ACM MM 2024 论文列表

High frame-rate~(HFR) videos of action recognition improve fine-grained expression while reducing the spatio-temporal relation and motion information density. Thus, large amounts of video samples are continuously required for traditional data-driven training. However, samples are not always sufficient in real-world scenarios, promoting few-shot action recognition~(FSAR) research. We observe that most recent FSAR works build spatio-temporal relation of video samples via temporal alignment after spatial feature extraction, cutting apart spatial and temporal features within samples. They also capture motion information via narrow perspectives between adjacent frames without considering density, leading to insufficient motion information capturing. Therefore, we propose a novel plug-and-play architecture for FSAR called Spatio-tempOral frAme tuPle enhancer (SOAP) in this paper. The model we designed with such architecture refers to SOAP-Net. Temporal connections between different feature channels and spatio-temporal relation of features are considered instead of simple feature extraction. Comprehensive motion information is also captured, using frame tuples with multiple frames containing more motion information than adjacent frames. Combining frame tuples of diverse frame counts further provides a broader perspective. SOAP-Net achieves new state-of-the-art performance across well-known benchmarks such as SthSthV2, Kinetics, UCF101, and HMDB51. Extensive empirical evaluations underscore the competitiveness, pluggability, generalization, and robustness of SOAP. The code is released at https://github.com/wenbohuang1002/SOAP.

In recent years, Vision-Language Pre-training (VLP) models have demonstrated rich prior knowledge for multimodal alignment, prompting investigations into their application in Specific Domain Image-Text Retrieval(SDITR) such as Text-Image Person Re-identification (TIReID) and Remote Sensing Image-Text Retrieval (RSITR). Due to the unique data characteristics in specific scenarios, the primary challenge is to leverage discriminative fine-grained local information for improved mapping of images and text into a shared space. Current approaches interact with all multimodal local features for alignment, implicitly focusing on discriminative local information to distinguish data differences, which may bring noise and uncertainty. Furthermore, their VLP feature extractors like CLIP often focus on instance-level representations, potentially reducing the discriminability of fine-grained local features. To alleviate these issues, we propose an Explicit Key Local information Selection and Reconstruction Framework (EKLSR), which explicitly selects key local information to enhance feature representation. Specifically, we introduce a Key Local information Selection and Fusion (KLSF) that utilizes hidden knowledge from the VLP model to select interpretably and fuse key local information. Secondly, we employ Key Local segment Reconstruction (KLR) based on multimodal interaction to reconstruct the key local segments of images (text), significantly enriching their discriminative information and enhancing both inter-modal and intra-modal interaction alignment. To demonstrate the effectiveness of our approach, we conducted experiments on five datasets across TIReID and RSITR. Notably, our EKLSR model achieves state-of-the-art performance on two RSITR datasets.

Whether it is an e-commerce platform or a short video platform, the effective use of multi-modal data plays an important role in the recommendation system. More and more researchers are exploring how to effectively use multimodal signals to entice more users to buy goods or watch short videos. Some studies have added multimodal features as side information to the model and achieved certain results. In practice, the purchase behavior of users mainly depends on some personalized intentions. However, it is difficult for neural networks to process noise information and extract high-level intention information effectively. To investigate the benefits of latent intentions and leverage them effectively for recommendation, we propose a Multimodal-aware Multi-intention Learning method for recommendation (MMIL). Specifically, we first construct a multi-intention recommendation framework based on the probability distribution relationship among predicted objectives and intentions, while avoiding intention overfitting. We then design an intention representation learning module to learn accurate multiple intention representations based on intention prototypes. Further, we propose a multi-modal intention perceptron module to learn multi-modal intention representations. In addition, we design self-supervised intention-based and representation-based contrastive objectives to achieve cross-modal representation alignment. On three real-world data sets, the proposed MMIL method outperforms other advanced techniques. The effectiveness of intention modeling and intention alignment is verified by comprehensive experiments. The source code is available at: https://github.com/ml-mindset/MMIL.

Recent work shows that documents from encyclopedias serve as helpful auxiliary information for zero-shot learning. Existing methods align the entire semantics of a document with corresponding images to transfer knowledge. However, they disregard that semantic information is not equivalent between them, resulting in a suboptimal alignment. In this work, we propose a novel network to extract multi-view semantic concepts from documents and images and align the matching rather than entire concepts. Specifically, we propose a semantic decomposition module to generate multi-view semantic embeddings from visual and textual sides, providing the basic concepts for partial alignment. To alleviate the issue of information redundancy among embeddings, we propose the local-to-semantic variance loss to capture distinct local details and multiple semantic diversity loss to enforce orthogonality among embeddings. Subsequently, two losses are introduced to partially align visual-semantic embedding pairs according to their semantic relevance at the view and word-to-patch levels. Consequently, we consistently outperform state-of-the-art methods under two document sources in three standard benchmarks for document-based zero-shot learning. Qualitatively, we show that our model learns the interpretable partial association. Code is available at https://github.com/MorningStarOvO/EmDepart.

Multi-modal learning leverages data from diverse perceptual media to obtain enriched representations, thereby empowering machine learning models to complete more complex tasks. However, recent research results indicate that multi-modal learning still suffers from " modality imbalance '': Certain modalities' contributions are suppressed by dominant ones, consequently constraining the overall performance enhancement of multimodal learning. To tackle this issue, current approaches attempt to mitigate modality competition in various ways, but their effectiveness is still limited. To this end, we propose an Euler Representation Learning-based Modality Rebalance (ERL-MR) strategy, which reshapes the underlying competitive relationships between modalities into mutually reinforcing win-win situations while maintaining stable feature optimization directions. Specifically, ERL-MR employs Euler's formula to map original features to complex space, constructing cooperatively enhanced non-redundant features for each modality, which helps reverse the situation of modality competition. Moreover, to counteract the performance degradation resulting from optimization drift among modalities, we propose a Multi-Modal Constrained (MMC) loss based on cosine similarity of complex feature phase and cross-entropy loss of individual modalities, guiding the optimization direction of the fusion network. Extensive experiments conducted on four multi-modal multimedia datasets and two task-specific multi-modal multimedia datasets demonstrate the superiority of our ERL-MR strategy over state-of-the-art baselines, achieving modality rebalancing and further performance improvements.

Dynamic facial expression recognition (DFER) is a rapidly developing field that focuses on recognizing facial expressions in video sequences. However, the complex temporal modeling caused by noisy frames, along with the limited training data significantly hinder the further development of DFER. Previous efforts in this domain have been limited as they tackled these issues separately. Inspired by recent advances of pretrained vision-language models (e.g., CLIP), we propose to leverage it to jointly address the two limitations in DFER. Since the raw CLIP model lacks the ability to model temporal relationships and determine the optimal task-related textual prompts, we utilize DFER-specific domain knowledge, including characteristics of temporal correlations and relationships between facial behavior descriptions at different levels, to guide the adaptation of CLIP to DFER. Specifically, we propose enhancements to CLIP's visual encoder through the design of a hierarchical video encoder that captures both short- and long-term temporal correlations in DFER. Meanwhile, we align facial expressions with action units through prior knowledge to construct semantically rich textual prompts, which are further enhanced with visual contents. Furthermore, we introduce a class-aware consistency regularization mechanism that adaptively filters out noisy frames, bolstering the model's robustness against interference. Extensive experiments on three in-the-wild dynamic facial expression datasets demonstrate that our method outperforms the state-of-the-art DFER approaches. The code is available at https://github.com/liliupeng28/DK-CLIP.

The 3D Gaussian Splatting (3D-GS) method has recently sparked a revolution in novel view synthesis with its remarkable visual effects and fast rendering speed. However, its reliance on simple spherical harmonics for color representation leads to subpar performance in complex scenes, particularly with effects like specular highlights and light refraction. Also, 3D-GS adopts a periodic split strategy, which significantly increases the model's disk space and hinders rendering efficiency. To tackle these challenges, we propose Gaussian Splatting with Neural Basis Extension (GSNB), a novel approach that substantially enhances the performance of 3D-GS in demanding scenes while reducing storage consumption. Drawing inspiration from basis function, GSNB utilizes a light-weight MLP to share feature coefficients with Spherical Harmonics (SH). This extends the color calculation of 3D Gaussians, resulting in more accurate visual effect modeling. This combination allows GSNB to achieve remarkable results even in scenes with challenging lighting and reflection conditions. Additionally, GSNB uses pre-computation to bake the MLP's output, thereby alleviating inference workload and subsequent speed loss. Furthermore, to leverage the capabilities of Neural Basis Extension and eliminate redundant Gaussians, we propose a new importance criterion to prune the converged Gaussian model and obtain a more compact representation through re-optimization. Our experimental results demonstrate that our method delivers high-quality rendering in most scenarios and effectively reduces redundant Gaussians without compromising rendering speed. The code is available at https://github.com/Dojizz/GSNB/.

Depression recognition based on physiological signals such as functional near-infrared spectroscopy (fNIRS) and electroencephalogram (EEG) has made considerable progress. However, most existing studies ignore the complementarity and semantic consistency of multimodal physiological signals under the same stimulation task in complex spatio-temporal patterns. In this paper, we introduce a multimodal physiological signals representation learning framework using Siamese architecture via multiscale contrasting for depression recognition (MRLMC). First, fNIRS and EEG are transformed into different but correlated data based on a time-domain data augmentation strategy. Then, we design a spatio-temporal contrasting module to learn the representation of fNIRS and EEG through weight-sharing multiscale spatio-temporal convolution. Furthermore, to enhance the learning of semantic representation associated with stimulation tasks, a semantic consistency contrast module is proposed, aiming to maximize the semantic similarity of fNIRS and EEG. Extensive experiments on publicly available and self-collected multimodal physiological signals datasets indicate that MRLMC outperforms the state-of-the-art models. Moreover, our proposed framework is capable of transferring to multimodal time series downstream tasks.

Few-shot open-set recognition (FSOR) is a challenging task that requires a model to recognize known classes and identify unknown classes with limited labeled data. Existing approaches, particularly Negative-Prototype-Based methods, generate negative prototypes based solely on known class data. However, as the unknown space is infinite while the known space is limited, these methods suffer from limited representation capability. To address this limitation, we propose a novel approach, termed Diversified Negative Prototypes Generator (DNPG), which adopts the principle of "learning unknowns from unknowns." Our method leverages the unknown space information learned from base classes to generate more representative negative prototypes for novel classes. During the pre-training phase, we learn the unknown space representation of the base classes. This representation, along with inter-class relationships, is then utilized in the meta-learning process to construct negative prototypes for novel classes. To prevent prototype collapse and ensure adaptability to varying data compositions, we introduce the Swap Alignment (SA) module. Our DNPG model, by learning from the unknown space, generates negative prototypes that cover a broader unknown space, thereby achieving state-of-the-art performance on three standard FSOR datasets. The repository of this project is available at https://github.com/iCGY96/DNPG.

The detection and localization of highly realistic deepfake audio-visual content are challenging even for the most advanced state-of-the-art methods. While most of the research efforts in this domain are focused on detecting high-quality deepfake images and videos, only a few works address the problem of the localization of small segments of audio-visual manipulations embedded in real videos. In this research, we emulate the process of such content generation and propose the AV-Deepfake1M dataset. The dataset contains content-driven (i) video manipulations, (ii) audio manipulations, and (iii) audio-visual manipulations for more than 2K subjects resulting in a total of more than 1M videos. The paper provides a thorough description of the proposed data generation pipeline accompanied by a rigorous analysis of the quality of the generated data. The comprehensive benchmark of the proposed dataset utilizing state-of-the-art deepfake detection and localization methods indicates a significant drop in performance compared to previous datasets. The proposed dataset will play a vital role in building the next-generation deepfake localization methods. The dataset and associated code are available at https://github.com/ControlNet/AV-Deepfake1M.

With the increasing spatial and temporal resolutions of obtained remote sensing (RS) images, effective compression becomes critical for storage, transmission, and large-scale in-memory processing. Although image compression methods achieve a series of breakthroughs for daily images, a straightforward application of these methods to RS domain underutilizes the properties of the RS images, such as content duplication, homogeneity, and temporal redundancy. This paper proposes a Spatial-Temporal Context model (STCM) for RS image compression, jointly leveraging context from a broader spatial scope and across different temporal images. Specifically, we propose a stacked diagonal masked module to expand the contextual reference scope, which is stackable and maintains its parallel capability. Furthermore, we propose spatial-temporal contextual adaptive coding to enable the entropy estimation to reference context across different temporal RS images at the same geographic location. Experiments show that our method outperforms previous state-of-the-art compression methods on rate-distortion (RD) performance. For downstream tasks validation, our method reduces the bitrate by 52 times for single temporal images in the scene classification task while maintaining accuracy.

In the Fourier frequency domain, luminance information is primarily encoded in the amplitude component, while spatial structure information is significantly contained within the phase component. Existing low-light image enhancement techniques using Fourier transform have mainly focused on amplifying the amplitude component and simply replicating the phase component, an approach that often leads to color distortions and noise issues. In this paper, we propose a Dual-Stage Multi-Branch Fourier Low-Light Image Enhancement (DMFourLLIE) framework to address these limitations by emphasizing the phase component's role in preserving image structure and detail. The first stage integrates structural information from infrared images to enhance the phase component and employs a luminance-attention mechanism in the luminance-chrominance color space to precisely control amplitude enhancement. The second stage combines multi-scale and Fourier convolutional branches for robust image reconstruction, effectively recovering spatial structures and textures. This dual-branch joint optimization process ensures that complex image information is retained, overcoming the limitations of previous methods that neglected the interplay between amplitude and phase. Extensive experiments across multiple datasets demonstrate that DMFourLLIE outperforms current state-of-the-art methods in low-light image enhancement.

Automated diagnosis of depression is crucial for early detection and timely intervention. Previous research has largely concentrated on visual information, often neglecting the value of leveraging a variety of data types. Although some studies have attempted to employ multiple modalities, they typically fall short in investigating the complex dynamics between features from various modalities over time. To address this challenge, we present an innovative Multi-modal Dual-Attention aggregation architecture for Depression Recognition (MDDR). This framework leverages multi-modal pre-trained features and introduces two attention aggregation mechanisms: the Feature Alignment and Aggregation (FAA) module and the Sequence Encoding and Aggregation (SEA) module. The FAA module is designed to dynamically evaluate the relevance of multi-modal features for each instance, facilitating a dynamic integration of these features over time. Following this, the SEA module determines the importance of the amalgamated features for each frame, ensuring that aggregation is conducted based on their significance, to extract the most relevant features for accurately diagnosing depression. Moreover, we propose a unique loss calculation method specifically designed for depression assessment, named DR Loss. Our approach, evaluated on the AVEC2013 and AVEC2014 depression audiovisual datasets, achieves unparalleled performance.

Deep Convolutional Neural Networks (CNNs) have demonstrated excellent performance in various multimedia application scenarios. However, complex models often require significant computational resources and energy costs. Therefore, CNN compression is crucial for addressing deployment challenges of multimedia application on resource constrained edge devices. However, existing CNN channel pruning strategies primarily focus on the "weights" or "activations" of the model, overlooking its "interpretability" information. In this paper, we explore CNN pruning strategies from the perspective of model interpretability. We model the correspondence between channel feature maps and interpretable visual perception based on class saliency maps, aiming to assess the contribution of each channel to the desired output. Additionally, we utilize Discrete Wavelet Transform (DWT) to capture the global features and structure of class saliency maps. Based on this, we propose a Channel Spatial Dependability (CSD) metric, evaluating the importance and contribution of channels in a bidirectional manner to guide model pruning. And we dynamically adjust the pruning rate of each layer based on performance changes, in order to achieve more accurate and efficient adaptive pruning. Our method achieves significant results across a range of different networks and datasets. For instance, we achieved a 51.3% pruning on the ResNet-56 model while maintaining an accuracy of 94.16%, outperforming feature-map or other State-of-the-Art (SOTA).

Multiple Instance Learning (MIL) represents the predominant framework in Whole Slide Image (WSI) classification, covering aspects such as sub-typing, diagnosis, and beyond. Current MIL models predominantly rely on instance-level features derived from pretrained models such as ResNet. These models segment each WSI into independent patches and extract features from these local patches, leading to a significant loss of global spatial context and restricting the model's focus to merely local features. To address this issue, we propose a novel MIL framework, named SAM-MIL, that emphasizes spatial contextual awareness and explicitly incorporates spatial context by extracting comprehensive, image-level information. The Segment Anything Model (SAM) represents a pioneering visual segmentation foundational model that can capture segmentation features without the need for additional fine-tuning, rendering it an outstanding tool for extracting spatial context directly from raw WSIs. Our approach includes the design of group feature extraction based on spatial context and a SAM-Guided Group Masking strategy to mitigate class imbalance issues. We implement a dynamic mask ratio for different segmentation categories and supplement these with representative group features of categories. Moreover, SAM-MIL divides instances to generate additional pseudo-bags, thereby augmenting the training set, and introduces consistency of spatial context across pseudo-bags to further enhance the model's performance. Experimental results on the CAMELYON-16 and TCGA Lung Cancer datasets demonstrate that our proposed SAM-MIL model outperforms existing mainstream methods in WSIs classification. Our open-source implementation code is is available at https://github.com/FangHeng/SAM-MIL.

Point clouds represent one of the prevalent formats for 3D content. Distortions introduced at various stages in the point cloud processing pipeline affect the visual quality, altering their geometric composition, texture information, or both. Understanding and quantifying the impact of the distortion domain on visual quality is vital to driving rate optimization and guiding post-processing steps to improve the quality of experience. In this paper, we propose a multi-task guided multi-modality no reference metric (M3-Unity), which utilizes 4 types of modalities across attributes and dimensionalities to represent point clouds. An attention mechanism establishes inter/intra associations among 3D/2D patches, which can complement each other, yielding local and global features, to fit the highly nonlinear property of the human vision system. A multi-task decoder involving distortion type classification selects the best association among 4 modalities, aiding the regression task and enabling the in-depth analysis of the interplay between geometrical and textural distortions. Furthermore, our framework design and attention strategy enable us to measure the impact of individual attributes and their combinations, providing insights into how these associations contribute particularly in relation to distortion type. Extensive experimental results on 4 datasets consistently outperform the state-of-the-art metrics by a large margin. The code is available at https://github.com/cwi-dis/ACMMM2024-Oral.

Expressive Human Mesh Recovery (HMR) involves reconstructing the 3D human body, including hands and face, from RGB images. It is difficult because humans are highly deformable, and hands are small and frequently occluded. Recent approaches have attempted to mitigate these issues using large datasets and models, but these solutions remain imperfect. Specifically, whole-body estimation models often inaccurately estimate hand poses, while hand expert models struggle with severe occlusions. To overcome these limitations, we introduce a dual-path cross augmentation framework with a novel adaptation approach called HMR-Adapter that enhances existing large HMR models. HMR-Adapter significantly improves expressive HMR performance by injecting additional guidance from other body parts. This approach refines hand pose predictions by incorporating body pose information and uses additional hand features to enhance body pose estimation in whole-body models. Remarkably, an HMR-Adapter with about 30M parameters significantly improves expressive HMR results by combining the adapted large whole-body and hand expert models. We show extensive experiments and analysis to demonstrate the efficacy of our method.

Image descriptions provide precious information for a myriad of visual media management tasks ranging from image classification to image search. The value of such curated collections comes from their diverse content and their accompanying extensive annotations. Such annotations are typically supplied by communities, where users (often volunteers) curate labels and/or descriptions of images. Supporting users in their quest to increase (overall) description completeness where possible is, therefore, of utmost importance.