ACM MM 2024 Papers

Cartoon animal parsing aims to segment the body parts such as heads, arms, legs and tails of cartoon animals. Different from previous parsing tasks, cartoon animal parsing faces new challenges, including irregular body structures, abstract drawing styles and diverse animal categories. Existing methods have difficulties when addressing these challenges caused by the spatial and structural properties of cartoon animals. To address these challenges, a novel spatial learning and structural modeling network, named CAPNet, is proposed for cartoon animal parsing. It aims to address the critical problems of spatial perception, structure modeling and spatial-structural consistency learning. A spatial-aware learning module integrates deformable convolutions to learn spatial features of diverse cartoon animals. The multi-task edge and center point prediction mechanism is incorporated to capture the intricate spatial patterns. A structural modeling method is proposed to model the complex structural representations of cartoon animals, which integrates a graph neural network with a shape-aware relation learning module. To mitigate the significant differences among animals, a spatial and structural consistency learning strategy is proposed to capture and learn feature correlations across different animal species. Extensive experiments conducted on benchmark datasets demonstrate the effectiveness of the proposed approach, which outperforms the state-of-the-art methods.

Embodied intelligence empowers agents with a profound sense of perception, enabling them to respond in a manner closely aligned with real-world situations. Large Language Models (LLMs) delve into language instructions with depth, serving a crucial role in generating plans for intricate tasks. Thus, LLM-based embodied models further enhance the agent's capacity to comprehend and process information. However, this amalgamation also ushers in new challenges in the pursuit of heightened intelligence. Specifically, attackers can manipulate LLMs to produce irrelevant or even malicious outputs by altering their prompts. Confronted with this challenge, we observe a notable absence of multi-modal datasets essential for comprehensively evaluating the robustness of LLM-based embodied models. Consequently, we construct the Embodied Intelligent Robot Attack Dataset (EIRAD), tailored specifically for robustness evaluation. Additionally, two attack strategies are devised, including untargeted attacks and targeted attacks, to effectively simulate a range of diverse attack scenarios. At the same time, during the attack process, to more accurately ascertain whether our method is successful in attacking the LLM-based embodied model, we devise a new attack success evaluation method utilizing the BLIP2 model. Recognizing the time and cost-intensive nature of the GCG algorithm in attacks, we devise a scheme for prompt suffix initialization based on various target tasks, thus expediting the convergence process. Experimental results demonstrate that our method exhibits a superior attack success rate when targeting LLM-based embodied models, indicating a lower level of decision-level robustness in these models.

AI-generated video has revolutionized short video production, filmmaking, and personalized media, making video local editing an essential tool. However, this progress also blurs the line between reality and fiction, posing challenges in multimedia forensics. To solve this urgent issue, V2A-Mark is proposed to address the limitations of current video tampering forensics, such as poor generalizability, singular function, and single modality focus. Combining the fragility of video-into-video steganography with deep robust watermarking, our method can embed invisible visual-audio localization watermarks and copyright watermarks into the original video frames and audio, enabling precise manipulation localization and copyright protection. We also design a temporal alignment and fusion module and degradation prompt learning to enhance the localization accuracy and decoding robustness. Meanwhile, we introduce a sample-level audio localization method and a cross-modal copyright extraction mechanism to couple the information of audio and video frames. The effectiveness of V2A-Mark has been verified on a visual-audio tampering dataset, emphasizing its superiority in localization precision and copyright accuracy, crucial for the sustainable development of video editing in the AIGC video era.

The rapid advancement of deepfake technology poses significant threats to social trust. Although recent deepfake detectors have exhibited promising results on deepfakes of the same type as those present in training, their effectiveness degrades significantly on novel deepfakes crafted by unseen algorithms due to the gap in forgery patterns. Some studies have enhanced detectors by adapting to the continuously emerging deepfakes through incremental learning. Despite the progress, they overlooked the scarcity of novel samples that can easily lead to insufficient learning of forgery patterns. To mitigate this issue, we introduce the Dynamic Mixed-Prototype (DMP) model, which dynamically increases prototypes to adapt to novel deepfakes efficiently. Specifically, the DMP model adopts multiple prototypes to represent both real and fake classes, enabling learning novel patterns by expanding prototypes and jointly retaining knowledge learned in previous prototypes. Furthermore, we propose the Prototype-Guided Replay strategy and Prototype Representation Distillation loss, both of which effectively prevent forgetting learned knowledge based on the prototypical representation of samples. Our method surpasses existing incremental deepfake detectors across four datasets and can generalize to novel deepfakes by learning limited deepfake samples.

Panoramic activity recognition is a comprehensive yet challenging task in crowd scene understanding, which aims to concurrently identify multi-grained human behaviors, including individual actions, social group activities, and global activities. Previous studies tend to capture cross-granularity activity-semantics relations from solely the video input, thus ignoring the intrinsic semantic hierarchy in label-text space. To this end, we propose a label text-aided hierarchical semantics mining (THSM) framework, which explores multi-level cross-modal associations by learning hierarchical semantic alignment between visual content and label texts. Specifically, a hierarchical encoder is first constructed to encode the visual and text inputs into semantics-aligned representations at different granularities. To fully exploit the cross-modal semantic correspondence learned by the encoder, a hierarchical decoder is further developed, which progressively integrates the lower-level representations with the higher-level contextual knowledge for coarse-to-fine action/activity recognition. Extensive experimental results on the public JRDB-PAR benchmark validate the superiority of the proposed THSM framework over state-of-the-art methods.

Universal few-shot dense prediction requires a versatile model capable of learning any dense prediction task from limited labeled images, which necessitates the model to possess efficient adaptation abilities. Prevailing few-shot learning methods rely on efficient fine-tuning of model weights for few-shot adaptation, which carries the risk of disrupting the pre-trained knowledge and lacks the capability to extract task-specific knowledge contained in the pre-trained model. To overcome these limitations, our paper approaches universal few-shot dense prediction from a novel perspective. Unlike conventional fine-tuning techniques that use all model parameters and modify a specific set of weights for few-shot adaptation, our method focuses on selecting task-relevant computation pathways of the pre-trained model while keeping the model weights frozen. Building upon this idea, we introduce a novel framework UniDense for universal few-shot dense prediction. First, we construct a versatile MoE (Mixture of Experts) architecture for dense prediction based on the Stable Diffusion model. We then utilize episodes-based meta-learning to train a set of routers for this MoE model, called Meta-Routers, which act as hyper-networks responsible for selecting computation blocks relevant to each task. We demonstrate that fine-tuning these meta-routers enables efficient few-shot adaptation of the entire model. Moreover, for each few-shot task, we leverage support samples to extract a task embedding, which serves as a conditioning factor for meta-routers. This strategy allows meta-routers to dynamically adapt themselves for different few-shot task, leading to improved adaptation performance. Experiments on a challenging variant of Taskonomy dataset with 10 dense prediction tasks demonstrate the superiority of our approach.

E-commerce has emerged as a significant endeavour in which technological advancements influence the shopping experience. Simultaneously, the metaverse is the next breakthrough to transform multimedia engagement. However, under such situations, deceiving designs aimed at deceiving users into making desired choices might be more successful. This paper proposes the design space of manipulative techniques in e-commerce applications for the metaverse. We construct our arguments by evaluating user interaction with manipulative design in metaverse shopping experiences, followed by a survey among users to understand the effect of counteracting manipulative e-commerce scenarios. Our findings can understanding of design guidelines according to metaverse e-commerce experiences and the possibility of opportunities to improve user awareness of manipulative experiences. © 2024 ACM.

While generative models have proved successful in many domains, they may pose a privacy leakage risk in practical deployment. To address this issue, differentially private generative model learning has emerged as a solution to train private generative models for different downstream tasks. However, existing private generative modeling approaches face significant challenges in generating high-dimensional data due to the inherent complexity involved in modeling such data. In this work, we present a new private generative modeling approach where samples are generated via Hamiltonian dynamics with gradients of the private dataset estimated by a well-trained network. In the approach, we achieve differential privacy by perturbing the projection vectors in the estimation of gradients with sliced score matching. In addition, we enhance the reconstruction ability of the model by incorporating a residual enhancement module during the score matching. For sampling, we perform Hamiltonian dynamics with gradients estimated by the well-trained network, allowing the sampled data close to the private dataset's manifold step by step. In this way, our model is able to generate data with a resolution of 256×256. Extensive experiments and analysis clearly demonstrate the effectiveness and rationality of the proposed approach.

Non-Fungible Tokens (NFTs) have emerged as a pivotal digital asset, offering authenticated ownership of unique digital content. Despite it has gained remarkable traction, yet face pressing storage and verification challenges stemming from blockchain's permanent data costs. Existing off-chain or centralized storage solutions, while being alternatives, also introduce notable security vulnerabilities. We present SemNFT, an innovative decentralized framework integrated with blockchain oracle middleware services, addressing these persistent NFT dilemmas. Our approach compresses NFT source data into compact embeddings encapsulating semantic essence. These arrays are stored on-chain, while facilitating reliable decentralized image reconstruction and ownership verification. We implemented ERC721-compliant smart contracts with supplementary functionalities, demonstrating SemNFT's seamless integrative capabilities within the ecosystem. Extensive evaluations evidence marked storage optimizations and preservation of requisite visual fidelity by comparison with existing solutions. The proposed SemNFT framework marks a significant advancement in holistically confronting rising NFT storage and verification challenges without compromising decentralization. It substantively propels the meaningful evolution of NFT infrastructure to achieve digital asset immortality.

Spiking neural networks (SNNs) have garnered significant attention for their low power consumption and high biological interpretability. Their rich spatio-temporal information processing capability and event-driven nature make them ideally well-suited for neuromorphic datasets. However, current SNNs struggle to balance accuracy and latency in classifying these datasets. In this paper, we propose Hybrid Step-wise Distillation (HSD) method, tailored for neuromorphic datasets, to mitigate the notable decline in performance at lower time steps. Our work disentangles the dependency between the number of event frames and the time steps of SNNs, utilizing more event frames during the training stage to improve performance, while using fewer event frames during the inference stage to reduce latency. Nevertheless, the average output of SNNs across all time steps is susceptible to individual time step with abnormal outputs, particularly at extremely low time steps. To tackle this issue, we implement Step-wise Knowledge Distillation (SKD) module that considers variations in the output distribution of SNNs at each time step. Empirical evidence demonstrates that our method yields competitive performance in classification tasks on neuromorphic datasets, especially at lower time steps. Our code will be available at: https://github.com/hsw0929/HSD.

This paper introduces HINER, a novel neural representation for compressing HSI and ensuring high-quality downstream tasks on compressed HSI. HINER fully exploits inter-spectral correlations by explicitly encoding of spectral wavelengths and achieves a compact representation of the input HSI sample through joint optimization with a learnable decoder. By additionally incorporating the Content Angle Mapper with the L1 loss, we can supervise the global and local information within each spectral band, thereby enhancing the overall reconstruction quality. For downstream classification on compressed HSI, we theoretically demonstrate the task accuracy is not only related to the classification loss but also to the reconstruction fidelity through a first-order expansion of the accuracy degradation, and accordingly adapt the reconstruction by introducing Adaptive Spectral Weighting. Owing to the monotonic mapping of HINER between wavelengths and spectral bands, we propose Implicit Spectral Interpolation for data augmentation by adding random variables to input wavelengths during classification model training. Experimental results on various HSI datasets demonstrate the superior compression performance of our HINER compared to the existing learned methods and also the traditional codecs. Our model is lightweight and computationally efficient, which maintains high accuracy for downstream classification task even on decoded HSIs at high compression ratios. Our materials will be released at https://github.com/Eric-qi/HINER.

Talking Face Generation (TFG) reconstructs facial motions concerning lips given speech input, which aims to generate highquality, synchronized, and lip-readable videos. Previous efforts have achieved success in generating quality and synchronization, and recently, there has been an increasing focus on the importance of intelligibility. Despite these efforts, there remains a challenge in achieving a balance among quality, synchronization, and intelligibility, often resulting in trade-offs that compromise one aspect in favor of another. In light of this, we propose SyncTalklip, a novel dual-tower framework designed to overcome the challenges of synchronization while improving lip-reading performance. To enhance the performance of SyncTalklip in both synchronization and intelligibility, we design AV-SyncNet, a pre-trained multi-task model, aiming to achieve a dual-focus on synchronization and intelligibility. Moreover, we propose a novel cross-modal contrastive learning bringing audio and video closer to enhance synchronization. Experimental results demonstrate that SyncTalklip achieves state-of-the-art performance in quality, intelligibility, and synchronization. Furthermore, extensive experiments have demonstrated our model's generalizability across domains. The code and demo is available at https://sync-talklip.github.io.

In multi-modal classification tasks, a good fusion algorithm can effectively integrate and process multi-modal data, thereby significantly improving its performance. Researchers often focus on the design of complex fusion operators and have proposed numerous fusion operators, while paying less attention to the design of feature fusion usage, specifically how features should be fused to better facilitate multi-modal classification tasks. In this article, we propose a progressive skip reasoning fusion network (PSRFN) to make some attempts to address this issue. Firstly, unlike most existing multi-modal fusion methods that only use one fusion operator in a single stage to fuse all view features, PSRFN utilizes the progressive skip reasoning (PSR) block to fuse all views with a fusion operator at each layer. Specifically, each PSR block utilizes all view features and the fused features from the previous layer to jointly obtain the fused features for the current layer. Secondly, each PSR block utilizes a dual-weighted fusion strategy with learnable parameters to adaptively allocate weights during the fusion process. The first level of weighting assigns weights to each view feature, while the second level assigns weights to the fused features from the previous layer and the fused features obtained from the first level of weighting in the current layer. This strategy ensures that the PSR block can dynamically adjust the weights based on the actual contribution of features. Finally, to enable the model to fully utilize feature information from different levels for feature fusion, the skip connections are adopted between PSR blocks. Extensive experiment results on six real multi-modal datasets show that a better usage for fusion operator is indeed able to improve performance.

The rapid development of Vision Foundation Model (VFM) brings inherent out-domain generalization for a variety of down-stream tasks. Among them, domain generalized semantic segmentation (DGSS) holds unique challenges as the cross-domain images share common pixel-wise content information but vary greatly in terms of the style. In this paper, we present a novel Spectral-dEcomposed Token (SET) learning framework to advance the frontier. Delving into further than existing fine-tuning token & frozen backbone paradigm, the proposed SET especially focuses on the way learning style-invariant features from these learnable tokens. Particularly, the frozen VFM features are first decomposed into the phase and amplitude components in the frequency space, which mainly contain the information of content and style, respectively, and then separately processed by learnable tokens for task-specific information extraction. Particularly, the frozen VFM features are first decomposed into the phase and amplitude components in the frequency space, which mainly contain the information of content and style, respectively, and then separately processed by learnable tokens for task-specific information extraction.After the decomposition, style variation primarily impacts the token-based feature enhancement within the amplitude branch. To address this issue, we further develop an attention optimization method to bridge the gap between style-affected representation and static tokens during inference. Extensive cross-domain experiments show its state-of-the-art performance.

Binarized Vision Transformers (BiViTs) aim to facilitate the efficient and lightweight utilization of Vision Transformers (ViTs) on devices with limited computational resources. Yet, the current approach to binarizing ViT leads to a substantial performance decrease compared to the full-precision model, posing obstacles to practical deployment. By empirical study, we reveal that spatial interaction (SI) is a critical factor that impacts performance due to lack of token-level correlation, but previous work ignores this factor. To this end, we design a ViT binarization approach dubbed SI-BiViT to incorporate spatial interaction in the binarization process. Specifically, an SI module is placed alongside the Multi-Layer Perceptron (MLP) module to formulate the dual-branch structure. This structure not only leverages knowledge from pre-trained ViTs by distilling over the original MLP, but also enhances spatial interaction via the introduced SI module. Correspondingly, we design a decoupled training strategy to train these two branches more effectively. Importantly, our SI-BiViT is orthogonal to existing Binarized ViTs approaches and can be directly plugged. Extensive experiments demonstrate the strong flexibility and effectiveness of SI-BiViT by plugging our method into four classic ViT backbones in supporting three downstream tasks, including classification, detection, and segmentation. In particular, SI-BiViT enhances the classification performance of binarized ViTs by an average of 10.52% in Top-1 accuracy compared to the previous state-of-the-art. Codes are available at https://github.com/VL-Group/SI-BiViT

Weakly-supervised Temporal Action Localization (WTAL) following a localization-by-classification paradigm has achieved significant results, yet still grapples with confounding arising from ambiguous snippets. Previous works have attempted to distinguish these ambiguous snippets from action snippets without investigating the underlying causes of their formation, thus failing to effectively eliminate the bias on both action-context and action-content. In this paper, we revisit WTAL from the perspective of structural causal model to identify the true origins of confounding, and propose an efficient dual-confounding eliminating framework to alleviate these biases. Specifically, we construct a Substituted Confounder Set (SCS) to eliminate the confounding bias on action-context by leveraging the modal disparity between RGB and FLOW. Then, a Multi-level Consistency Mining (MCM) method is designed to mitigate the confounding bias on action-content by utilizing the consistency between discriminative snippets and corresponding proposals at both the feature and label levels. Notably, SCS and MCM could be seamlessly integrated into any two-stream models without additional parameters by Expectation-Maximization (EM) algorithm. Extensive experiments on two challenging benchmarks including THUMOS14 and ActivityNet-1.2 demonstrate the superior performance of our method.

Recent advancements in machine learning have fueled research on multimodal tasks, such as for instance text-to-video and text-to-audio retrieval. These tasks require models to understand the semantic content of video and audio data, including objects, and characters. The models also need to learn spatial arrangements and temporal relationships. In this work, we analyse the temporal ordering of sounds, which is an understudied problem in the context of text-to-audio retrieval. In particular, we dissect the temporal understanding capabilities of a state-of-the-art model for text-to-audio retrieval on the AudioCaps and Clotho datasets. Additionally, we introduce a synthetic text-audio dataset that provides a controlled setting for evaluating temporal capabilities of recent models. Lastly, we present a loss function that encourages text-audio models to focus on the temporal ordering of events. Code and data are available at https://github.com/oncescuandreea/DTU_text_audio.

Facial action units (AUs), as defined in the Facial Action Coding System (FACS), have received significant research interest owing to their diverse range of applications in facial state analysis. Current mainstream FAU recognition models have a notable limitation, i.e., focusing only on the accuracy of AU recognition and overlooking explanations of corresponding AU states. In this paper, we propose an end-to-end Vision-Language joint learning network for explainable FAU recognition (termed VL-FAU), which aims to reinforce AU representation capability and language interpretability through the integration of joint multimodal tasks. Specifically, VL-FAU brings together language models to generate fine-grained local muscle descriptions and distinguishable global face description when optimising FAU recognition. Through this, the global facial representation and its local AU representations will achieve higher distinguishability among different AUs and different subjects. In addition, multi-level AU representation learning is utilised to improve AU individual attention-aware representation capabilities based on multi-scale combined facial stem feature. Extensive experiments on DISFA and BP4D AU datasets show that the proposed approach achieves superior performance over the state-of-the-art methods on most of the metrics. In addition, compared with mainstream FAU recognition methods, VL-FAU can provide local- and global-level interpretability language descriptions with the AUs' predictions.