ACM MM 2024 Papers

The fusion of images from dual camera systems featuring a wide-angle and a telephoto camera has become a hotspot problem recently. By integrating simultaneously captured wide-angle and telephoto images from these systems, the resulting fused image achieves a wide field of view (FOV) coupled with high-definition quality. Existing approaches are mostly deep learning methods, and predominantly rely on supervised learning, where the training dataset plays a pivotal role. However, current datasets typically adopt a data synthesis approach, where the wide-angle inputs are synthesized rather than captured using real wide-angle cameras, and the ground-truth image is captured by wide-angle cameras whose quality is substantially lower than that of input telephoto images captured by telephoto cameras. To address these limitations, we introduce a novel hardware setup utilizing a beam splitter to simultaneously capture three images, i.e. input pairs and ground-truth images, from two authentic cellphones equipped with wide-angle and telephoto dual cameras. Specifically, the wide-angle and telephoto images captured by cellphone 2 serve as the input pair, while the telephoto image captured by cellphone 1, which is calibrated to match the optical path of the wide-angle image from cellphone 2, serves as the ground-truth image, maintaining quality on par with the input telephoto image. Experiments validate the efficacy of our newly introduced dataset, named ReWiTe, which can significantly enhance the performance of various existing methods for the real-world wide-angle and telephoto dual image fusion task.

Traditional deep neural network (DNN)-based image quality assessment (IQA) models leverage convolutional neural networks (CNN) or Transformer to learn the quality-aware feature representation, achieving commendable performance on natural scene images. However, when applied to AI-Generated images (AGIs), these DNN-based IQA models exhibit subpar performance. This situation is largely due to the semantic inaccuracies inherent in certain AGIs caused by uncontrollable nature of the generation process. Thus, the capability to discern semantic content becomes crucial for assessing the quality of AGIs. Traditional DNN-based IQA models, constrained by limited parameter complexity and training data, struggle to capture complex fine-grained semantic features, making it challenging to grasp the existence and coherence of semantic content of the entire image. To address the shortfall in semantic content perception of current IQA models, we introduce a large Multi-modality model Assisted AI-Generated Image Quality Assessment (MA-AGIQA) model, which utilizes semantically informed guidance to sense semantic information and extract semantic vectors through carefully designed text prompts. Moreover, it employs a mixture of experts (MoE) structure to dynamically integrate the semantic information with the quality-aware features extracted by traditional DNN-based IQA models. Comprehensive experiments conducted on two AI-generated content datasets and two traditional IQA datasets show that MA-AGIQA achieves state-of-the-art performance, and demonstrate its superior generalization capabilities on assessing the quality of AGIs. The code is available at https://github.com/wangpuyi/MA-AGIQA.

In the mobile internet era, short videos are inundating people's lives. However, research on visual language models specifically designed for short videos has not yet received sufficient attention. Short videos are not just videos of limited duration. The prominent visual details and high information density of short videos differentiate them to long videos. In this paper, we propose the SpatioTemporal Fine-grained Description (STFVD) emphasizing on the uniqueness of short videos, which entails capturing the intricate details of the main subject and fine-grained movements. To this end, we create a comprehensive Short Video Advertisements Description (SVAD) dataset, comprising 34,930 clips from 5,046 videos. The dataset covers a range of topics, including 191 sub-industries, 649 popular products, and 470 trending games. Various efforts have been made in the data annotation process to ensure the inclusion of fine-grained spatiotemporal information, resulting in 34,930 high-quality annotations. Compared to existing datasets, samples in SVAD exhibit a superior text information density, suggesting that SVAD is more appropriate for the analysis of short videos. Based on the SVAD dataset, we develop a visual language model (SVAD-VLM) to generate spatiotemporal fine-grained description for short videos. We use a prompt-guided keyword generation task to efficiently learn key visual information. Moreover, we also utilize dual visual alignment to exploit the advantage of mixed-datasets training. Experiments on SVAD dataset demonstrate the challenge of STFVD and the competitive performance of proposed method compared to previous ones.

With Vision-Language Pre-training (VLP) models demonstrating powerful multimodal interaction capabilities, the application scenarios of neural networks are no longer confined to unimodal domains but have expanded to more complex multimodal V+L downstream tasks. The security vulnerabilities of unimodal models have been extensively examined, whereas those of VLP models remain challenging. We note that in CV models, the understanding of images comes from annotated information, while VLP models are designed to learn image representations directly from raw text. Motivated by this discrepancy, we developed the Feature Guidance Attack (FGA), a novel method that uses text representations to direct the perturbation of clean images, resulting in the generation of adversarial images. FGA is orthogonal to many advanced attack strategies in the unimodal domain, facilitating the direct application of rich research findings from the unimodal to the multimodal scenario. By appropriately introducing text attack into FGA, we construct Feature Guidance with Text Attack (FGA-T). Through the interaction of attacking two modalities, FGA-T achieves superior attack effects against VLP models. Moreover, incorporating data augmentation and momentum mechanisms significantly improves the black-box transferability of FGA-T. Our method demonstrates stable and effective attack capabilities across various datasets, downstream tasks, and both black-box and white-box settings, offering a unified baseline for exploring the robustness of VLP models.

The prevalence of multimedia applications has led to increased concerns and demand for auto face retouching. Face retouching aims to enhance portrait quality by removing blemishes. However, the existing auto-retouching methods rely heavily on a large amount of paired training samples, and perform less satisfactorily when handling complex and unusual blemishes. To address this issue, we propose a Language-guided Blemish Removal Transformer for automatically retouching face images, while at the same time reducing the dependency of the model on paired training data. Our model is referred to as LangBRT, which leverages vision-language pre-training for precise facial blemish removal. Specifically, we design a text-prompted blemish detection module that indicates the regions to be edited. The priors not only enable the transformer network to handle specific blemishes in certain areas, but also reduce the reliance on retouching training data. Further, we adopt a target-aware cross attention mechanism, such that the blemish-like regions are edited accurately while at the same time maintaining the normal skin regions unchanged. Finally, we adopt a regularization approach to encourage the semantic consistency between the synthesized image and the text description of the desired retouching outcome. Extensive experiments are performed to demonstrate the superior performance of LangBRT over competing auto-retouching methods in terms of dependency on training data, blemish detection accuracy and synthesis quality.

The outdoor vision systems are frequently contaminated by rain streaks and raindrops, which significantly degenerate the performance of visual tasks and multimedia applications. The nature of videos exhibits redundant temporal cues for rain removal with higher stability. Traditional video deraining methods heavily rely on optical flow estimation and kernel-based manners, which have a limited receptive field. Yet, transformer architectures, while enabling long-term dependencies, bring about a significant increase in computational complexity. Recently, the linear-complexity operator of the state space models (SSMs) has contrarily facilitated efficient long-term temporal modeling, which is crucial for rain streaks and raindrops removal in videos. Unexpectedly, its uni-dimensional sequential process on videos destroys the local correlations across the spatio-temporal dimension by distancing adjacent pixels. To address this, we present an improved SSMs-based video deraining network (RainMamba) with a novel Hilbert scanning mechanism to better capture sequence-level local information. We also introduce a difference-guided dynamic contrastive locality learning strategy to enhance the patch-level self-similarity learning ability of the proposed network. Extensive experiments on four synthesized video deraining datasets and real-world rainy videos demonstrate the superiority of our network in the removal of rain streaks and raindrops. Our code and results are available at https://github.com/TonyHongtaoWu/RainMamba.

We proposed Precomputed Radiance Transfer of Gaussian Splats (PRTGS), a real-time high-quality relighting method for Gaussian splats in low-frequency lighting environments that captures soft shadows and interreflections by precomputing 3D Gaussian splats' radiance transfer. Existing studies have demonstrated that 3D Gaussian splatting (3DGS) outperforms neural fields in efficiency for dynamic lighting scenarios. However, the current relighting method based on 3DGS is still struggling to compute high-quality shadow and indirect illumination in real time for dynamic light, leading to unrealistic rendering results. We solve this problem by precomputing the expensive transport simulations required for complex transfer functions like shadowing, the resulting transfer functions are represented as dense sets of vectors or matrices for every Gaussian splat. We introduce distinct precomputing methods tailored for training and rendering stages, along with unique ray tracing and indirect lighting precomputation techniques for 3D Gaussian splats to accelerate training speed and compute accurate indirect lighting related to environment light. Experimental analyses demonstrate that our approach achieves state-of-the-art visual quality while maintaining competitive training times and importantly allows high-quality real-time (30+ fps) relighting for dynamic light and relatively complex scenes at 1080p resolution.

In the domain of multimedia and multimodal processing, the efficient handling of diverse data streams such as images, video, and sensor data is paramount. Model compression and multitask learning (MTL) are crucial in this field, offering the potential to address the resource-intensive demands of processing and interpreting multiple forms of media simultaneously. However, effectively compressing a multitask model presents significant challenges due to the complexities of balancing sparsity allocation and accuracy performance across multiple tasks. To tackle these challenges, we propose AdapMTL, an adaptive pruning framework for MTL models. AdapMTL leverages multiple learnable soft thresholds independently assigned to the shared backbone and the task-specific heads to capture the nuances in different components' sensitivity to pruning. During training, it co-optimizes the soft thresholds and MTL model weights to automatically determine the suitable sparsity level at each component to achieve both high task accuracy and high overall sparsity. It further incorporates an adaptive weighting mechanism that dynamically adjusts the importance of task-specific losses based on each task's robustness to pruning. We demonstrate the effectiveness of AdapMTL through comprehensive experiments on popular multitask datasets, namely NYU-v2 and Tiny-Taskonomy, with different architectures, showcasing superior performance compared to state-of-the-art pruning methods.

Recent advancements in Large Vision-Language Models (VLMs) have underscored their superiority in various multimodal tasks. However, the adversarial robustness of VLMs has not been fully explored. Existing methods mainly assess robustness through unimodal adversarial attacks that perturb images, while assuming inherent resilience against text-based attacks. Different from existing attacks, in this work we propose a more comprehensive strategy that jointly attacks both text and image modalities to exploit a broader spectrum of vulnerability within VLMs. Specifically, we propose a dual optimization objective aimed at guiding the model to generate highly toxic affirmative responses. Our attack method begins by optimizing an adversarial image prefix from random noise to generate diverse harmful responses in the absence of text input, thus imbuing the image with toxic semantics. Subsequently, an adversarial text suffix is integrated and co-optimized with the adversarial image prefix to maximize the probability of eliciting affirmative responses to various harmful instructions. The discovered adversarial image prefix and text suffix are collectively denoted as a Universal Master Key (UMK). When integrated into various malicious queries, UMK can circumvent the alignment defenses of VLMs and lead to the generation of objectionable content, known as jailbreaks. The experimental results demonstrate that our universal attack strategy can effectively jailbreak MiniGPT-4 with a 96% success rate, highlighting the fragility of VLMs and the exigency for new alignment strategies. Codes are available at https://github.com/roywang021/UMK. Disclaimer: This paper contains potentially disturbing and offensive content.

Deep learning-based lane detection (LD) plays a critical role in autonomous driving systems, such as adaptive cruise control. However, it is vulnerable to backdoor attacks. Existing backdoor attack methods on LD exhibit limited effectiveness in dynamic real-world scenarios, primarily because they fail to consider dynamic scene factors, including changes in driving perspectives (e.g., viewpoint transformations) and environmental conditions (e.g., weather or lighting changes). To tackle this issue, this paper introduces BadLANE, a dynamic scene adaptation backdoor attack for LD designed to withstand changes in real-world dynamic scene factors. To address the challenges posed by changing driving perspectives, we propose an amorphous trigger pattern composed of shapeless pixels. This trigger design allows the backdoor to be activated by various forms or shapes of mud spots or pollution on the road or lens, enabling adaptation to changes in vehicle observation viewpoints during driving. To mitigate the effects of environmental changes, we design a meta-learning framework to train meta-generators tailored to different environmental conditions. These generators produce meta-triggers that incorporate diverse environmental information, such as weather or lighting conditions, as the initialization of the trigger patterns for backdoor implantation, thus enabling adaptation to dynamic environments. Extensive experiments on various commonly used LD models in both digital and physical domains validate the effectiveness of our attacks, outperforming other baselines significantly (+25.15% on average in Attack Success Rate). Our codes can be found in https://github.com/Veee9/BadLANE.

Weak diagram analysis abilities of LLMs or Multimodal LLMs greatly limit their application scenarios for scientific academic paper writing. In this work, towards a more versatile copilot for academic paper writing, we mainly focus on strengthening the multi-modal diagram analysis ability of Multimodal LLMs. By parsing Latex source files of academic papers, we carefully build a multi-modal diagram understanding dataset M-Paper. By aligning diagrams in the paper with related paragraphs, we construct professional diagram analysis samples for training and evaluation. M-Paper is the first dataset to support joint comprehension of multiple scientific diagrams, including figures and tables in the format of images or Latex codes. Besides, to better align the copilot with the user's intention, we introduce the 'outline' as the control signal, which could be directly given by the user or revised based on auto-generated ones. Comprehensive experiments with a state-of-the-art Multimodal LLM demonstrate that training on our dataset shows stronger scientific diagram understanding performance. The dataset, code, and model are publicly available at https://github.com/X-PLUG/mPLUG-DocOwl/tree/main/PaperOwl.

Video frame interpolation is a critical component of video streaming, a vibrant research area dealing with requests of both service providers and users. However, existing methods cannot handle changing video resolutions while improving user perceptual quality. We aim to unleash the multifaceted knowledge yielded by the hierarchical views at multiple scales in a pyramid network. Specifically, we build a dual-view pyramid network by introducing pyramidal dual-view correspondence matching. It compels each scale to actively seek knowledge in view of both the current scale and a coarser scale, conducting robust correspondence matching by considering neighboring scales. Meanwhile, an auxiliary multi-scale collaborative supervision is devised to enforce the exchange of knowledge among scales and thus reduce error propagation from coarse to fine scales. Based on the robust capture of video dynamics via pyramidal dual-view correspondence matching, we further construct a pyramidal refinement module that formulates frame refinement as progressive latent representation generations by developing flow-guided cross-scale attention for feature fusion among frames. The proposed method is able to improve the perceptual quality on several benchmarks of varying video resolutions, while keeping low distortion and a compact model size.

We propose Magic Clothing, a latent diffusion model (LDM)-based network architecture for an unexplored garment-driven image synthesis task. Aiming at generating customized characters wearing the target garments with diverse text prompts, the image controllability is the most critical issue, i.e., to preserve the garment details and maintain faithfulness to the text prompts. To this end, we introduce a garment extractor to capture the detailed garment features, and employ self-attention fusion to incorporate them into the pretrained LDMs, ensuring that the garment details remain unchanged on the target character. Then, we leverage the joint classifier-free guidance to balance the control of garment features and text prompts over the generated results. Meanwhile, the proposed garment extractor is a plug-in module applicable to various finetuned LDMs, and it can be combined with other extensions like ControlNet and IP-Adapter to enhance the diversity and controllability of the generated characters. Furthermore, we design Matched-Points-LPIPS (MP-LPIPS), a robust metric for evaluating the consistency of the target image to the source garment. Extensive experiments demonstrate that our Magic Clothing achieves state-of-the-art results under various conditional controls for garment-driven image synthesis. Our source code is available at https://github.com/ShineChen1024/MagicClothing.

Different from traditional video retrieval, sign language retrieval is more biased towards understanding the semantic information of human actions contained in video clips. Previous works typically only encode RGB videos to obtain high-level semantic features, resulting in local action details drowned in a large amount of visual information redundancy. Furthermore, existing RGB-based sign retrieval works suffer from the huge memory cost of dense visual data embedding in end-to-end training, and adopt offline RGB encoder instead, leading to suboptimal feature representation. To address these issues, we propose a novel sign language representation framework called Semantically Enhanced Dual-Stream Encoder (SEDS), which integrates Pose and RGB modalities to represent the local and global information of sign language videos. Specifically, the Pose encoder embeds the coordinates of keypoints corresponding to human joints, effectively capturing detailed action features. For better context-aware fusion of two video modalities, we propose a Cross Gloss Attention Fusion (CGAF) module to aggregate the adjacent clip features with similar semantic information from intra-modality and inter-modality. Moreover, a Pose-RGB Fine-grained Matching Objective is developed to enhance the aggregated fusion feature by contextual matching of fine-grained dual-stream features. Besides the offline RGB encoder, the whole framework only contains learnable lightweight networks, which can be trained end-to-end. Extensive experiments demonstrate that our framework significantly outperforms state-of-the-art methods on various datasets. Code will be available at https://github.com/longtaojiang/SEDS.

The problem of blind image super-resolution aims to recover high-resolution (HR) images from low-resolution (LR) images with unknown degradation modes. Most existing methods model the image degradation process using blur kernels. However, this explicit modeling approach struggles to cover the complex and varied degradation processes encountered in the real world, such as high-order combinations of JPEG compression, blur, and noise. Implicit modeling for the degradation process can effectively overcome this issue, but a key challenge of implicit modeling is the lack of accurate ground truth labels for the degradation process to conduct supervised training. To overcome this limitations inherent in implicit modeling, we propose an \textbf{U}ncertainty-based degradation representation for blind \textbf{S}uper-\textbf{R}esolution framework (\textbf{USR}). By suppressing the uncertainty of local degradation representations in images, USR facilitated self-supervised learning of degradation representations. The USR consists of two components: Adaptive Uncertainty-Aware Degradation Extraction (AUDE) and a feature extraction network composed of Variable Depth Dynamic Convolution (VDDC) blocks. To extract Uncertainty-based Degradation Representation from LR images, the AUDE utilizes the Self-supervised Uncertainty Contrast module with Uncertainty Suppression Loss to suppress the inherent model uncertainty of the Degradation Extractor. Furthermore, VDDC block integrates degradation information through dynamic convolution. Rhe VDDC also employs an Adaptive Intensity Scaling operation that adaptively adjusts the degradation representation according to the network hierarchy, thereby facilitating the effective integration of degradation information. Quantitative and qualitative experiments affirm the superiority of our approach.

We introduce a new task, novel view synthesis for LiDAR sensors. While traditional model-based LiDAR simulators with style-transfer neural networks can be applied to render novel views, they fall short of producing accurate and realistic LiDAR patterns because the renderers rely on explicit 3D reconstruction and exploit game engines, that ignore important attributes of LiDAR points. We address this challenge by formulating, to the best of our knowledge, the first differentiable end-to-end LiDAR rendering framework, LiDAR-NeRF, leveraging a neural radiance field (NeRF) to facilitate the joint learning of geometry and the attributes of 3D points. However, simply employing NeRF cannot achieve satisfactory results, as it only focuses on learning individual pixels while ignoring local information, especially at low texture areas, resulting in poor geometry. To this end, we have taken steps to address this issue by introducing a structural regularization method to preserve local structural details. To evaluate the effectiveness of our approach, we establish an object-centric multi-view LiDAR dataset, dubbed NeRF-MVL. It contains observations of objects from 9 categories seen from 360-degree viewpoints captured with multiple LiDAR sensors. Our extensive experiments on the scene-level KITTI-360 dataset, and on our object-level NeRF-MVL show that our LiDAR-NeRF surpasses the model-based algorithms significantly.

Complaints are pivotal expressions within e-commerce communication, yet the intricate nuances of human interaction present formidable challenges for AI agents to grasp comprehensively. While recent attention has been drawn to analyzing complaints within a multimodal context, relying solely on text and images is insufficient for organizations. The true value lies in the ability to pinpoint complaints within the intricate structures of discourse, scrutinizing them at a granular aspect level. Our research delves into the discourse structure of e-commerce video-based product reviews, pioneering a novel task we term Aspect-Level Complaint Detection from Discourse (ACDD). Embedded in a multimodal framework, this task entails identifying aspect categories and assigning complaint/non-complaint labels at a nuanced aspect level. To facilitate this endeavour, we have curated a unique multimodal product review dataset, meticulously annotated at the utterance level with aspect categories and associated complaint labels. To support this undertaking, we introduce a Multimodal Aspect-Aware Complaint Analysis (MAACA) model that incorporates a novel pre-training strategy and a global feature fusion technique across the three modalities. Additionally, the proposed framework leverages a moment retrieval step to identify the relevant portion of the clip, crucial for accurately detecting the fine-grained aspect categories and conducting aspect-level complaint detection. Extensive experiments conducted on the proposed dataset showcase that our framework outperforms unimodal and bimodal baselines, offering valuable insights into the application of video-audio-text representation learning frameworks for downstream tasks. The dataset and code are available at: https://github.com/rdev12/MAACA.