ACM MM 2024 论文列表

In this paper, we study the problem of Text-to-Image Person Re-identification (TIReID), which aims to find images of the same identity described by a text sentence from a pool of candidate images. Benefiting from Vision-Language Pre-training, such as CLIP (Contrastive Language-Image Pretraining), the TIReID techniques have achieved remarkable progress recently. However, most existing methods only focus on instance-level matching and ignore identity-level matching, which involves associating multiple images and texts belonging to the same person. In this paper, we propose a novel prototypical prompting framework (Propot) designed to simultaneously model instance-level and identity-level matching for TIReID. Our Propot transforms the identity-level matching problem into a prototype learning problem, aiming to learn identity-enriched prototypes. Specifically, Propot works by 'initialize, adapt, enrich, then aggregate'. We first use CLIP to generate high-quality initial prototypes. Then, we propose a domain-conditional prototypical prompting (DPP) module to adapt the prototypes to the TIReID task using task-related information. Further, we propose an instance-conditional prototypical prompting (IPP) module to update prototypes conditioned on intra-modal and inter-modal instances to ensure prototype diversity. Finally, we design an adaptive prototype aggregation module to aggregate these prototypes, generating final identity-enriched prototypes. With identity-enriched prototypes, we diffuse its rich identity information to instances through prototype-to-instance contrastive loss to facilitate identity-level matching. Extensive experiments conducted on three benchmarks demonstrate the superiority of Propot compared to existing TIReID methods.

Understanding of video creativity and content often varies among individuals, with differences in focal points and cognitive levels across different ages, experiences, and genders. There is currently a lack of research in this area, and most existing benchmarks suffer from several drawbacks: 1) a limited number of modalities and answers with restrictive length; 2) the content and scenarios within the videos are excessively monotonous, transmitting allegories and emotions that are overly simplistic. To bridge the gap to real-world applications, we introduce a large-scale Video Subjective Multi-modal Evaluation dataset, namely Video-SME. Specifically, we collected real changes in Electroencephalographic (EEG) and eye-tracking regions from different demographics while they viewed identical video content. Utilizing this multi-modal dataset, we developed tasks and protocols to analyze and evaluate the extent of cognitive understanding of video content among different users. Along with the dataset, we designed a Hypergraph Multi-modal Large Language Model (HMLLM) to explore the associations among different demographics, video elements, EEG and eye-tracking indicators. HMLLM could bridge semantic gaps across rich modalities and integrate information beyond different modalities to perform logical reasoning. Extensive experimental evaluations on Video-SME and other additional video-based generative performance benchmarks demonstrate the effectiveness of our method. The code and dataset are available at https://github.com/mininglamp-MLLM/HMLLM

3D object detection plays a pivotal role in autonomous driving and robotics, demanding precise interpretation of Bird's Eye View (BEV) images. The dynamic nature of real-world environments necessitates the use of dynamic query mechanisms in 3D object detection to adaptively capture and process the complex spatio-temporal relationships present in these scenes. However, prior implementations of dynamic queries have often faced difficulties in effectively leveraging these relationships, particularly when it comes to integrating temporal information in a computationally efficient manner. Addressing this limitation, we introduce a framework utilizing dynamic query evolution strategy, harnesses K-means clustering and Top-K attention mechanisms for refined spatio-temporal data processing. By dynamically segmenting the BEV space and prioritizing key features through Top-K attention, our model achieves a real-time, focused analysis of pertinent scene elements. Our extensive evaluation on the nuScenes and Waymo dataset showcases a marked improvement in detection accuracy, setting a new benchmark in the domain of query-based BEV object detection. Our dynamic query evolution strategy has the potential to push the boundaries of current BEV methods with enhanced adaptability and computational efficiency. Project page: https://github.com/Jiawei-Yao0812/QE-BEV

Zero-shot human-object interaction (HOI) detector is capable of generalizing to HOI categories even not encountered during training. Inspired by the impressive zero-shot capabilities offered by CLIP, latest methods strive to leverage CLIP embeddings for improving zero-shot HOI detection. However, these embedding-based methods train the classifier on seen classes only, inevitably resulting in seen-unseen confusion for the model during inference. Besides, we find that using prompt-tuning and adapters further increases the gap between seen and unseen accuracy. To tackle this challenge, we present the first generation-based model using CLIP for zero-shot HOI detection, coined HOIGen. It allows to unlock the potential of CLIP for feature generation instead of feature extraction only. To achieve it, we develop a CLIP-injected feature generator in accordance with the generation of human, object and union features. Then, we extract realistic features of seen samples and mix them with synthetic features together, allowing the model to train seen and unseen classes jointly. To enrich the HOI scores, we construct a generative prototype bank in a pairwise HOI recognition branch, and a multi-knowledge prototype bank in an image-wise HOI recognition branch, respectively. Extensive experiments on HICO-DET benchmark demonstrate our HOIGen achieves superior performance for both seen and unseen classes under various zero-shot settings, compared with other top-performing methods. Code is available at: https://github.com/soberguo/HOIGen

Considering that image editing and manipulation technologies pose significant threats to the authenticity and security of image content, research on image regional manipulation detection has always been a critical issue. The accelerated advancement of generative AI significantly enhances the viability and effectiveness of generative regional editing methods and has led to their gradual replacement of traditional image editing tools or algorithms. However, current research primarily focuses on traditional image tampering, and there remains a lack of a comprehensive dataset containing images edited with abundant generative regional editing methods. We endeavor to fill this vacancy by constructing the GRE dataset, a large-scale generative regional editing detection dataset with the following advantages: 1) Integration of a logical and simulated editing pipeline, leveraging multiple large models in various modalities. 2) Inclusion of various editing approaches with distinct characteristics. 3) Provision of comprehensive benchmark and evaluation of SOTA methods across related domains. 4) Analysis of the GRE dataset from multiple dimensions including necessity, rationality, and diversity. Extensive experiments and in-depth analysis demonstrate that this larger and more comprehensive dataset will significantly enhance the development of detection methods for generative editing. The corresponding repository is at https://github.com/ICTMCG/GRE.

Recent works on audio-driven talking head synthesis using Neural Radiance Fields (NeRF) have achieved impressive results. However, due to inadequate pose and expression control caused by NeRF implicit representation, these methods still have some limitations, such as unsynchronized or unnatural lip movements, and visual jitter and artifacts. In this paper, we propose GaussianTalker, a novel method for audio-driven talking head synthesis based on 3D Gaussian Splatting. With the explicit representation property of 3D Gaussians, intuitive control of the facial motion is achieved by binding Gaussians to 3D facial models. GaussianTalker consists of two modules, Speaker-specific Motion Translator and Dynamic Gaussian Renderer. Speaker-specific Motion Translator achieves accurate lip movements specific to the target speaker through universalized audio feature extraction and customized lip motion generation. Dynamic Gaussian Renderer introduces Speaker-specific BlendShapes to enhance facial detail representation via a latent pose, delivering stable and realistic rendered videos. Extensive experimental results suggest that GaussianTalker outperforms existing state-of-the-art methods in talking head synthesis, delivering precise lip synchronization and exceptional visual quality. Our method achieves rendering speeds of 130 FPS on NVIDIA RTX4090 GPU, significantly exceeding the threshold for real-time rendering performance, and can potentially be deployed on other hardware platforms.

In the medical field, managing high-dimensional massive medical imaging data and performing reliable medical analysis from it is a critical challenge, especially in resource-limited environments such as remote medical facilities and mobile devices. This necessitates effective dataset compression techniques to reduce storage, transmission, and computational cost. However, existing coreset selection methods are primarily designed for natural image datasets, and exhibit doubtful effectiveness when applied to medical image datasets due to challenges such as intra-class variation and inter-class similarity. In this paper, we propose a novel coreset selection strategy termed as Evolution-aware VAriance (EVA), which captures the evolutionary process of model training through a dual-window approach and reflects the fluctuation of sample importance more precisely through variance measurement. Extensive experiments on medical image datasets demonstrate the effectiveness of our strategy over previous SOTA methods, especially at high compression rates. EVA achieves 98.27% accuracy with only 10% training data, compared to 97.20% for the full training set. None of the compared baseline methods can exceed Random at 5% selection rate, while EVA outperforms Random by 5.61%, showcasing its potential for efficient medical image analysis.

Gaussian splatting, renowned for its exceptional rendering quality and efficiency, has emerged as a prominent technique in 3D scene representation. However, the substantial data volume of Gaussian splatting impedes its practical utility in real-world applications. Herein, we propose an efficient 3D scene representation, named Compressed Gaussian Splatting (CompGS), which harnesses compact Gaussian primitives for faithful 3D scene modeling with a remarkably reduced data size. To ensure the compactness of Gaussian primitives, we devise a hybrid primitive structure that captures predictive relationships between each other. Then, we exploit a small set of anchor primitives for prediction, allowing the majority of primitives to be encapsulated into highly compact residual forms. Moreover, we develop a rate-constrained optimization scheme to eliminate redundancies within such hybrid primitives, steering our CompGS towards an optimal trade-off between bitrate consumption and representation efficacy. Experimental results show that the proposed CompGS significantly outperforms existing methods, achieving superior compactness in 3D scene representation without compromising model accuracy and rendering quality. Our code will be released on GitHub for further research.

Recent advancements in diffusion models trained on large-scale data have enabled the generation of indistinguishable human-level images, yet they often produce harmful content misaligned with human values, e.g., social bias, and offensive content. Despite extensive research on Large Language Models (LLMs), the challenge of Text-to-Image (T2I) model alignment remains largely unexplored. Addressing this problem, we propose LiVO (Lightweight Value Optimization), a novel lightweight method for aligning T2I models with human values. LiVO only optimizes a plug-and-play value encoder to integrate a specified value principle with the input prompt, allowing the control of generated images over both semantics and values. Specifically, we design a diffusion model-tailored preference optimization loss, which theoretically approximates the Bradley-Terry model used in LLM alignment but provides a more flexible trade-off between image quality and value conformity. To optimize the value encoder, we also develop a framework to automatically construct a text-image preference dataset of 86k (prompt, aligned image, violating image, value principle) samples. Without updating most model parameters and through adaptive value selection from the input prompt, LiVO significantly reduces harmful outputs and achieves faster convergence, surpassing several strong baselines and taking an initial step towards ethically aligned T2I models. Warning: This paper involves descriptions and images depicting discriminatory, pornographic, bloody, and horrific scenes.

Enzyme design plays a crucial role in both industrial production and biology. However, this field faces challenges due to the lack of comprehensive benchmarks and the complexity of enzyme design tasks, leading to a dearth of systematic research. Consequently, computational enzyme design is relatively overlooked within the broader protein domain and remains in its early stages. In this work, we address these challenges by introducing MetaEnzyme, a staged and unified enzyme design framework. We begin by employing a cross-modal structure-to-sequence transformation architecture, as the feature-driven starting point to obtain initial robust protein representation. Subsequently, we leverage domain adaptive techniques to generalize specific enzyme design tasks under low-resource conditions. MetaEnzyme focuses on three fundamental low-resource enzyme redesign tasks: functional design (FuncDesign), mutation design (MutDesign), and sequence generation design (SeqDesign). Through novel unified paradigm and enhanced representation capabilities, MetaEnzyme demonstrates adaptability to diverse enzyme design tasks, yielding outstanding results. Wet lab experiments further validate these findings, reinforcing the efficacy of the redesign process.

The widespread adoption of bio-inspired cameras has catalyzed the development of spike-based intelligent applications. Despite its innovative imaging principle allows for functionality in extreme scenarios, the intricate nature of spike signals poses processing challenges to achieve desired performance. Traditional methods struggles to deliver visual perception and temporal prediction simultaneously, and they lack the flexibility needed for diverse intelligent applications. To address this problem, we analyze the spatio-temporal correlations between spike information at different temporal scales. A novel spike processing method is introduced for compact spike representations that utilizes intra-scale correlation for higher predictive accuracy. Additionally, we propose a multi-scale spatio-temporal aggregation unit (MSTAU) that further leverages inter-scale correlation to achieve efficient perception and precise prediction. Experimental results show noticeable improvements in scene reconstruction and object classification, with increases of 3.49dB in scene reconstruction quality and 2.20% in accuracy, respectively. Besides, the proposed method accommodate different visual applications via switching analysis models, offering a novel perspective for spike processing.

The growing interest in embodied intelligence has brought ego-centric perspectives to contemporary research. One significant challenge within this realm is the accurate localization and tracking of objects in ego-centric videos, primarily due to the substantial variability in viewing angles. Addressing this issue, this paper introduces a novel zero-shot approach for the 3D reconstruction and tracking of all objects from the ego-centric video. We present Ego3DT, a novel framework that initially identifies and extracts detection and segmentation information of objects within the ego environment. Utilizing information from adjacent video frames, Ego3DT dynamically constructs a 3D scene of the ego view using a pre-trained 3D scene reconstruction model. Additionally, we have innovated a dynamic hierarchical association mechanism for creating stable 3D tracking trajectories of objects in ego-centric videos. Moreover, the efficacy of our approach is corroborated by extensive experiments on two newly compiled datasets, with 1.04 × - 2.90× in HOTA, showcasing the robustness and accuracy of our method in diverse ego-centric scenarios.

Text-to-image (T2I) customization aims to create images that embody specific visual concepts delineated in textual descriptions. However, existing works still face a main challenge, concept overfitting. To tackle this challenge, we first analyze overfitting, categorizing it into concept-agnostic overfitting, which undermines non-customized concept knowledge, and concept-specific overfitting, which is confined to customize on limited diversities, i.e, backgrounds, layouts, styles. To evaluate the overfitting degree, we further introduce two metrics, i.e, Latent Fisher divergence and Wasserstein metric to measure the distribution changes of non-customized and customized concept respectively. Drawing from the analysis, we propose Infusion, a T2I customization method that enables the learning of target concepts to avoid being constrained by limited training diversities, while preserving non-customized knowledge. Remarkably, Infusion achieves this feat with remarkable efficiency, requiring a mere 11KB of trained parameters. Extensive experiments also demonstrate that our approach outperforms state-of-the-art methods in both single and multi-concept customized generation. Project page: https://zwl666666.github.io/infusion/.

Large Vision Language Models (VLMs) extend and enhance the perceptual abilities of Large Language Models (LLMs).Despite offering new possibilities for LLM applications, these advancements raise significant security and ethical concerns, particularly regarding the generation of harmful content.While LLMs have undergone extensive security evaluations with the aid of red teaming frameworks, VLMs currently lack a well-developed one.To fill this gap, we introduce Arondight, a standardized red team framework tailored specifically for VLMs.Arondight is dedicated to resolving issues related to the absence of visual modality and inadequate diversity encountered when transitioning existing red teaming methodologies from LLMs to VLMs.Our framework features an automated multi-modal jailbreak attack, wherein visual jailbreak prompts are produced by a red team VLM, and textual prompts are generated by a red team LLM guided by a reinforcement learning agent.To enhance the comprehensiveness of VLM security evaluation, we integrate entropy bonuses and novelty reward metrics.These elements incentivize the RL agent to guide the red team LLM in creating a wider array of diverse and previously unseen test cases.Our evaluation of ten cutting-edge VLMs exposes significant security vulnerabilities, particularly in generating toxic images and aligning multi-modal prompts.In particular, our Arondight achieves an average attack success rate of 84.5% on GPT-4 in all fourteen prohibited scenarios defined by OpenAI in terms of generating toxic text.For a clearer comparison, we also categorize existing VLMs based on their safety levels and provide corresponding reinforcement recommendations.Our multimodal prompt dataset and red team code will be released after ethics committee approval.

With the development of diffusion-based customization methods like DreamBooth, individuals now have access to train the models that can generate their personalized images. Despite the convenience, malicious users have misused these techniques to create fake images, thereby triggering a privacy security crisis. In light of this, proactive adversarial attacks are proposed to protect users against customization. The adversarial examples are trained to distort the customization model's outputs and thus block the misuse. In this paper, we propose DisDiff (Disrupting Diffusion), a novel adversarial attack method to disrupt the diffusion model outputs. We first delve into the intrinsic image-text relationships, well-known as cross-attention, and empirically find that the subject-identifier token plays an important role in guiding image generation. Thus, we propose the Cross-Attention Erasure module to explicitly "erase" the indicated attention maps and disrupt the text guidance. Besides, we analyze the influence of the sampling process of the diffusion model on Projected Gradient Descent (PGD) attack and introduce a novel Merit Sampling Scheduler to adaptively modulate the perturbation updating amplitude in a step-aware manner. Our DisDiff outperforms the state-of-the-art methods by 12.75% of FDFR scores and 7.25% of ISM scores across two facial benchmarks and two commonly used prompts on average.

In recent years, Multi-Modality Image Fusion (MMIF) has been applied to many fields, which has attracted many scholars to endeavour to improve the fusion performance. However, the prevailing focus has predominantly been on the architecture design, rather than the training strategies. As a low-level vision task, image fusion is supposed to quickly deliver output images for observation and supporting downstream tasks. Thus, superfluous computational and storage overheads should be avoided. In this work, a lightweight Distilled Mini-Model with a Dynamic Refresh strategy (MMDRFuse) is proposed to achieve this objective. To pursue model parsimony, an extremely small convolutional network with a total of 113 trainable parameters (0.44 KB) is obtained by three carefully designed supervisions. First, digestible distillation is constructed by emphasising external spatial feature consistency, delivering soft supervision with balanced details and saliency for the target network. Second, we develop a comprehensive loss to balance the pixel, gradient, and perception clues from the source images. Third, an innovative dynamic refresh training strategy is used to collaborate history parameters and current supervision during training, together with an adaptive adjust function to optimise the fusion network. Extensive experiments on several public datasets demonstrate that our method exhibits promising advantages in terms of model efficiency and complexity, with superior performance in multiple image fusion tasks and downstream pedestrian detection application. The code of this work is publicly available at https://github.com/yanglinDeng/MMDRFuse.

Although the Segment Anything Model (SAM) has achieved impressive results in many segmentation tasks and benchmarks, its performance noticeably deteriorates when applied to high-resolution images for high-precision segmentation, limiting it's usage in many real-world applications.In this work, we explored transferring SAM into the domain of high-resolution images and proposed Pi-SAM. Compared to the original SAM and its variants, Pi-SAM demonstrates the following superiorities: Firstly, Pi-SAM possesses a strong perception capability for the extremely fine details in high-resolution images, enabling it to generate high-precision segmentation masks. As a result,Pi-SAM significantly surpasses previous methods in four high-resolution datasets. Secondly, Pi-SAM supports more precise user interactions. In addition to the native promptable ability of SAM, Pi-SAM allows users to interactively refine the segmentation predictions simply by clicking. While the original SAM fails to achieve this on high-resolution images. Thirdly, building upon SAM, Pi-SAM introduces very few additional parameters and computational costs and ensures highly efficient model fine-tuning to achieve the above performance.