ACM MM 2024 论文列表

Due to the limitation of collection device and unstable scanning process, point cloud data is usually noisy. This noise deforms the underlying structures of point clouds and inevitably affects downstream tasks such as rendering, reconstruction and classification. In this paper, we propose a Cross-stage Cross-coder Adaptive Edge Graph Convolution Network (C2AENet) to denoise point clouds. Our network uses multiple stages to progressively and iteratively denoise points. To improve the effectiveness, we add connections between two stages and between the encoder and decoder, leading to the cross-stage cross-coder architecture. Additionally, existing graph-based point cloud learning methods tend to capture the local structure. They typically construct a semantic graph based on semantic distance, which may ignore Euclidean neighbors and lead to insufficient geometry perception. Therefore, we introduce a geometric graph and adaptively calculate edge attention based on the local and global structural information of the points. This results in a novel graph convolution module that allows the network to capture richer contextual information and focus on more important parts. Extensive experiments demonstrate that the proposed method is competitive compared with other state-of-the-art methods. The code is available at: https://github.com/chenwuwq/C2AENet.

Foundational segmentation models, predominantly trained on scenes typical of natural environments, struggle to generalize across varied image domains. Traditional "training-to-adapt'' methods rely heavily on extensive data retraining and model architectures modifications. This significantly limits the models' generalization capabilities and efficiency in deployment. In this study, we propose a novel adaptation paradigm, termed "prompting-to-adapt'', to tackle the above issue by introducing an innovative image prompter. This prompter generates domain-specific prompts through few-shot image-mask pairs, incorporating diverse image processing techniques to enhance adaptability. To tackle the inherent non-differentiability of image prompts, we further devise an information-estimation-based gradient descent strategy that leverages the information entropy of image processing combinations to optimize the prompter, ensuring effective adaptation. Through extensive experiments across nine datasets spanning seven image domains (i.e., depth, thermal, camouflage, endoscopic, ultrasound, grayscale, and natural) and four scenarios (i.e., common scenes, camouflage objects, medical images, and industrial data), we demonstrate that our approach significant improves the foundational models' adaptation capabilities. Moreover, the interpretability of the generated prompts provides insightful revelations into their image processing mechanisms. Source code is available at: \urlgithub.com/yuema1303/Prompting-to-Adapt-FSM.

3D facial animation has attracted considerable attention due to its extensive applications in the multimedia field. Audio-driven 3D facial animation has been widely explored with promising results. However, multi-modal 3D facial animation, especially text-guided 3D facial animation is rarely explored due to the lack of multi-modal 3D facial animation dataset. To fill this gap, we first construct a large-scale multi-modal 3D facial animation dataset, MMHead, which consists of 49 hours of 3D facial motion sequences, speech audios, and rich hierarchical text annotations. Each text annotation contains abstract action and emotion descriptions, fine-grained facial and head movements (i.e., expression and head pose) descriptions, and three possible scenarios that may cause such emotion. Concretely, we integrate five public 2D portrait video datasets, and propose an automatic pipeline to 1) reconstruct 3D facial motion sequences from monocular videos; and 2) obtain hierarchical text annotations with the help of AU detection and ChatGPT. Based on the MMHead dataset, we establish benchmarks for two new tasks: text-induced 3D talking head animation and text-to-3D facial motion generation. Moreover, a simple but efficient VQ-VAE-based method named MM2Face is proposed to unify the multi-modal information and generate diverse and plausible 3D facial motions, which achieves competitive results on both benchmarks. Extensive experiments and comprehensive analysis demonstrate the significant potential of our dataset and benchmarks in promoting the development of multi-modal 3D facial animation. The dataset will be released at: https://wsj-sjtu.github.io/MMHead/.

Action detection and understanding provide the foundation for the generation and interaction of multimedia content. However, existing methods mainly focus on constructing complex relational inference networks, overlooking the judgment of detection effectiveness. Moreover, these methods frequently generate detection results with cognitive abnormalities. To solve the above problems, this study proposes a cognitive effectiveness network based on fuzzy inference (Cefdet), which introduces the concept of 'cognition--based detection' to simulate human cognition. First, a fuzzy-driven cognitive effectiveness evaluation module (FCM) is established to introduce fuzzy inference into action detection. FCM is combined with human action features to simulate the cognition-based detection process, which clearly locates the position of frames with cognitive abnormalities. Then, a fuzzy cognitive update strategy (FCS) is proposed based on the FCM, which utilizes fuzzy logic to re-detect the cognition-based detection results and effectively update the results with cognitive abnormalities. Experimental results demonstrate that Cefdet exhibits superior performance against several mainstream algorithms on the public datasets, validating its effectiveness and superiority.

As a widely explored multi-modal task, 3D object grounding endeavors to localize a unique pre-existing object within a single 3D scene given a natural language description. However, such a strict setting is unnatural as it is not always possible to know whether a target object exists in a specific 3D scene. In real-world scenarios, a collection of 3D scenes is generally available, some of which may not contain the described object while some potentially contain multiple target objects. To this end, we introduce a more realistic setting, named Group-wise 3D Object Grounding, to simultaneously process a group of related 3D scenes, allowing a flexible number of target objects to exist in each scene. Instead of localizing target objects in each scene individually, we argue that ignoring the rich visual information contained in other related 3D scenes within the same group may lead to sub-optimal results. To achieve more accurate localization, we propose a baseline method named GNL3D, a Grouped Neural Listener for 3D grounding in the group-wise setting, which extends the traditional 3D object grounding pipeline with a novel language-guided consensus aggregation and distribution mechanism to explicitly exploit the intra-group visual connections. Specifically, based on context-aware spatial-semantic alignment, a language-guided consensus aggregation module is developed to aggregate the visual features of target objects in each 3D scene to form a visual consensus representation, which is then distributed and injected into a consensus-modulated feature refinement module for refining visual features, thus benefiting the subsequent multi-modal reasoning. To validate the effectiveness of the proposed method, we reorganize and enhance the ReferIt3D dataset and propose evaluation metrics to benchmark prior work and GNL3D. Extensive experiments demonstrate that GNL3D achieves state-of-the-art results on the group-wise setting and the traditional 3D object grounding task.

Reconstructing garments from monocular videos has attracted considerable attention as it provides a convenient and low-cost solution for clothing digitization. In reality, people wear clothing with countless variations and multiple layers. Existing studies attempt to extract garments from a single video. They either behave poorly in generalization due to reliance on limited clothing templates or struggle to handle the intersections of multi-layered clothing leading to the lack of physical plausibility. Besides, there are inevitable and undetectable overlaps for a single video that hinder researchers from modeling complete and intersection-free multi-layered clothing. To address the above limitations, in this paper, we propose a novel method to reconstruct multi-layered clothing from multiple monocular videos sequentially, which surpasses existing work in generalization and robustness against penetration. For each video, neural fields are employed to implicitly represent the clothed body, from which the meshes with frame-consistent structures are explicitly extracted. Next, we implement a template-free method for extracting a single garment by back-projecting the image segmentation labels of different frames onto these meshes. In this way, multiple garments can be obtained from these monocular videos and then aligned to form the whole outfit. However, intersection always occurs due to overlapping deformation in the real world and perceptual errors in monocular videos. To this end, we innovatively introduce a physics-aware module that combines neural fields with a position-based simulation framework to fine-tune the penetrating vertices of garments, ensuring robustly intersection-free. Additionally, we collect a mini dataset with fashionable garments to evaluate the quality of clothing reconstruction comprehensively. We release our code and data at https://github.com/SMY19999/IF-Garments.

Camouflaged instance segmentation is a challenging task due to the various aspects such as color, structure, lighting, etc., of object instances embedded in complex backgrounds. Although the current DETR-based scheme simplifies the pipeline, it suffers from a large number of object queries, leading to many false positive instances. To address this issue, we propose an adaptive query selection mechanism. Our research reveals that a large number of redundant queries scatter the extracted features of the camouflaged instances. To remove these redundant queries with weak correlation, we evaluate the importance of the object query from the perspectives of information entropy and volatility. Moreover, we observed that occlusion and overlapping instances significantly impact the accuracy of the selection mechanism. Therefore, we design a boundary location embedding mechanism that incorporates fake instance boundaries to obtain better location information for more accurate query instance matching. We conducted extensive experiments on two challenging camouflaged instance segmentation datasets, namely COD10K and NC4K, and demonstrated the effectiveness of our proposed model. Compared with the OSFormer, our model significantly improves the performance by 3.8% AP and 5.6% AP with less computational cost, achieving the state-of-the-art of 44.8 AP and 48.1 AP with ResNet-50 on the COD10K and NC4K test-dev sets, respectively.

Human facial reactions play crucial roles in dyadic human-human interactions, where individuals (i.e., listeners) with varying cognitive process styles may display different but appropriate facial reactions in response to an identical behaviour expressed by their conversational partners. While several existing facial reaction generation approaches are capable of generating multiple appropriate facial reactions (AFRs) in response to each given human behaviour, they fail to take human's personalised cognitive process in AFRs generation. In this paper, we propose the first online personalised multiple appropriate facial reaction generation (MAFRG) approach which learns a unique personalised cognitive style from the target human listener's previous facial behaviours and represents it as a set of network weight shifts. These personalised weight shifts are then applied to edit the weights of a pre-trained generic MAFRG model, allowing the obtained personalised model to naturally mimic the target human listener's cognitive process in its reasoning for multiple AFRs generations. Experimental results show that our approach not only largely outperformed all existing approaches in generating more appropriate and diverse generic AFRs, but also serves as the first reliable personalised MAFRG solution. Our code is made available at https://github.com/xk0720/PerFRDiff.

Content-adaptive compression is crucial for enhancing the adaptability of the pre-trained neural codec for various contents. Though, its application in neural video compression (NVC) is still limited due to two main aspects: 1), video compression relies heavily on temporal redundancy, therefore updating just one or a few frames can lead to significant errors accumulating over time; 2), NVC frameworks are generally complex, with many comprehensive components that are not trivial to update quickly during the encoding procedure. To address these challenges, we have developed a content-adaptive NVC technique called Group-aware Parameter-efficient Updating (GPU). Initially, to minimize error accumulation, we adopt a group-aware approach for updating encoder parameters. This involves adopting a patch-based Group of Pictures (GoP) updating strategy to segment a video into patch-based GoPs, which will be updated to facilitate a globally optimized domain-transferable solution. Subsequently, we introduce a parameter-efficient delta-tuning strategy, which is achieved by integrating several light-weight adapters into each encoding component by using both serial and parallel configuration. Such architecture-agnostic modules stimulate the components with large parameters, thereby reducing the updating cost during the encoding stage. We incorporate our GPU into the latest NVC framework and conduct extensive experiments, whose results showcase outstanding video compression efficiency across six video compression benchmarks and the adaptability of one medical volumetric image compression benchmark.

Recently, stable diffusion (SD) models have typically flourished in the field of image synthesis and personalized editing, with a range of photorealistic and unprecedented images being successfully generated. As a result, widespread interest has been ignited to develop and use various SD-based tools for visual content creation. However, the exposure of AI-created content on public platforms could raise both legal and ethical risks. In this regard, the traditional methods of adding watermarks to the already generated images (i.e. post-processing) may face a dilemma (e.g., being erased or modified) in terms of copyright protection and content monitoring, since the powerful image inversion and text-to-image editing techniques have been widely explored in SD-based methods. In this work, we propose a Safe and high-traceable Stable Diffusion framework (namely Safe-SD) to adaptively implant the graphical watermarks (e.g., QR code) into the imperceptible structure-related pixels during the generative diffusion process for supporting text-driven invisible watermarking and detection. Different from the previous high-cost injection-then-detection training framework, we design a simple and unified architecture, which makes it possible to simultaneously train watermark injection and detection in a single network, greatly improving the efficiency and convenience of use. Moreover, to further support text-driven generative watermarking and deeply explore its robustness and high-traceability, we elaborately design a λ-sampling and λ-encryption algorithm to fine-tune a latent diffuser wrapped by a VAE for balancing high-fidelity image synthesis and high-traceable watermark detection. We present our quantitative and qualitative results on two representative datasets LSUN, COCO and FFHQ, demonstrating state-of-the-art performance of Safe-SD and showing it significantly outperforms the previous approaches.

Sampling strategies have been widely adopted in Vision-Language Pre-training (VLP) and have achieved great success recently. However, the sampling strategies adopted by current VLP works are limited in two ways: i) they only focus on negative sampling, ignoring the importance of more informative positive samples; ii) their sampling strategies are conducted in the local in-batch level, which may lead to sub-optimal results. To tackle these problems, in this paper, we propose a curriculum-based Global Positive-Negative Sampling (GPN-S) framework for vision-language pre-training, which conducts both positive and negative sampling in the global level, grounded on the notion of neighborhood relationships. Additionally, we incorporate curriculum learning into our sampling strategy, progressively increasing the complexity of samples as the training progresses. Specifically, our proposed GPN-S framework is capable of utilizing positive sampling to bring semantically equivalent samples closer, as well as employing negative sampling to push challenging negative samples farther away. We jointly consider them for vision-language pre-training on the global-level perspective rather than a local-level mini-batch, which provides more informative and diverse samples. We evaluate the effectiveness of the proposed GPN-S framework by conducting experiments on several common downstream tasks, and the results demonstrate significant performance improvement over the existing models.

Multi-object tracking (MOT) is a pivotal task for media interpretation, where reliable motion and appearance cues are essential for cross-frame identity preservation. However, limited by the inherent perspective properties of 2D space, the crowd density and frequent occlusions in real-world scenes expose the fragility of these cues. We observe the natural advantage of objects being well-separated in high-dimensional space and propose a novel 2D MOT framework, "Detecting-Lifting-Tracking'' (DLT). Initially, a pre-trained detector is employed to capture 2D object information. Secondly, we introduce a Mamba Distance Estimator to obtain the distances of objects to a monocular camera with temporal consistency, achieving object-level pseudo-3D lifting. Finally, we thoroughly explore distance-aware tracking via pseudo-3D information. Specifically, we introduce a Score-Distance Hierarchical Matching and Short-Long Terms Association to enhance accurate and robust association capability. Even without appearance cues, our DLT achieves state-of-the-art performance on MOT17, MOT20, and DanceTrack, demonstrating its potential to address occlusion challenges.

Modeling in Computer Vision has evolved to MLPs. Vision MLPs naturally lack local modeling capability, to which the simplest treatment is combined with convolutional layers. Convolution, famous for its sliding window scheme, also suffers from this scheme of redundancy and lower parallel computation. In this paper, we seek to dispense with the windowing scheme and introduce a more elaborate and parallelizable method to exploit locality. To this end, we propose a new MLP module, namely Shifted-Pillars-Concatenation (SPC), that consists of two steps of processes: (1) Pillars-Shift, which generates four neighboring maps by shifting the input image along four directions, and (2) Pillars-Concatenation, which applies linear transformations and concatenation on the maps to aggregate local features. SPC module offers superior local modeling power and performance gains, making it a promising alternative to the convolutional layer. Then, we build a pure-MLP architecture called Caterpillar by replacing the convolutional layer with the SPC module in a hybrid model of sMLPNet. Extensive experiments show Caterpillar's excellent performance on both small-scale and ImageNet-1k classification benchmarks, with remarkable scalability and transfer capability possessed as well. The code is available at https://github.com/sunjin19126/Caterpillar.

Multimodal contrastive learning (MCL) has shown remarkable advances in zero-shot classification by learning from millions of image-caption pairs crawled from the Internet. However, this reliance poses privacy risks, as hackers may unauthorizedly exploit image-text data for model training, potentially including personal and privacy-sensitive information. Recent works propose generating unlearnable examples by adding imperceptible perturbations to training images to build shortcuts for protection. However, they are designed for unimodal classification, which remains largely unexplored in MCL. We first explore this context by evaluating the performance of existing methods on image-caption pairs, and they do not generalize effectively to multimodal data and exhibit limited impact to build shortcuts due to the lack of labels and the dispersion of pairs in MCL. In this paper, we propose Multi-step Error Minimization (MEM), a novel optimization process for generating multimodal unlearnable examples. It extends the Error-Minimization (EM) framework to optimize both image noise and an additional text trigger, thereby enlarging the optimized space and effectively misleading the model to learn the shortcut between the noise features and the text trigger. Specifically, we adopt projected gradient descent to solve the noise minimization problem and use HotFlip to approximate the gradient and replace words to find the optimal text trigger. Extensive experiments demonstrate the effectiveness of MEM, with post-protection retrieval results nearly half of random guessing, and its high transferability across different models. Our code is available on the https://github.com/thinwayliu/Multimodal-Unlearnable-Examples

Video Virtual Try-On aims to transfer a garment onto a person in the video. Previous methods typically focus on image-based virtual try-on, but directly applying these methods to videos often leads to temporal discontinuity due to inconsistencies between frames. Limited attempts in video virtual try-on also suffer from unrealistic results and poor generalization ability. In light of previous research, we posit that the task of video virtual try-on can be decomposed into two key aspects: (1) single-frame results are realistic and natural, while retaining consistency with the garment; (2) the person's actions and the garment are coherent throughout the entire video. To address these two aspects, we propose a novel two-stage framework based on Latent Diffusion Model, namely Garment-Preserving Diffusion for Video Virtual Try-On (GPD-VVTO). In the first stage, the model is trained on single-frame data to improve the ability of generating high-quality try-on images. We integrate both low-level texture features and high-level semantic features of the garment into the denoising network to preserve garment details while ensuring a natural fit between the garment and the person. In the second stage, the model is trained on video data to enhance temporal consistency. We devise a novel Garment-aware Temporal Attention (GTA) module that incorporates garment features into temporal attention, enabling the model to maintain the fidelity to the garment during temporal modeling. Furthermore, we collect a video virtual try-on dataset containing high-resolution videos from diverse scenes, addressing the limited variety of current datasets in terms of video background and human actions. Extensive experiments demonstrate that our method outperforms existing state-of-the-art methods in both image-based and video-based virtual try-on tasks, indicating the effectiveness of our proposed framework.

Graph-based fraud detection (GFD) has garnered increasing attention due to its effectiveness in identifying fraudsters within multimedia data such as online transactions, product reviews, or telephone voices. However, the prevalent in-distribution (ID) assumption significantly impedes the generalization of GFD approaches to out-of-distribution (OOD) scenarios, which is a pervasive challenge considering the dynamic nature of fraudulent activities. In this paper, we introduce the Heterophilic Graph Invariant Learning Framework (HGIF), a novel approach to bolster the OOD generalization of GFD. HGIF addresses two pivotal challenges: creating diverse virtual training environments and adapting to varying target distributions. Leveraging edge-aware augmentation, HGIF efficiently generates multiple virtual training environments characterized by generalized heterophily distributions, thereby facilitating robust generalization against fraud graphs with diverse heterophily degrees. Moreover, HGIF employs a shared dual-channel encoder with heterophilic graph contrastive learning, enabling the model to acquire stable high-pass and low-pass node representations during training. During the Test-time Training phase, the shared dual-channel encoder is flexibly fine-tuned to adapt to the test distribution through graph contrastive learning. Extensive experiments showcase HGIF's superior performance over existing methods in OOD generalization, setting a new benchmark for GFD in OOD scenarios.

Generating face image with specific gaze information has attracted considerable attention in recent years. Existing approaches typically input gaze values directly for face generation, which is unnatural and requires annotated gaze datasets for training, thereby limiting its application. In this paper, we present a novel gaze-controllable face generation task that overcomes these limitations. Our approach inputs textual descriptions that describe human gaze and head behavior and generates corresponding face images. Our work first introduces a text-of-gaze dataset containing over 90k text descriptions spanning a dense distribution of gaze and head poses. We further propose a gaze-controllable text-to-face method. Our method contains a sketch-conditioned face diffusion module and a model-based sketch diffusion module. We define a face sketch based on facial landmarks and eye segmentation map. It provides a structured and detailed foundation for generating facial images. The face diffusion module generates face images from the face sketch, and the sketch diffusion module employs a 3D face model to generate face sketch from text description. Experiments on the FFHQ dataset show the effectiveness of our method. Our dataset is available at https://github.com/hengfei-wang/TextGaze.

Multimodal Dialogue agents are often required to respond to conversation history using both textual and visual content. Even though current dialogue studies predominantly strive to generate natural texts or images, they fall short in considering the relevance of multimodal responses within a dialogue context, consequently confining agents from making prudent choices based on multiple alternatives and their associated relevance scores for decision-making. In this paper, we present a bidirectional multimodal dialogue framework that skillfully combines the forward generation of multiple text and image response candidates with reverse selection guided by relevance scores evaluated on dialogue context, facilitating agents in selecting the most suitable multimodal responses. Specifically, the forward generation aspect of our framework leverages a stage-wise approach, first producing textual replies and composite visual descriptions from the dialogue context, followed by the generation of visual responses aligned with the descriptions. In the reverse selection process, visual responses are translated into tangible descriptive texts that, in conjunction with textual responses, are inversely tied back to the dialogue context for relevance assessment, assigning a reference score to each multimodal response candidate to assist the intelligent agent in making informed decisions. Experimental outcomes demonstrate that our proposed bidirectional dialogue response framework markedly elevates performance in both automatic and human evaluations, yielding a range of contextually fitting multimodal responses for selection.