ACM MM 2024 论文列表

Multimodal knowledge graph (MKG) reasoning has attracted significant attention since impressive performance has been achieved by adding multimodal auxiliary information (i.e., texts and images) to the entities of traditional KGs. However, existing studies heavily rely on path-based methods for learning structural modality, failing to capture the complex structural interactions among multimodal entities beyond the reasoning path. In addition, existing studies have largely ignored the dynamic impact of different multimodal features on different decision facts for reasoning, which utilize asymmetric coattention to independently learn the static interplay between different modalities without dynamically joining the reasoning process. We propose a novel Dynamic Structure-aware representation learning method, namely DySarl, to overcome this problem and significantly improve the MKG reasoning performance. Specifically, we devise a dual-space multihop structural learning module in DySarl, aggregating the multihop structural features of multimodal entities via a novel message-passing mechanism. It integrates the message paradigms in Euclidean and hyperbolic spaces, effectively preserving the neighborhood information beyond the limited multimodal query paths. Furthermore, DySarl has an interactive symmetric attention module to explicitly learn the dynamic impacts of unimodal attention senders and multimodal attention targets on decision facts through a newly designed symmetric attention component and fact-specific gated attention unit, equipping DySarl with the dynamic associations between the multimodal feature learning and later reasoning. Extensive experiments show that DySarl achieves significantly improved reasoning performance on two public MKG datasets compared with that of the state-of-the-art baselines. Source codes are available at https://github.com/HUSTNLP-codes/DySarl.

Unsupervised visible-infrared person re-identification (USL-VI-ReID) is of great research and practical significance yet remains challenging due to significant modality discrepancy and lack of annotations. Many existing approaches utilize variants of bipartite graph global matching algorithms to address this issue, aiming to establish cross-modality correspondences. However, these methods may encounter mismatches due to significant modality gaps and limited model representation. To mitigate this, we propose a simple yet effective framework for USL-VI-ReID, which gradually establishes associations between different modalities. To measure the confidence whether samples from different modalities belong to the same identity, we introduce a bidirectional-consistency criterion, which not only considers direct relationships between samples from different modalities but also incorporates potential hard negative samples from the same modality. Additionally, we propose a cross-modality correlation preserving module to further enhance the semantic representation of the model by maintaining consistency in correlations across modalities. Extensive experiments conducted on the public SYSU-MM01 and RegDB datasets demonstrate the superiority of our method over existing USL-VI-ReID approaches across various settings, despite the simplicity of our method.

With the continuous development of imaging technology and the gradual expansion of the amount of image data, how to achieve high compression efficiency of high-resolution images is a challenge problem for storage and transmission. Image rescaling aims to reduce the original data amount through downscaling to facilitate data transmission and storage before encoding, and reconstruct the quality through upscaling after decoding, which is a key technology to assist in high-ratio image compression. However, existing rescaling approaches are more focused on reconstruction quality rather than image compressibility. In repetitive observation scenarios, multi-temporal images brought by periodic observations provide an opportunity to alleviate the conflict between reconstruction quality and compressibility, that is, the historical images as reference indicates what information can be dropped at downscaling to reduce the information content in downscaled image and provides the dropped information to improve the image restoration quality at upscaling. Based on this consideration, we propose a novel multi-temporal assisted reference-based image rescaling framework (RefScale). Specifically, a referencing network is proposed to calculate the similarity map to provide the referencing condition, which is then injected into the conditional invertible neural network to guide the information drop at the downscaling stage and information fusion at the upscaling stage. Additionally, a low-resolution guidance loss is proposed to further constrain the data amount of the downscaled image. Experiments conducted on both satellite imaging and autonomous driving show the superior performance of our approach over the state-of-the-art methods.

Diffusion-based text-to-image personalization have achieved great success in generating subjects specified by users among various contexts. Even though, existing finetuning-based methods still suffer from model overfitting, which greatly harms the generative diversity, especially when given subject images are few. To this end, we propose Pick-and-Draw, a training-free semantic guidance approach to boost identity consistency and generative diversity for personalization methods. Our approach consists of two components: appearance picking guidance and layout drawing guidance. As for the former, we construct an appearance palette with visual features from the reference image, where we pick local patterns for generating the specified subject with consistent identity. As for layout drawing, we outline the subject's contour by referring to a generative template from the vanilla diffusion model, and inherit the strong image prior to synthesize diverse contexts according to different text conditions. The proposed approach can be applied to any personalized diffusion models and requires as few as a single reference image. Qualitative and quantitative experiments show that Pick-and-Draw consistently improves identity consistency and generative diversity, pushing the trade-off between subject fidelity and image-text fidelity to a new Pareto frontier.

In challenging low-light and adverse weather conditions, thermal vision algorithms, especially object detection, have exhibited remarkable potential, contrasting with the frequent struggles encountered by visible vision algorithms. Nevertheless, the efficacy of thermal vision algorithms driven by deep learning models remains constrained by the paucity of available training data samples. To this end, this paper introduces a novel approach termed the edge-guided conditional diffusion model (ECDM). This framework aims to produce meticulously aligned pseudo thermal images at the pixel level, leveraging edge information extracted from visible images. By utilizing edges as contextual cues from the visible domain, the diffusion model achieves meticulous control over the delineation of objects within the generated images. To alleviate the impacts of those visible-specific edge information that should not appear in the thermal domain, a two-stage modality adversarial training (TMAT) strategy is proposed to filter them out from the generated images by differentiating the visible and thermal modality. Extensive experiments on LLVIP demonstrate ECDM's superiority over existing state-of-the-art approaches in terms of image generation quality. The pseudo thermal images generated by ECDM also help to boost the performance of various thermal object detectors by up to 7.1 mAP. Code is available at https://github.com/lengmo1996/ECDM.

With the rapid advancements of large-scale text-to-image diffusion models, various practical applications have emerged, bringing significant convenience to society. However, model developers may misuse the unauthorized data to train diffusion models. These data are at risk of being memorized by the models, thus potentially violating citizens' privacy rights. Therefore, in order to judge whether a specific image is utilized as a member of a model's training set, Membership Inference Attack (MIA) is proposed to serve as a tool for privacy protection. Current MIA methods predominantly utilize pixel-wise comparisons as distinguishing clues, considering the pixel-level memorization characteristic of diffusion models. However, it is practically impossible for text-to-image models to memorize all the pixel-level information in massive training sets. Therefore, we move to the more advanced structure-level memorization. Observations on the diffusion process show that the structures of members are better preserved compared to those of nonmembers, indicating that diffusion models possess the capability to remember the structures of member images from training sets. Drawing on these insights, we propose a simple yet effective MIA method tailored for text-to-image diffusion models. Extensive experimental results validate the efficacy of our approach. Compared to current pixel-level baselines, our approach not only achieves state-of-the-art performance but also demonstrates remarkable robustness against various distortions.

Text-driven 3D indoor scene generation aims to automatically generate and arrange the objects, which form a 3D scene that accurately captures the semantics detailed in the given text description. Recent works have shown the potential to generate 3D scenes guided by specific object categories and room layouts but lack a robust mechanism to maintain consistent spatial relationships in alignment with the provided text description during the 3D scene generation. Besides, the annotations of the object and relationships of the 3D scenes are usually time- and cost-consuming, which are not easily obtained for the model training. Thus, in this paper, we conduct a dataset and benchmark for assessing spatial relations in text-driven 3D scene generation, which contains a comprehensive collection of 3D scenes, including textual descriptions, annotating object spatial relations, and providing both template and free-form natural language descriptions. We also provide a pseudo description feature generation method to address the 3D scenes without language annotations. We design an aligned latent space for spatial relation in 3D scenes and text description, in which we can sample the features according to the spatial relation for the few-shot learning. We also propose new metrics to investigate the ability of the approach to generate correct spatial relationships among objects.

Cloud-based machine learning services offer significant advantages but also introduce the risk of tampering with cloud-deployed deep neural network (DNN) models. Black-box integrity verification (BIV) allows model owners and end-users to determine if a cloud-deployed DNN model has been tampered with by examining only the top-1 label responses. Fingerprinting generates fingerprint samples to query the model, achieving BIV with no impact on the model's accuracy. In this paper, we present BIVBench, the first comprehensive benchmark for BIV of DNN models. BIVBench covers 16 types of model modifications, providing extensive coverage of practical modification scenarios. Our analysis reveals that existing fingerprinting methods, which are typically focused on significant tampering, lack the sensitivity needed to effectively detect subtle yet common and potentially severe modifications. To address this limitation, we propose MiSentry (Model Integrity Sentry), a novel fingerprinting method that leverages meta-learning. MiSentry strategically incorporates a few subtly modified models into the meta-learning model zoo and maximizes the divergence of output predictions between the target model and the modified models in the model zoo to generate highly sensitive, generalizable, and effective fingerprint samples. Extensive evaluations using BIVBench demonstrate that MiSentry outperforms existing state-of-the-art methods overall and significantly surpasses them in detecting subtle modifications. The BIVBench and supplementary materials are available at: https://github.com/CGCL-codes/BIVBench.

Research on continual learning in multi-modal tasks has been receiving increasing attention. However, most existing work overlooks the explicit cross-modal and cross-task interactions. In this paper, we innovatively propose the Low-rank Prompt Interaction (LPI) to address this general problem of multi-modal understanding, which considers both cross-modal and cross-task interactions. Specifically, as for the former, we employ multi-modal correlation modules for corresponding Transformer layers. Considering that the training parameters scale to the number of layers and tasks, we propose low-rank interaction-augmented decomposition to avoid memory explosion while enhancing the cross-modal association through sharing and separating common-specific low-rank factors. In addition, due to the multi-modal semantic differences carried by the low-rank initialization, we adopt hierarchical low-rank contrastive learning to ensure training robustness. As for the latter, we initially employ a visual analysis and identify that different tasks have clear distinctions in proximity. Therefore, we introduce explicit task contrastive constraints in the prompt learning process based on task semantic distances. Experiments on two retrieval tasks show performance improvements with the introduction of a minimal number of parameters, demonstrating the effectiveness of our method. Code is available at https://github.com/Kelvin-ywc/LPI.

Polygonal meshes are widely used to represent complex geometries. However, the increasing complexity of models often leads to large meshes with millions of triangles, raising significant challenges for storage, transmission, and computation. Mesh simplification, a process of reducing the number of triangles in a mesh while preserving its overall shape and important features, has emerged as an indispensable technique to address these challenges. In this work, we focus on the problem of obtaining a visually consistent ultra-low-polygon mesh for complex meshes. Unlike previous methods, we design a robust simplification framework, SimpliGuard, to handle any meshes in the wild. Firstly, a reconstruction module is used to construct a low-polygon mesh with a similar shape but a manifold topology. Then, a texture initialization module is employed to quickly initialize the entire texture map. After that, a differentiable rendering module is utilized to optimize the overall structure and texture details, ensuring high-quality results. For meshes with skeletons, the correctness of motion can be preserved with our designed motion post-processing module. Experimental results demonstrate that SimpliGuard significantly outperforms previous methods and various featured software, including Blender and Simplygon.

Salient Object Detection (SOD) aims to identify and segment the most prominent objects in images. Advanced SOD methods often utilize various Convolutional Neural Networks (CNN) or Transformers for deep feature extraction. However, these methods still deliver low performance and poor generalization in complex cases. Recently, Segment Anything Model (SAM) has been proposed as a visual fundamental model, which gives strong segmentation and generalization capabilities. Nonetheless, SAM requires accurate prompts of target objects, which are unavailable in SOD. Additionally, SAM lacks the utilization of multi-scale and multi-level information, as well as the incorporation of fine-grained details. To address these shortcomings, we propose a Multi-scale and Detail-enhanced SAM (MDSAM) for SOD. Specifically, we first introduce a Lightweight Multi-Scale Adapter (LMSA), which allows SAM to learn multi-scale information with very few trainable parameters. Then, we propose a Multi-Level Fusion Module (MLFM) to comprehensively utilize the multi-level information from the SAM's encoder. Finally, we propose a Detail Enhancement Module (DEM) to incorporate SAM with fine-grained details. Experimental results demonstrate the superior performance of our model on multiple SOD datasets and its strong generalization on other segmentation tasks. The source code is released at https://github.com/BellyBeauty/MDSAM

Recently, video diffusion models (VDMs) have garnered significant attention due to their notable advancements in generating coherent and realistic video content. However, processing multiple frame features concurrently, coupled with the considerable model size, results in high latency and extensive memory consumption, hindering their broader application. Post-training quantization (PTQ) is an effective technique to reduce memory footprint and improve computational efficiency. Unlike image diffusion, we observe that the temporal features, which are integrated into all frame features, exhibit pronounced skewness. Furthermore, we investigate significant inter-channel disparities and asymmetries in the activation of video diffusion models, resulting in low coverage of quantization levels by individual channels and increasing the challenge of quantization. To address these issues, we introduce the first PTQ strategy tailored for video diffusion models, dubbed QVD. Specifically, we propose the High Temporal Discriminability Quantization (HTDQ) method, designed for temporal features, which retains the high discriminability of quantized features, providing precise temporal guidance for all video frames. In addition, we present the Scattered Channel Range Integration (SCRI) method which aims to improve the coverage of quantization levels across individual channels. Experimental validations across various models, datasets, and bit-width settings demonstrate the effectiveness of our QVD in terms of diverse metrics. In particular, we achieve near-lossless performance degradation on W8A8, outperforming the current methods by 205.12 in FVD.

In recent years, the Few-Shot Fine-Grained Image Classification (FS-FGIC) problem has gained widespread attention. A number of effective methods have been proposed that focus on extracting discriminative information within high-level features in a single episode/task. However, this is insufficient for addressing the cross-task challenges of FS-FGIC, which is represented in two aspects. On the one hand, from the perspective of the Fine-Grained Image Classification (FGIC) task, there is a need to supplement the model with mid-level features containing rich fine-grained information. On the other hand, from the perspective of the Few-Shot Learning (FSL) task, explicit modeling of cross-task general knowledge is required. In this paper, we propose a novel Bi-directional Task-Guided Network (BTG-Net) to tackle these issues. Specifically, from the FGIC task perspective, we design the Semantic-Guided Noise Filtering (SGNF) module to filter noise on mid-level features rich in detailed information. Further, from the FSL task perspective, the General Knowledge Prompt Modeling (GKPM) module is proposed to retain the cross-task general knowledge by utilizing the prompting mechanism, thereby enhancing the model's generalization performance on novel classes. We have conducted extensive experiments on five fine-grained benchmark datasets, and the results demonstrate that BTG-Net outperforms state-of-the-art methods comprehensively.

With the rapid development of high-bit-depth display devices, bit-depth expansion (BDE) algorithms that extend low-bit-depth images to high-bit-depth images have received increasing attention. Due to the sensitivity of bit-depth distortions to tiny numerical changes in the least significant bits, the nuanced degradation differences in the training process may lead to varying degradation data distributions, causing the trained models to overfit specific types of degradations. This paper focuses on the problem of blind video BDE, proposing a degradation prediction and embedding framework, and designing a video BDE network based on a recurrent structure and dual-frame alignment fusion. Experimental results demonstrate that the proposed model can outperform some state-of-the-art (SOTA) models in terms of banding artifact removal and color correction, avoiding overfitting to specific degradations and obtaining better generalization ability across multiple datasets. https://github.com/duanpanjun/BVBDE

Deep Video Quality Assessment (VQA) methods have shown impressive high-performance capabilities. Notably, no-reference (NR) VQA methods play a vital role in situations where obtaining reference videos is restricted or not feasible. Nevertheless, as more streaming videos are being created in ultra-high definition (e.g., 4K) to enrich viewers' experiences, the current deep VQA methods face unacceptable computational costs. Furthermore, the resizing, cropping, and local sampling techniques employed in these methods can compromise the details and content of original 4K videos, thereby negatively impacting quality assessment. In this paper, we propose a highly efficient and novel NR 4K VQA technology. Specifically, first, a novel data sampling and training strategy is proposed to tackle the problem of excessive resolution. This strategy allows the VQA Swin Transformer-based model to effectively train and make inferences using the full data of 4K videos on standard consumer-grade GPUs without compromising content or details. Second, a weighting and scoring scheme is developed to mimic the human subjective perception mode, which is achieved by considering the distinct impact of each sub-region within a 4K frame on the overall perception. Third, we incorporate the frequency domain information of video frames to better capture the details that affect video quality, consequently further improving the model's generalizability. To our knowledge, this is the first technology for the NR 4K VQA task. Thorough empirical studies demonstrate it not only significantly outperforms existing methods on a specialized 4K VQA dataset but also achieves state-of-the-art performance across multiple open-source NR video quality datasets.

Spatial transcriptomics provides revolutionary insights into cellular interactions and disease development mechanisms by combining high-throughput gene sequencing and spatially resolved imaging technologies to analyze genes naturally associated with spatially variable tissue genes. However, existing methods typically map aggregated multi-view features into a unified representation, ignoring the heterogeneity and view independence of genes and spatial information. To this end, we construct a heterogeneous Graph guided Contrastive Learning (stGCL) for aggregating spatial transcriptomics data. The method is guided by the inherent heterogeneity of cellular molecules by dynamically coordinating triple-level node attributes through comparative learning loss distributed across view domains, thus maintaining view independence during the aggregation process. In addition, we introduce a cross-view hierarchical feature alignment module employing a parallel approach to decouple spatial and genetic views on molecular structures while aggregating multi-view features according to information theory, thereby enhancing the integrity of inter- and intra-views. Rigorous experiments demonstrate that stGCL outperforms existing methods in various tasks and related downstream applications.

Cross-lingual cross-modal retrieval (CCR) aims to retrieve visually relevant content based on non-English queries, without relying on human-labeled cross-modal data pairs during training. One popular approach involves utilizing machine translation (MT) to create pseudo-parallel data pairs, establishing correspondence between visual and non-English textual data. However, aligning their representations poses challenges due to the significant semantic gap between vision and text, as well as the lower quality of non-English representations caused by pre-trained encoders and data noise. To overcome these challenges, we propose LECCR, a novel solution that incorporates the multi-modal large language model (MLLM) to improve the alignment between visual and non-English representations. Specifically, we first employ MLLM to generate detailed visual content descriptions and aggregate them into multi-view semantic slots that encapsulate different semantics. Then, we take these semantic slots as internal features and leverage them to interact with the visual features. By doing so, we enhance the semantic information within the visual features, narrowing the semantic gap between modalities and generating local visual semantics for subsequent multi-level matching. Additionally, to further enhance the alignment between visual and non-English features, we introduce softened matching under English guidance. This approach provides more comprehensive and reliable inter-modal correspondences between visual and non-English features. Extensive experiments on four CCR benchmarks, i.e., Multi30K, MSCOCO, VATEX, and MSR-VTT-CN, demonstrate the effectiveness of our proposed method. Code: https://github.com/LiJiaBei-7/leccr.

This paper presents the first study to explore the potential of parameter quantization for multimodal large language models to alleviate the significant resource constraint encountered during vision-language instruction tuning. We introduce a Quantization-aware Scale LeArning method based on multimodal Warmup, termed QSLAW. This method is grounded in two key innovations: (1) The learning of group-wise scale factors for quantized LLM weights to mitigate the quantization error arising from activation outliers and achieve more effective vision-language instruction tuning; (2) The implementation of a multimodal warmup that progressively integrates linguistic and multimodal training samples, thereby preventing overfitting of the quantized model to multimodal data while ensuring stable adaptation of multimodal large language models to downstream vision-language tasks. Extensive experiments demonstrate that models quantized by QSLAW perform on par with, or even surpass, their full-precision counterparts, while facilitating up to 1.4 times reduction in VL tuning time and GPU consumption.