ACM MM 2024 Papers

Recently, transformer-based techniques incorporating superpoints have become prevalent in 3D instance segmentation. However, they often encounter an over-segmentation problem, especially noticeable with large objects. Additionally, unreliable mask predictions stemming from superpoint mask prediction further compound this issue. To address these challenges, we propose a novel framework called MSTA3D. It leverages multi-scale feature representation and introduces a twin-attention mechanism to effectively capture them. Furthermore, MSTA3D integrates a box query with a box regularizer, offering a complementary spatial constraint alongside semantic queries. Experimental evaluations on ScanNetV2, ScanNet200 and S3DIS datasets demonstrate that our approach surpasses state-of-the-art 3D instance segmentation methods.

Dynamic Facial Expression Recognition (DFER) is crucial for understanding human behavior. However, current methods exhibit limited performance mainly due to the scarcity of high-quality data, the insufficient utilization of facial dynamics, and the ambiguity of expression semantics, etc. To this end, we propose a novel framework, named Multi-modal Fine-grained CLIP for Dynamic Facial Expression Recognition with AdaptERs (FineCLIPER), incorporating the following novel designs: 1) To better distinguish between similar facial expressions, we extend the class labels to textual descriptions from both positive and negative aspects, and obtain supervision by calculating the cross-modal similarity based on the CLIP model; 2) Our FineCLIPER adopts a hierarchical manner to effectively mine useful cues from DFE videos. Specifically, besides directly embedding video frames as input (low semantic level), we propose to extract the face segmentation masks and landmarks based on each frame (middle semantic level) and utilize the Multi-modal Large Language Model (MLLM) to further generate detailed descriptions of facial changes across frames with designed prompts (high semantic level). Additionally, we also adopt Parameter-Efficient Fine-Tuning (PEFT) to enable efficient adaptation of large pre-trained models (i.e., CLIP) for this task. Our FineCLIPER achieves SOTA performance on the DFEW, FERV39k, and MAFW datasets in both supervised and zero-shot settings with few tunable parameters. Project Page: https://haroldchen19.github.io/FineCLIPER-Page/

Multi-party Mobile Virtual Reality (MMVR) enables multiple mobile users to share virtual scenes for immersive multimedia experience in scenarios such as gaming, social interaction, and industrial mission collaboration. Dynamic 3D Point Cloud (DPCL) is an emerging representation form of MMVR that can be consumed as a free-viewpoint video with 6 degrees of freedom. Given that it is challenging to render DPCL at a satisfying frame rate with limited on-device resources, offloading rendering tasks to edge servers is recognized as a practical solution. However, repeated loading of DPCL scenes with a substantial amount of metadata introduces a significant redundancy overhead that cannot be overlooked when enabling multiple edge servers to support the rendering requirements of user groups. In this paper, we design PoClVR, an edge-assisted DPCL rendering system for MMVR applications, which breaks down the rendering process of the complete dynamic scene into multiple rendering tasks of dynamic objects. PoClVR significantly reduces the repetitive loading overhead of DPCL scenes on edge servers and periodically adjusts the rendering task allocation during the application running to accommodate rendering requirements. We deploy PoClVR based on a real-world implementation and the experimental evaluation results show that PoClVR can reduce GPU utilization by up to 15.1% and increase rendering frame rate by up to 34.6% compared to other baselines while ensuring that the image quality viewed by the user is virtually unchanged.

Click-through rate (CTR) prediction is an essential component of industrial multimedia recommendation, and the key to enhancing the accuracy of CTR prediction lies in the effective modeling of feature interactions using rich user profiles, item attributes, and contextual information. Most of the current deep CTR models resort to parallel or stacked structures to break through the performance bottleneck of Multi-Layer Perceptron (MLP). However, we identify two limitations in these models: (1) parallel or stacked structures often treat explicit and implicit components as isolated entities, leading to a loss of mutual information; (2) traditional CTR models, whether in terms of supervision signals or interaction methods, lack the ability to filter out noise information, thereby limiting the effectiveness of the models.

Video Moment Retrieval (MR) tasks involve predicting the moment described by a given natural language or spoken language query in an untrimmed video. In this paper, we propose a novel Maskable Retentive Network (MRNet) to address two key challenges in MR tasks: cross-modal guidance and video sequence modeling. Our approach introduces a new retention mechanism into the multimodal Transformer architecture, incorporating modality-specific attention modes. Specifically, we employ the Unlimited Attention for language-related attention regions to maximize cross-modal mutual guidance. Then, we introduce the Maskable Retention for video-only attention region to enhance video sequence modeling, that is, recognizing two crucial characteristics of video sequences: 1) bidirectional, decaying, and non-linear temporal associations between video clips, and 2) sparse associations of key information semantically related to the query. We propose a bidirectional decay retention mask to explicitly model temporal-distant context dependencies of video sequences, along with a learnable sparse retention mask to adaptively capture strong associations relevant to the target event. Extensive experiments conducted on five popular benchmarks ActivityNet Captions, TACoS, Charades-STA, ActivityNet Speech, and QVHighlights for MR tasks demonstrate the significant improvements achieved by our method over existing approaches. Code is available at https://github.com/xian-sh/MRNet.

Vision transformer family has dominated the satellite pan-sharpening field driven by the global-wise spatial information modeling mechanism from the core self-attention ingredient. The standard modeling rules within these promising pan-sharpening methods are to roughly stack the transformer variants in a cascaded manner. Despite the remarkable advancement, their success may be at the huge cost of model parameters and FLOPs, thus preventing its application over low-resource satellites.To address this challenge between favorable performance and expensive computation, we tailor an efficient linearly-evolved transformer variant and employ it to construct a lightweight pan-sharpening framework. In detail, we deepen into the popular cascaded transformer modeling with cutting-edge methods and develop the alternative 1-order linearly-evolved transformer variant with the 1-dimensional linear convolution chain to achieve the same function. In this way, our proposed method is capable of benefiting the cascaded modeling rule while achieving favorable performance in the efficient manner. Extensive experiments over multiple satellite datasets suggest that our proposed method achieves competitive performance against other state-of-the-art with fewer computational resources. Further, the consistently favorable performance has been verified over the hyper-spectral image fusion task. Our main focus is to provide an alternative global modeling framework with an efficient structure. The code will be publicly available.

Event-based human pose estimation has gained popularity due to the benefits of high temporal resolution and high dynamic range offered by event cameras. The inherent spatial sparsity of event data makes discarding less significant regions a straightforward and effective way to decrease the computation. However, implementing this operation in CNNs poses a challenge, as it disrupts the regularity of dense convolutional workload. In this paper, we propose an adaptive vision transformer, a novel efficient backbone for human pose estimation with event cameras. Specifically, we present two adaptive patch and token sampling approaches based on the characteristics of events, thereby reducing the computational load while still achieving comparable performance. Firstly, we design an adaptive patch sampling scheme to eliminate inactivity patches by assessing the entropy of the events before they are inputted into the transformer. Secondly, we further propose an adaptive token reduction strategy to selectively remove less informative tokens in transformer layers through a dynamic token pruning algorithm. To exploit event-based visual cues in human pose estimation tasks, we construct a large-scale frame-event-based dataset, dubbed Event Multi Movement HPE (EventMM HPE). The dataset provides annotation frequencies up to 240 Hz. Extensive experiments demonstrate that our proposed approach outperforms existing state-of-the-art methods in estimation accuracy. The source code and dataset are available at https://github.com/doublemanyu/Adaptive-Vision-Transformer-for-Event-Based-HPE.

The open-vocabulary human-object interaction (Ov-HOI) detection aims to identify both base and novel categories of human-object interactions while only base categories are available during training. Existing Ov-HOI methods commonly leverage knowledge distilled from CLIP to extend their ability to detect previously unseen interaction categories. However, our empirical observations indicate that the inherent noise present in CLIP has a detrimental effect on HOI prediction. Moreover, the absence of novel human-object position distributions often leads to overfitting on the base categories within their learned queries. To address these issues, we propose a two-step framework named, CaM-LQ, Calibrating visual-language Models, (e.g., CLIP) for open-vocabulary HOI detection with Locality-aware Queries. By injecting the fine-grained HOI supervision from the calibrated CLIP into the HOI decoder, our model can achieve the goal of predicting novel interactions. Extensive experimental results demonstrate that our approach performs well in open-vocabulary human-object interaction detection, surpassing state-of-the-art methods across multiple metrics on mainstream datasets and showing superior open-vocabulary HOI detection performance, e.g., with 4.54 points improvement on the HICO-DET dataset over the SoTA CLIP4HOI on the UV task with the same backbone ResNet-50.

In practical object detection scenarios, distributed data and stringent privacy protections significantly limit the feasibility of traditional centralized training methods. Federated learning (FL) emerges as a promising solution to this dilemma. Nonetheless, the issue of data heterogeneity introduces distinct challenges to federated object detection, evident in diminished object perception, classification and localization abilities. In response, we introduce a task-driven federated learning methodology, dubbed Adaptive Hierarchical Aggregation (FedAHA), tailored to overcome these obstacles. Our algorithm unfolds in two strategic phases from shallow-to-deep layers: (1) Structure-aware Aggregation (SAA) aligns feature extractors during the aggregation phase, thus bolstering the global model's object perception capabilities; (2) Convex Semantic Calibration (CSC) leverages convex function theory to average semantic features instead of model parameters, enhancing the global model's classification and localization precision. We demonstrate experimentally and theoretically the effectiveness of the proposed two modules respectively. Our method consistently outperforming the state-of-the-art methods across multiple valuable application scenarios from 2.26% to 7.61%. Moreover, we build a real FL system using Raspberry Pis to demonstrate that our approach achieves a good trade-off between performance and efficiency.

LiDAR-based Moving Object Segmentation (MOS) aims to locate and segment moving objects in point clouds of the current scan using motion information from previous scans. Despite the promising results achieved by previous MOS methods, several key issues, such as the weak coupling of temporal and spatial information, still need further study. In this paper, we propose a novel LiDAR-based 3D Moving Object Segmentation with Motion-aware State Space Model, termed MambaMOS. Firstly, we develop a novel embedding module, the Time Clue Bootstrapping Embedding (TCBE), to enhance the coupling of temporal and spatial information in point clouds and alleviate the issue of overlooked temporal clues. Secondly, we introduce the Motion-aware State Space Model (MSSM) to endow the model with the capacity to understand the temporal correlations of the same object across different time steps. Specifically, MSSM emphasizes the motion states of the same object at different time steps through two distinct temporal modeling and correlation steps. We utilize an improved state space model to represent these motion differences, significantly modeling the motion states. Finally, extensive experiments on the SemanticKITTI-MOS and KITTI-Road benchmarks demonstrate that the proposed MambaMOS achieves state-of-the-art performance. The source code is publicly available at https://github.com/Terminal-K/MambaMOS

The detection of fake news has emerged as a pressing issue in the era of online social media. To detect meticulously fabricated fake news, propagation paths are introduced to provide nuanced social context to complement the pure semantics within news content. However, existing propagation-enhanced models face a dilemma between detection efficacy and social hazard. In this paper, we investigate the novel problem of early fake news detection via propagation path generation, capable of enjoying the merits of rich social context within propagation paths while alleviating potential social hazards. In contrast to previous discriminative detection models, we further propose a novel generative model, DGA-Fake, by simulating realistic propagation paths based on news content before actual spreading. A guided diffusion module is integrated into DGA-Fake to generate simulated user interaction sequences, guided by historical interactions and news content. Evaluation across three datasets demonstrates the superiority of our proposal.

Audio-Visual Segmentation (AVS) aims to segment sound-producing objects in videos according to associated audio cues, where both modalities are affected by noise to different extents, such as the blending of background noises in audio or the presence of distracted objects in video. Most existing methods focus on learning interactions between modalities at high semantic levels but is incapable of filtering low-level noise or achieving fine-grained representational interactions during the early feature extraction phase. Consequently, they struggle with illusion issues, where nonexistent audio cues are erroneously linked to visual objects. In this paper, we present SelM, a novel architecture that leverages selective mechanisms to counteract these illusions. SelM employs State Space model for noise reduction and robust feature selection. By imposing additional bidirectional constraints on audio and visual embeddings, it is able to precisely identify crucial features corresponding to sound-emitting targets. To fill the existing gap in early fusion within AVS, SelM introduces a dual alignment mechanism specifically engineered to facilitate intricate spatio-temporal interactions between audio and visual streams, achieving more fine-grained representations. Moreover, we develop a cross-level decoder for layered reasoning, significantly enhancing segmentation precision by exploring the complex relationships between audio and visual information. SelM achieves state-of-the-art performance in AVS tasks, especially in the challenging Audio-Visual Semantic Segmentation subset. The code can be found at https://github.com/Cyyzpoi/SelM.

Blind Face Restoration (BFR) aims to restore high-quality face images from low-quality images with unknown degradation. Previous GAN-based or ViT-based methods have shown promising results, but have identity details loss once degradation is severe; while recent diffusion-based methods work on image level and take a lot of time to infer. To restore images in any degradation types with high quality and spend less time compared to the classic diffusion-based method, we propose LD-BFR, a novel BFR framework that integrates both the strengths of vector quantization and latent diffusion. First, we employ a Dual Cross-Attention vector quantization to restore the degraded image in a global manner. Then we utilize the restored high-quality quantized feature as the guidance in our latent diffusion model to generate high-quality restored images with rich details. With the help of the proposed high-quality feature injection module, our LD-BFR effectively injects the high-quality feature as a condition to guide the generation of our latent diffusion model. Extensive experiments demonstrate the superior performance of our model over the SOTA BFR methods. The code is available at: https://github.com/YuzhenD/LD-BFR.git

Although existing video-based 3D human mesh recovery methods have made significant progress, simultaneously estimating human pose and shape from low-resolution image features limits their performance. These image features lack sufficient spatial information about the human body and contain various noises (e.g., background, lighting, and clothing), which often results in inaccurate pose and inconsistent motion. Inspired by the rapid advance in human pose estimation, we discover that compared to image features, skeletons inherently contain accurate human pose and motion. Therefore, we propose a novel semiAnalytical Regressor using disenTangled Skeletal representations for human mesh recovery from videos, called ARTS. Specifically, a skeleton estimation and disentanglement module is proposed to estimate the 3D skeletons from a video and decouple them into disentangled skeletal representations (i.e., joint position, bone length, and human motion). Then, to fully utilize these representations, we introduce a semi-analytical regressor to estimate the parameters of the human mesh model. The regressor consists of three modules: Temporal Inverse Kinematics (TIK), Bone-guided Shape Fitting (BSF), and Motion-Centric Refinement (MCR). TIK utilizes joint position to estimate initial pose parameters and BSF leverages bone length to regress bone-aligned shape parameters. Finally, MCR combines human motion representation with image features to refine the initial human model parameters. Extensive experiments demonstrate that our ARTS surpasses existing state-of-the-art video-based methods in both per-frame accuracy and temporal consistency on popular benchmarks: 3DPW, MPI-INF-3DHP, and Human3.6M. Code is available at https://github.com/TangTao-PKU/ARTS.

Point cloud data is pivotal in applications like autonomous driving, virtual reality, and robotics. However, its substantial volume poses significant challenges in storage and transmission. In order to obtain a high compression ratio, crucial semantic details usually confront severe damage, leading to difficulties in guaranteeing the accuracy of downstream tasks. To tackle this problem, we are the first to introduce a novel Region of Interest (ROI)-guided Point Cloud Geometry Compression (RPCGC) method for human and machine vision. Our framework employs a dual-branch parallel structure, where the base layer encodes and decodes a simplified version of the point cloud, and the enhancement layer refines this by focusing on geometry details. Furthermore, the residual information of the enhancement layer undergoes refinement through an ROI prediction network. This network generates mask information, which is then incorporated into the residuals, serving as a strong supervision signal. Additionally, we intricately apply these mask details in the Rate-Distortion (RD) optimization process, with each point weighted in the distortion calculation. Our loss function includes RD loss and detection loss to better guide point cloud encoding for the machine. Experiment results demonstrate that RPCGC achieves exceptional compression performance and better detection accuracy (10% gain) than some learning-based compression methods at high bitrates in ScanNet and SUN RGB-D datasets.

Image Aesthetic Assessment (IAA) aims to objectively predict the generic or personalized evaluations, of the aesthetic or fine-grained multi-attributes, based on visual or multimodal inputs. Previously, researchers have designed diverse and specialized methods, for specific IAA tasks, based on different input-output situations. Is it possible to design a universal IAA framework applicable for the whole IAA task taxonomy? In this paper, we explore this issue, and propose a modular IAA framework, dubbed AesMamba. Specially, we use the Visual State Space Model (VMamba), instead of CNNs or ViTs, to learn comprehensive representations of aesthetic-related attributes; because VMamba can efficiently achieve both global and local effective receptive fields. Afterward, a modal-adaptive module is used to automatically produce the integrated representations, conditioned on the type of input. In the prediction module, we propose a Multitask Balanced Adaptation (MBA) module, to boost task-specific features, with emphasis on the tail instances. Finally, we formulate the personalized IAA task as a multimodal learning problem, by converting a user's anonymous subject characters to a text prompt. This prompting strategy effectively employs the semantics of flexibly selected characters, for inferring individual preferences. AesMamba can be applied to diverse IAA tasks, through flexible combination of these modules. Extensive experiments on numerous datasets, demonstrate that AesMamba consistently achieves superior or competitive performance, on all IAA tasks, in comparison with previous SOTA methods. The code has been released at https://github.com/AiArt-Gao/AesMamba Github.

Multi-modality image fusion (MMIF) aims to integrate the complementary features of source images into the fused image, including target saliency and texture specifics. Recently, image fusion methods leveraging diffusion models have demonstrated commendable results. Despite their strengths, diffusion models reduce the capability to perceive local features. Additionally, their inherent working mechanism, introducing noise to the inputs, consequently leads to a loss of original information. To overcome this problem, we propose a novel Diffusion-CNN feature Aggregation Fusion (DCAFuse) network that can extract complementary features from the dual branches and aggregate them effectively. Specifically, we utilize the denoising diffusion probabilistic model (DDPM) in the diffusion-based branch to construct global information, and multi-scale convolutional kernels in the CNN-based branch to extract local detailed features. Afterward, we design a novel complementary feature aggregation module (CFAM). By constructing coordinate attention maps for features, CFAM captures long-range dependencies in both horizontal and vertical directions, thereby dynamically guiding the aggregation weights of branches. In addition, to further improve the complementarity of dual-branch features, we introduce a novel loss function based on cosine similarity and a unique denoising timestep selection strategy. Extensive experimental results show that our proposed DCAFuse outperforms other state-of-the-art methods in multiple image fusion tasks, including infrared and visible image fusion (IVF) and medical image fusion (MIF).

Deep learning has made significant advancements and breakthroughs in medical image recognition. However, the clinical reality is complex and multifaceted, with patients often suffering from multiple intertwined diseases, not all of which are equally common, leading to medical datasets that are frequently characterized by multi-labels and a long-tailed distribution. In this paper, we propose a method involving label decoupling and reconstruction (LDRNet) to address these two specific challenges. The label decoupling utilizes the fusion of semantic information from both categories and images to capture the class-aware features across different labels. This process not only integrates semantic information from labels and images to improve the model's ability to recognize diseases, but also captures comprehensive features across various labels to facilitate a deeper understanding of disease characteristics within the dataset. Following this, our label reconstruction method uses the class-aware features to reconstruct the label distribution. This step generates a diverse array of virtual features for tail categories, promoting unbiased learning for the classifier and significantly enhancing the model's generalization ability and robustness. Extensive experiments conducted on three multi-label long-tailed medical image datasets, including the Axial Spondyloarthritis Dataset, NIH Chest X-ray 14 Dataset, and ODIR-5K Dataset, have demonstrated that our approach achieves state-of-the-art performance, showcasing its effectiveness in handling the complexities associated with multi-label and long-tailed distributions in medical image recognition.

Ultra-high-definition (UHD) technology has attracted widespread attention due to its exceptional visual quality, but it also poses new challenges for low-light image enhancement (LLIE) techniques. UHD images inherently possess high computational complexity, leading existing UHD LLIE methods to employ high-magnification downsampling to reduce computational costs, which in turn results in information loss. The wavelet transform not only allows downsampling without loss of information, but also separates the image content from the noise. It enables state space models (SSMs) to avoid being affected by noise when modeling long sequences, thus making full use of the long-sequence modeling capability of SSMs. On this basis, we propose Wave-Mamba, a novel approach based on two pivotal insights derived from the wavelet domain: 1) most of the content information of an image exists in the low-frequency component, less in the high-frequency component. 2) The high-frequency component exerts a minimal influence on the outcomes of low-light enhancement. Specifically, to efficiently model global content information on UHD images, we proposed a low-frequency state space block (LFSSBlock) by improving SSMs to focus on restoring the information of low-frequency sub-bands. Moreover, we propose a high-frequency enhance block (HFEBlock) for high-frequency sub-band information, which uses the enhanced low-frequency information to correct the high-frequency information and effectively restore the correct high-frequency details. Through comprehensive evaluation, our method has demonstrated superior performance, significantly outshining current leading techniques while maintaining a more streamlined architecture. The code is available at https://github.com/AlexZou14/Wave-Mamba.