpretation that annotates in-the-wild speech clips with expressive and vivid human language descriptions. Initially, speech audios are processed by a series of expert classifiers and captioning models to capture diverse speech characteristics, followed by a fine-tuned LLaMA for customized annotation generation. Unlike previous tag/templet-based annotation frameworks with limited information and diversity, our system provides in-depth understandings of speech style through tailored natural language descriptions, thereby enabling accurate and voluminous data generation for large model training. With this system, we create SpeechCraft, a fine-grained bilingual expressive speech dataset. It is distinguished by highly descriptive natural language style prompts, containing approximately 2,000 hours of audio data and encompassing over two million speech clips. Extensive experiments demonstrate that the proposed dataset significantly boosts speech-language task performance in stylist speech synthesis and speech style understanding.

Talking head generation is a significant research topic that still faces numerous challenges. Previous works often adopt generative adversarial networks or regression models, which are plagued by generation quality and average facial shape problem. Although diffusion models show impressive generative ability, their exploration in talking head generation remains unsatisfactory. This is because they either solely use the diffusion model to obtain an intermediate representation and then employ another pre-trained renderer, or they overlook the feature decoupling of complex facial details, such as expressions, head poses and appearance textures. Therefore, we propose a Facial Decoupled Diffusion model for Talking head generation called FD2Talk, which fully leverages the advantages of diffusion models and decouples the complex facial details through multi-stages. Specifically, we separate facial details into motion and appearance. In the initial phase, we design the Diffusion Transformer to accurately predict motion coefficients from raw audio. These motions are highly decoupled from appearance, making them easier for the network to learn compared to high-dimensional RGB images. Subsequently, in the second phase, we encode the reference image to capture appearance textures. The predicted facial and head motions and encoded appearance then serve as the conditions for the Diffusion UNet, guiding the frame generation. Benefiting from decoupling facial details and fully leveraging diffusion models, extensive experiments substantiate that our approach excels in enhancing image quality and generating more accurate and diverse results compared to previous state-of-the-art methods.