ACM MM 2024 Papers

Understanding a meme is a challenging task, due to the metaphorical information contained in the meme that requires intricate interpretation to grasp its intended meaning fully. In previous works, attempts have been made to facilitate computational understanding of memes through introducing human-annotated metaphors as extra input features into machine learning models. However, these approaches mainly focus on formulating linguistic representation of a metaphor (extracted from the texts appearing in memes), while ignoring the connection between the metaphor and corresponding visual features (e.g., objects in meme images). In this paper, we argue that a more comprehensive understanding of memes can only be achieved through a joint modelling of both visual and linguistic features of memes. To this end, we propose an approach to generate Multimodal Metaphorical feature for Meme Classification, named MMMC. MMMC derives visual characteristics from linguistic attributes of metaphorical concepts, which more effectively convey the underlying metaphorical concept, leveraging a text-conditioned generative adversarial network. The linguistic and visual features are then integrated into a set of multimodal metaphorical features for classification purpose. We perform extensive experiments on a benchmark metaphorical meme dataset, MET-Meme. Experimental results show that MMMC significantly outperforms existing baselines on the task of emotion classification and intention detection. Our code and dataset are available at https://github.com/liaolianfoka/MMMC.

In real-world recon-videos such as surveillance and drone reconnaissance videos, commonly used explicit language, acoustic and facial expressions information is often missing. However, these videos are always rich in anomalous sentiments (e.g., criminal tendencies), which urgently requires the implicit scene information (e.g., actions and object relations) to fast and precisely identify these anomalous sentiments. Motivated by this, this paper proposes a new chat-paradigm Implicit anomalous sentiment Discovering and grounding (IasDig) task, aiming to interactively, fast discovering and grounding anomalous sentiments in recon-videos via leveraging the implicit scene information (i.e., actions and object relations). Furthermore, this paper believes that this IasDig task faces two key challenges, i.e., scene modeling and scene balancing. To this end, this paper proposes a new Scene-enhanced Video Large Language Model named Hawkeye, i.e., acting like a raptor (e.g., a Hawk) to discover and locate prey, for the IasDig task. Specifically, this approach designs a graph-structured scene modeling module and a balanced heterogeneous MoE module to address the above two challenges, respectively. Extensive experimental results on our constructed scene-sparsity and scene-density IasDig datasets demonstrate the great advantage of Hawkeye to IasDig over the advanced Video-LLM baselines, especially on the metric of false negative rates. This justifies the importance of the scene information for identifying implicit anomalous sentiments and the impressive practicality of Hawkeye for real-world applications.

By integrating various modules with the Visual Transformer (ViT), we facilitate a interpretation of image processing across each layer and attention head. This method allows us to explore the connections both within and across the layers, enabling a analysis of how images are processed at different layers. Conducting a analysis of the contributions from each layer and attention head, shedding light on the intricate interactions and functionalities within the model's layers. This in-depth exploration not only highlights the visual cues between layers but also examines their capacity to navigate the transition from abstract concepts to tangible objects. It unveils the model's mechanism to building an understanding of images, providing a strategy for adjusting attention heads between layers, thus enabling targeted pruning and enhancement of performance for specific tasks. Our research indicates that achieving a scalable understanding of transformer models is within reach, offering ways for the refinement and enhancement of such models.

Scene image is one of the important windows for showcasing product design. To obtain it, the standard 3D-based pipeline requires designer to not only create the 3D model of product, but also manually construct the entire scene in software, which hindering its adaptability in situations requiring rapid evaluation. This study aims to realize a novel conditional synthesis method to create the scene image based on a single-model rendering of the desired object and the scene description. In this task, the major challenges are ensuring the strict appearance fidelity of drawn object and the overall visual harmony of synthesized image. The former's achievement relies on maintaining an appropriate condition-output constraint, while the latter necessitates a well-balanced generation process for all regions of image. In this work, we propose Scene Diffusion framework to meet these challenges. Its first progress is introducing the Shading Adaptive Condition Alignment (SACA), which functions as an intensive training objective to promote the appearance consistency between condition and output image without hindering the network's learning to the global shading coherence. Afterwards, a novel low-to-high Frequency Progression Training Schedule (FPTS) is utilized to maintain the visual harmony of entire image by moderating the growth of high-frequency signals in the object area. Extensive qualitative and quantitative results are presented to support the advantages of the proposed method. In addition, we also demonstrate the broader uses of Scene Diffusion, such as its incorporation with ControlNet.

Person re-identification (ReID) is crucial in video surveillance, aiming to match individuals across different camera views while cloth-changing person re-identification (CC-ReID) focuses on pedestrians changing attire. Many existing CC-ReID methods overlook generalization, crucial for universality across cloth-consistent and cloth-changing scenarios. This paper pioneers exploring the cloth-generalized person re-identification (CG-ReID) task and introduces the Cloth-aware Augmentation (CaAug) strategy. Comprising domain augmentation and feature augmentation, CaAug aims to learn identity-relevant features adaptable to both scenarios. Domain augmentation involves creating diverse fictitious domains and simulating various clothing scenarios. Supervising features from different cloth domains enhances robustness and generalization against clothing changes. Additionally, for feature augmentation, element exchange introduces diversity concerning clothing changes. Regularizing the model with these augmented features strengthens resilience against clothing change uncertainty. Extensive experiments on cloth-changing datasets demonstrate the efficacy of our approach, consistently outperforming state-of-the-art methods.

3D face recognition is subject to frequent spoofing attacks, in which 3D face presentation attack is one of the most notorious attacks. The attacker takes advantages of 3D scanning and printing techniques to generate masks of targets, which has found success in numerous real-life examples. The salient feature in such attacks is to obtain 3D face models through 3D scanning, though relatively more expensive and inconvenient when comparing with 2D photos. In this work, we propose a new method, DREAM, to recover 3D face models from single 2D image. Specifically, we adopt a black-box approach, which recovers 'sufficient' depths to defeat target recognition models (e.g., face identification and face authentication models) by accessing its output and the corresponding RGB photo. The key observation is that it is not necessary to restore the true value of depths, but only need to recover the essential features relevant to the target model. We used four public 3D face datasets to verify the effectiveness of DREAM. The experimental results show that DREAM can achieve a success rate of 94% on face authentication model, even in cross-dataset testing, and a success rate of 36% on face identification model.

Visual grounding is the task of locating objects specified by natural language expressions. Existing methods extend generic object detection frameworks to tackle this task. They typically extract visual and textual features separately using independent visual and textual encoders, then fuse these features in a multi-modal decoder for final prediction. However, visual grounding presents unique challenges. It often involves locating objects with different text descriptions within the same image. Existing methods struggle with this task because the independent visual encoder produces identical visual features for the same image, limiting detection performance. Some recently approaches propose various language-guided visual encoders to address this issue, but they mostly rely solely on textual information and require sophisticated designs. In this paper, we introduce Multi-modal Conditional Adaptation (MMCA), which enables the visual encoder to adaptively update weights, directing its focus towards text-relevant regions. Specifically, we first integrate information from different modalities to obtain multi-modal embeddings. Then we utilize a set of weighting coefficients, which generated from the multimodal embeddings, to reorganize the weight update matrices and apply them to the visual encoder of the visual grounding model. Extensive experiments on four widely used datasets demonstrate that MMCA achieves significant improvements and state-of-the-art results. Ablation experiments further demonstrate the lightweight and efficiency of our method. Our source code is available at: https://github.com/Mr-Bigworth/MMCA.

Recent advances of large multi-modality models (LMM) have greatly improved the ability of image quality assessment (IQA) method to evaluate and explain the quality of visual content. However, these advancements are mostly focused on overall quality assessment, and the detailed examination of local quality, which is crucial for comprehensive visual understanding, is still largely unexplored. In this work, we introduce Q-Ground, the first framework aimed at tackling fine-scale visual quality grounding by combining large multi-modality models with detailed visual quality analysis. Cen- tral to our contribution is the introduction of the QGround-100K dataset, a novel resource containing 100k triplets of (image, quality text, distortion segmentation) to facilitate deep investigations into visual quality. The dataset comprises two parts: one with human- labeled annotations for accurate quality assessment, and another la- beled automatically by LMMs such as GPT4V, which helps improve the robustness of model training while also reducing the costs of data collection. With the QGround-100K dataset, we propose a LMM-based method equipped with multi-scale feature learning to learn models capable of performing both image quality answer- ing and distortion segmentation based on text prompts. This dual- capability approach not only refines the model’s understanding of region-aware image quality but also enables it to interactively re- spond to complex, text-based queries about image quality and spe- cific distortions. Q-Ground takes a step towards sophisticated vi- sual quality analysis in a finer scale, establishing a new benchmark for future research in the area. Codes and dataset are available at https://github.com/Q-Future/Q-Ground.

Modern perception systems for autonomous flight are sensitive to occlusion and have limited long-range capability, which is a key bottleneck in improving low-altitude economic task performance. Recent research has shown that the UAV-to-UAV (U2U) cooperative perception system has great potential to revolutionize the autonomous flight industry. However, the lack of a large-scale dataset is hindering progress in this area. This paper presents U2UData, the first large-scale cooperative perception dataset for swarm UAVs autonomous flight. The dataset was collected by three UAVs flying autonomously in the U2USim, covering a 9 km$^2$ flight area. It comprises 315K LiDAR frames, 945K RGB and depth frames, and 2.41M annotated 3D bounding boxes for 3 classes. It also includes brightness, temperature, humidity, smoke, and airflow values covering all flight routes. U2USim is the first real-world mapping swarm UAVs simulation environment. It takes Yunnan Province as the prototype and includes 4 terrains, 7 weather conditions, and 8 sensor types. U2UData introduces two perception tasks: cooperative 3D object detection and cooperative 3D object tracking. This paper provides comprehensive benchmarks of recent cooperative perception algorithms on these tasks.

Forensic person identification is of paramount importance in accidents and criminal investigations. Existing methods based on soft tissue or DNA can be unavailable if the body is badly decomposed, white-ossified, or charred. However, bones last a long time. This raises a natural question: can we learn to identify a person using bone data? We present a novel feature of bones called Neural Boneprint for personal identification. In particular, we exploit the thoracic skeletal data including chest radiographs (CXRs) and computed tomography (CT) images enhanced by the volume rendering technique (VRT) as an example to explore the availability of the neural boneprint. We then represent the neural boneprint as a joint latent embedding of VRT images and CXRs through a bidirectional cross-modality translation and contrastive learning. Preliminary experimental results on real skeletal data demonstrate the effectiveness of the Neural Boneprint for identification. We hope that this approach will provide a promising alternative for challenging forensic cases where conventional methods are limited. The code is available at https://github.com/CheltonNiu/Neural-Boneprint.git.

Dataset distillation, also known as dataset condensation, offers a possibility for compressing a large-scale dataset into a small-scale one (i.e., distilled dataset) while achieving similar performance during model training. This method effectively tackles the challenges of training efficiency and storage cost posed by the large-scale dataset. Existing dataset distillation methods can be categorized into Optimization-Oriented (OO)-based and Distribution-Matching (DM)-based methods. Since OO-based methods require bi-level optimization to alternately optimize the model and the distilled data, they face challenges due to high computational overhead in practical applications. Thus, DM-based methods have emerged as an alternative by aligning the prototypes of the distilled data to those of the original data. Although efficient, these methods overlook the diversity of the distilled data, which will limit the performance of evaluation tasks. In this paper, we propose a novel Diversified Semantic Distribution Matching (DSDM) approach for dataset distillation. To accurately capture semantic features, we first pre-train models for dataset distillation. Subsequently, we estimate the distribution of each category by calculating its prototype and covariance matrix, where the covariance matrix indicates the direction of semantic feature transformations for each category. Then, in addition to the prototypes, the covariance matrices are also matched to obtain more diversity for the distilled data. However, since the distilled data are optimized by multiple pre-trained models, the training process will fluctuate severely. Therefore, we match the distilled data of the current pre-trained model with the historical integrated prototypes. Experimental results demonstrate that our DSDM achieves state-of-the-art results on both image and speech datasets. Code is available at https://github.com/Li-Hongcheng/DSDM.

Cinemagraph creates captivating video experience by combining elements of still photography and subtle motion. However, most existing cinemagraph video generation lacks depth information, being restricted within 2-dimensional (2D) image space. We advance cinemagraph from 2D image space to 3-dimensional (3D) space with high quality by proposing LoopGaussian. It is based on 3D Gaussian modeling, taking advantage of the 3D Gaussian Splatting (3D-GS) technique that has significantly improved the field of novel view synthesis. Here is a brief overview of our new approach: It employs 3D-GS to reconstruct 3D Gaussian point clouds from multi-view images of static scenes, where shape regularization is used to prevent blurring or artifacts caused by object deformation. To maintain local continuity between scenes, it then clusters the 3D Gaussian points by the proposed SuperGaussian algorithm using features acquired by an autoencoder tailored for 3D Gaussian. Similarities between clusters are used to derive an Eulerian motion field for describing velocities across the entire scene. The estimated Eulerian motion field drives the movement of the 3D Gaussian points, based on which a 3D Cinemagraph is generated through bidirectional animation. The resulting 3D Cinemagraph exhibits natural and seamlessly loopable dynamics. Experiment results validate the effectiveness of the proposed approach, demonstrating high-quality and visually appealing video generation.

Visual emotion recognition (VER) is a longstanding field that has garnered increasing attention with the advancement of deep neural networks. Although recent studies have achieved notable improvements by leveraging the knowledge embedded within pre-trained visual models, the lack of direct association between factual-level features and emotional categories, called the ''affective gap'', limits the applicability of pre-training knowledge for VER tasks. On the contrary, the explicit emotional expression and high information density in textual modality eliminate the ''affective gap''. Therefore, we propose borrowing the knowledge from the pre-trained textual model to enhance the emotional perception of pre-trained visual models. We focus on the factual and emotional connections between images and texts in noisy social media data, and propose Partitioned Adaptive Contrastive Learning (PACL) to leverage these connections. Specifically, we manage to separate different types of samples and devise distinct contrastive learning strategies for each type. By dynamically constructing negative and positive pairs, we fully exploit the potential of noisy samples. Through comprehensive experiments, we demonstrate that bridging the "affective gap'' significantly improves the performance of various pre-trained visual models in downstream emotion-related tasks. Our code is released on https://github.com/wdqqdw/PACL.

Recently, a novel form of audio partial forgery has posed challenges to its forensics, requiring advanced countermeasures to detect subtle forgery manipulations within long-duration audio. However, existing countermeasures still serve a classification purpose and fail to perform meaningful analysis of the start and end timestamps of partial forgery segments. To address this challenge, we introduce a novel coarse-to-fine proposal refinement framework (CFPRF) that incorporates a frame-level detection network (FDN) and a proposal refinement network (PRN) for audio temporal forgery detection and localization. Specifically, the FDN aims to mine informative inconsistency cues between real and fake frames to obtain discriminative features that are beneficial for roughly indicating forgery regions. The PRN is responsible for predicting confidence scores and regression offsets to refine the coarse-grained proposals derived from the FDN. To learn robust discriminative features, we devise a difference-aware feature learning (DAFL) module guided by contrastive representation learning to enlarge the sensitive differences between different frames induced by minor manipulations. We further design a boundary-aware feature enhancement (BAFE) module to capture the contextual information of multiple transition boundaries and guide the interaction between boundary information and temporal features via a cross-attention mechanism. Extensive experiments show that our CFPRF achieves state-of-the-art performance on various datasets, including LAV-DF, ASVS2019PS, and HAD.

Due to the limited permissions for upgrading dual-side (i.e., server-side and client-side) loss tolerance schemes from the perspective of CDN vendors in a multi-supplier market, modern large-scale live streaming services are still using the automatic-repeat-request (ARQ) based paradigm for loss recovery, which only requires server-side modifications. In this paper, we first conduct a large-scale measurement study with up to 50 million live streams. We find that loss shows dynamics and live streaming contains frequent on-off mode switching in the wild. We further find that the recovery latency, enlarged by the ubiquitous retransmission loss, is a critical factor affecting live streaming's client side QoE (e.g., video freezing). We then propose an enhanced recovery mechanism called AutoRec, which can transform the disadvantages of on-off mode switching into an advantage for reducing loss recovery latency without any modifications on the client side. AutoRec also adopts an online learning-based policy to fit the dynamics of loss, balancing the tradeoff between the recovery latency and the incurred overhead. We implement AutoRec upon QUIC and evaluate it via both testbed and real-world commercial services deployments. The experimental results demonstrate the practicability and profitability of AutoRec, in which the average times and duration of client-side video freezing can be lowered by 11.4% and 5.2%, respectively.

Stance detection, which aims to identify public opinion towards specific targets using social media data, is an important yet challenging task. With the proliferation of diverse multimodal social media content including text, and images multimodal stance detection (MSD) has become a crucial research area. However, existing MSD studies have focused on modeling stance within individual text-image pairs, overlooking the multi-party conversational contexts that naturally occur on social media. This limitation stems from a lack of datasets that authentically capture such conversational scenarios, hindering progress in conversational MSD. To address this, we introduce a new multimodal multi-turn conversational stance detection dataset (called MmMtCSD). To derive stances from this challenging dataset, we propose a novel multimodal large language model stance detection framework (MLLM-SD), that learns joint stance representations from textual and visual modalities. Experiments on MmMtCSD show state-of-the-art performance of our proposed MLLM-SD approach for multimodal stance detection. We believe that MmMtCSD will contribute to advancing real-world applications of stance detection research.

Emotional Video Captioning (EVC) is an emerging task that aims to describe factual content with the intrinsic emotions expressed in videos. The essential of the EVC task is to effectively perceive subtle and ambiguous visual emotional cues during the caption generation, which is neglected by the traditional video captioning. Existing emotional video captioning methods perceive global visual emotional cues at first, and then combine them with the video features to guide the emotional caption generation, which neglects two characteristics of the EVC task. Firstly, their methods neglect the dynamic subtle changes in the intrinsic emotions of the video, which makes it difficult to meet the needs of common scenes with diverse and changeable emotions. Secondly, as their methods incorporate emotional cues into each step, the guidance role of emotion is overemphasized, which makes factual content more or less ignored during generation. To this end, we propose a dual-path collaborative generation network, which dynamically perceives visual emotional cues evolutions while generating emotional captions by collaborative learning. The two paths promote each other and significantly improve the generation performance. Specifically, in the dynamic emotion perception path, we propose a dynamic emotion evolution module, which first aggregates visual features and historical caption features to summarize the global visual emotional cues, and then dynamically selects emotional cues required to be re-composed at each stage as well as re-composed them to achieve emotion evolution by dynamically enhancing or suppressing different granularity subspace's semantics. Besides, in the adaptive caption generation path, to balance the description of factual content and emotional cues, we propose an emotion adaptive decoder, which firstly estimates emotion intensity via the alignment of emotional features and historical caption features at each generation step, and then, emotional guidance adaptively incorporate into the caption generation based on the emotional intensity. Thus, our methods can generate emotion-related words at the necessary time step, and our caption generation balances the guidance of factual content and emotional cues well. Extensive experiments on three challenging datasets demonstrate the superiority of our approach and each proposed module.