论文检索

Mengqi GUO, Chen Li, Hanlin Chen, Gim Hee Lee

Recent neural implicit representations (NIRs) have achieved great success in the tasks of 3D reconstruction and novel view synthesis. However, they require the images of a scene from different camera views to be available for one-time training. This is expensive especially for scenarios with large-scale scenes and limited data storage. In view of this, we explore the task of incremental learning for NIRs in this work. We design a student-teacher framework to mitigate the catastrophic forgetting problem. As a result, the student network is able to learn new incoming data while preserving old knowledge simultaneously, aided by a random inquirer and an uncertainty-based filter for effective knowledge merging. Our proposed method is general and thus can be adapted to different implicit representations such as neural radiance field (NeRF) and neural SDF. Extensive experimental results for both 3D reconstruction and novel view synthesis demonstrate the effectiveness of our approach compared to different baselines.

Robin Courant, Nicolas Dufour, Xi WANG, Marc Christie, Vicky Kalogeiton

Stories and emotions in movies emerge through the effect of well-thought-out directing decisions, and in particular camera placement and movements over time. Crafting compelling camera motion trajectories remains a complex iterative process even for skilful artists. While recent work has been focusing on speeding up the process, current solutions remain limited in describing and generating complex and content-aware camera trajectories, especially for movies, where the story evolves around moving characters and hence the camera follows them. To alleviate this, in this paper, we propose a diffusion-based approach, named DIRECTOR, which generates complex compositions of camera trajectories from high-level textual inputs that describe the relation and synchronisation between the camera and characters. Furthermore, we propose a dataset called Exceptional Trajectories (E.T.) with camera motion trajectories along with textual captions with descriptive information of camera and character motion. To our knowledge, this is the first movie dataset of its kind. For proper evaluation, we also provide a robust and accurate language trajectory feature representation. Extensive experiments and analysis show that DIRECTOR successfully leverages both the caption and camera trajectories and sets the new state of the art on this task. Our work represents a significant advancement in democratizing the art of cinematography for amateur and experienced users.

Arpit Garg, Cuong Cao Nguyen, RAFAEL FELIX, Thanh-Toan Do, Gustavo Carneiro

Deep learning faces a formidable challenge when handling noisy labels, as models tend to overfit samples affected by label noise. This challenge is further compounded by the presence of instance-dependent noise (IDN), a realistic form of label noise arising from ambiguous sample information. To address IDN, Label Noise Learning (LNL) incorporates a sample selection stage to differentiate clean and noisy-label samples. This stage uses an arbitrary criterion and a pre-defined curriculum that initially selects most samples as noisy and gradually decreases this selection rate during training. Such curriculum is sub-optimal since it does not consider the actual label noise rate in the training set. This paper addresses this issue with a new noise-rate estimation method that is easily integrated with most state-of-the-art (SOTA) LNL methods to produce a more effective curriculum. Synthetic and real-world benchmarks’ results demonstrate that integrating our approach with SOTA LNL methods improves accuracy in most cases.

Sheng Jin, Shuhuai Li, Tong Li, Wentao Liu, Chen Qian, Ping Luo

Human-centric perception (\eg detection, segmentation, pose estimation, and attribute analysis) is a long-standing problem for computer vision. This paper introduces a unified and versatile framework (HQNet) for single-stage multi-person multi-task human-centric perception (HCP). Our approach centers on learning a unified human query representation, denoted as Human Query, which captures intricate instance-level features for individual persons and disentangles complex multi-person scenarios. Although different HCP tasks have been well-studied individually, single-stage multi-task learning of HCP tasks has not been fully exploited in the literature due to the absence of a comprehensive benchmark dataset. To address this gap, we propose COCO-UniHuman benchmark to enable model development and comprehensive evaluation. Experimental results demonstrate the proposed method's state-of-the-art performance among multi-task HCP models and its competitive performance compared to task-specific HCP models. Moreover, our experiments underscore Human Query's adaptability to new HCP tasks, thus demonstrating its robust generalization capability. Codes and data are available at \url{https://github.com/lishuhuai527/COCO-UniHuman}.

Aayam Shrestha, Pan Liu, German Ros, Kai Yuan, Alan Fern

This work focuses on generating realistic, physically-based human behaviors from multi-modal inputs, which may only partially specify the desired motion. For example, the input may come from a VR controller providing arm motion and body velocity, partial key-point animation, computer vision applied to videos, or even higher-level motion goals. This requires a versatile low-level humanoid controller that can handle such sparse, under-specified guidance, seamlessly switch between skills, and recover from failures. Current approaches for learning humanoid controllers from demonstration data capture some of these characteristics, but none achieve them all. To this end, we introduce the Masked Humanoid Controller (MHC), a novel approach that applies multi-objective imitation learning on augmented and selectively masked motion demonstrations. The training methodology results in an MHC that exhibits the key capabilities of catch-up to out-of-sync input commands, combining elements from multiple motion sequences, and completing unspecified parts of motions from sparse multimodal input. We demonstrate these key capabilities for an MHC learned over a dataset of 87 diverse skills and showcase different multi-modal use cases, including integration with planning frameworks to highlight MHC’s ability to solve new user-defined tasks without any finetuning.

Casper van Engelenburg, Fatemeh Mostafavi, Emanuel Kuhn, Yuntae Jeon, Michael Franzen, Matthias Standfest, Jan van Gemert, Seyran Khademi

Diverse and realistic floor plan data are essential for the development of useful computer-aided methods in architectural design. Today's large-scale floor plan datasets predominantly feature simple floor plan layouts, typically representing single-apartment dwellings only. To compensate for the mismatch between current datasets and the real world, we develop \textbf{Modified Swiss Dwellings} (MSD) -- the first large-scale floor plan dataset that contains a significant share of layouts of multi-apartment dwellings. MSD features over 5.3K floor plans of medium- to large-scale building complexes, covering over 18.9K distinct apartments. We validate that existing approaches for floor plan generation, while effective in simpler scenarios, cannot yet seamlessly address the challenges posed by MSD. Our benchmark calls for new research in floor plan machine understanding. Code and data are open.

Jin Chen

This paper presents an optimized approach for the AI-generated image detection task in the 2024 ACM Multimedia Grand Challenge. Given the rapidly evolving capabilities of generative models, traditional detection methods often struggle with accuracy and generalization. The proposed solution builds upon the baseline by integrating advanced model architecture enhancements and novel detection modules, specifically designed to address the complexities of AI-generated images. Through rigorous testing, the approach demonstrates significant improvements in precision, particularly in identifying images produced by unknown generative models. This work highlights the critical need for adaptable and robust detection methods to keep pace with the advancements in AI-generated content and sets a new standard for future research and development in this domain.

Jingyu Wei, Yi Su 0010, Kele Xu, Lingbin Zeng, Bo Liu 0014, Huaimin Wang 0001

Multimodal Large Language Models (MLLMs), by expanding the model's capabilities to perceive and interact through multi-modalities, have significantly enhanced performance across various tasks. The perception of vision is an important modality developed into LLM, enabling research in vision-language to continuously lead the cutting-edge advancements in the MLLM community. However, the standard pre-training pipeline on image-text pairs results in a limited model understanding of relationships between multiple images and texts, as well as visual details. Additionally, the setting of fine-tuning with a frozen visual backbone hinders the enhancement of visual representations on new data. These two issues lead to suboptimal performance in models for demonstrative instruction following about multiple images. This work introduces a novel framework called MLoEM, which first converts long multimodal data into an interleaved image-instruction format, and then adopts a fully autoregressive architecture model, allowing for more robust and coherent learning from naturally occurring multimodal documents than pair-based pipeline. Additionally, we incorporate the Low-Rank Adaptation (LoRA) fine-tuning method, enhancing visual representations while maintaining the stability of previously learned knowledge. Finally, we utilize ensemble methods to enhance model performance on tasks. To alleviate the storage overhead issue of parallel ensembles with large models, we design an ensemble approach that shares the MLLM while only switching the LoRA matrices. In the experiments, the proposed MLoEM shows superior performance on the testing set.

Philipp Müller 0001, Michal Balazia, Tobias Baur 0001, Michael Dietz, Alexander Heimerl, Anna Penzkofer, Dominik Schiller, François Brémond, Jan Alexandersson, Elisabeth André 等

Estimating the momentary level of participant's engagement is an important prerequisite for assistive systems that support human interactions. Previous work has addressed this task in within-domain evaluation scenarios, i.e. training and testing on the same dataset. This is in contrast to real-life scenarios where domain shifts between training and testing data frequently occur. With MultiMediate'24, we present the first challenge addressing multi-domain engagement estimation. As training data, we utilise the NOXI database of dyadic novice-expert interactions. In addition to within-domain test data, we add two new test domains. First, we introduce recordings following the NOXI protocol but covering languages that are not present in the NOXI training data. Second, we collected novel engagement annotations on the MPIIGroupInteraction dataset which consists of group discussions between three to four people. In this way, MultiMediate'24 evaluates the ability of approaches to generalise across factors such as language and cultural background, group size, task, and screen-mediated vs. face-to-face interaction. This paper describes the MultiMediate'24 challenge and presents baseline results. In addition, we discuss selected challenge solutions.

Yuning Wu 0001, Jiatong Shi, Yifeng Yu, Yuxun Tang, Tao Qian, Yueqian Lin, Jionghao Han, Xinyi Bai, Shinji Watanabe 0001, Qin Jin

This research presents Muskits-ESPnet, a versatile toolkit that introduces new paradigms to Singing Voice Synthesis (SVS) through the application of pretrained audio models in both continuous and discrete approaches. Specifically, we explore discrete representations derived from SSL models and audio codecs and offer significant advantages in versatility and intelligence, supporting multi-format inputs and adaptable data processing workflows for various SVS models. The toolkit features automatic music score error detection and correction, as well as a perception auto-evaluation module to imitate human subjective evaluating scores. Muskits-ESPnet is available at https://github.com/espnet/espnet.

Jiyi Zhang, Han Fang 0004, Ee-Chien Chang

Understanding the correct input domain for black-box models is vital for tasks such as model cloning, inversion, and membership inference. However, this area remains underexplored, hindering related methods' efficacy without domain information. In this paper, we highlight the need for discovering the data domain and propose an approach that leverages existing generative models to address this challenge. With hard-label black-box access to a neural network model, our method produces a set of embeddings that, when utilized with the generative model, yield samples closely aligned with each target class's data domain, facilitating downstream tasks. Central to our method is an objective function covering both functional relevance and embedding generality. We employ an iterative search algorithm to identify the optimal set of embeddings. Starting with initial embeddings, new data points are generated and classified by the target model. Successful classifications guide embedding resampling, refining subsequent iterations' generated images closer to the target class's data domain. Consequently, the embeddings are iteratively modified to better match the data domain of the target class. Given the vast embedding space, we introduce an optional preprocessing phase. This phase leverages a comprehensive corpus like ImageNet to select a representative subset of samples, roughly aligned with the model's input domain, to serve as starting points.

Carlos de la Torre-Ortiz, Tuukka Ruotsalo

Visual similarity estimation plays a fundamental role both in human cognition and multimedia information processing as it is the basis for many applications ranging from image search and recommendation to visual content generation. Existing computational models to assess visual similarity often diverge from human perception as they are typically trained solely on image data without information about how humans perceive image similarity. Here, we present an approach for learning perceptual visual similarity from brain recordings obtained via electroencephalogram (EEG). Our approach establishes a mapping between similarity reflected in the human cognitive system and a latent image representation. We evaluate the approach in two tasks. First, predicting visual distance from EEG data and second, adjusting a latent representation of a generative model to generate new images at a predicted distance from a given source image. Experiments demonstrate that the predicted distances from EEG closely align with the ground truth distances, and images generated using these predicted distances closely resemble the ground truth images. These findings open new possibilities for leveraging signals measured from human cognition to infer similarity as opposed to using only content-based models.

Guogang Zhu, Xuefeng Liu 0001, Jianwei Niu 0002, Shaojie Tang 0001, Xinghao Wu, Jiayuan Zhang 0001

In personalized federated learning (PFL), it is widely recognized that achieving both high model generalization and effective personalization poses a significant challenge due to their conflicting nature. As a result, existing PFL methods can only manage a trade-off between these two objectives. This raises an interesting question: Is it feasible to develop a model capable of achieving both objectives simultaneously? Our paper presents an affirmative answer, and the key lies in the observation that deep models inherently exhibit hierarchical architectures, which produce representations with various levels of generalization and personalization at different stages. A straightforward approach stemming from this observation is to select multiple representations from these layers and combine them to concurrently achieve generalization and personalization. However, the number of candidate representations is commonly huge, which makes this method infeasible due to high computational costs. To address this problem, we propose DualFed, a new method that can directly yield dual representations correspond to generalization and personalization respectively, thereby simplifying the optimization task. Specifically, DualFed inserts a personalized projection network between the encoder and classifier. The pre-projection representations are able to capture generalized information shareable across clients, and the post-projection representations are effective to capture task-specific information on local clients. This design minimizes the mutual interference between generalization and personalization, thereby achieving a win-win situation. Extensive experiments show that DualFed can outperform other FL methods. Code is available at https://github.com/GuogangZhu/DualFed.

Lingfei Ren, Ruimin Hu, Zheng Wang 0007, Yilin Xiao 0002, Dengshi Li, Junhang Wu, Yilong Zang, Jinzhang Hu, Zijun Huang

Graph-based fraud detection (GFD) has garnered increasing attention due to its effectiveness in identifying fraudsters within multimedia data such as online transactions, product reviews, or telephone voices. However, the prevalent in-distribution (ID) assumption significantly impedes the generalization of GFD approaches to out-of-distribution (OOD) scenarios, which is a pervasive challenge considering the dynamic nature of fraudulent activities. In this paper, we introduce the Heterophilic Graph Invariant Learning Framework (HGIF), a novel approach to bolster the OOD generalization of GFD. HGIF addresses two pivotal challenges: creating diverse virtual training environments and adapting to varying target distributions. Leveraging edge-aware augmentation, HGIF efficiently generates multiple virtual training environments characterized by generalized heterophily distributions, thereby facilitating robust generalization against fraud graphs with diverse heterophily degrees. Moreover, HGIF employs a shared dual-channel encoder with heterophilic graph contrastive learning, enabling the model to acquire stable high-pass and low-pass node representations during training. During the Test-time Training phase, the shared dual-channel encoder is flexibly fine-tuned to adapt to the test distribution through graph contrastive learning. Extensive experiments showcase HGIF's superior performance over existing methods in OOD generalization, setting a new benchmark for GFD in OOD scenarios.

Jiancheng Huang, Mingfu Yan, Songyan Chen, Yi Huang 0035, Shifeng Chen

Amid the surge in generic text-to-video generation, the field of personalized human video generation has witnessed notable advancements, primarily concentrated on single-person scenarios. However, to our knowledge, the domain of two-person interactions, particularly in the context of martial arts combat, remains uncharted. We identify a significant gap: existing models for single-person dancing generation prove insufficient for capturing the subtleties and complexities of two engaged fighters, resulting in challenges such as identity confusion, anomalous limbs, and action mismatches. To address this, we introduce a pioneering new task, Personalized Martial Arts Combat Video Generation. Our approach, MagicFight, is specifically crafted to overcome these hurdles. Given this pioneering task, we face a lack of appropriate datasets. Thus, we generate a bespoke dataset using the game physics engine Unity, meticulously crafting a multitude of 3D characters, martial arts moves, and scenes designed to represent the diversity of combat. MagicFight refines and adapts existing models and strategies to generate high-fidelity two-person combat videos that maintain individual identities and ensure seamless, coherent action sequences, thereby laying the groundwork for future innovations in the realm of interactive video content creation.

Wei Lou, Guanbin Li, Xiang Wan, Haofeng Li

Whole-slide image (WSI) classification methods play a crucial role in tumor diagnosis. Most of them use hematoxylin and eosin (H&E) stained images, while Immunohistochemistry (IHC) staining provides molecular markers and protein expression information that highlights cancer regions. However, obtaining IHC-stained images requires higher costs in practice. In this work, we propose a multi-modal denoising diffusion pre-training framework that harnesses the advantages of IHC staining to learn visual representations. The framework is trained with the H&E-to-IHC re-staining task and IHC-stained image reconstruction task, which helps capture the structural similarity and staining difference between two image modalities. The trained model can then provide IHC-guided features, by taking only H&E-stained images as inputs. Besides, we build a new class-constraint constrastive loss to achieve the semantic consistency between dual-modal features from our pre-training framework. To integrate with WSI classifiers based on multi-instance learning, we further propose a bag feature augmentation strategy to extend bags with the features extracted by our pre-trained model. Experimental results on three datasets show that our pre-training framework effectively improves WSI classification and surpasses the state-of-the-art pre-training approaches. Code and model are released via https://github.com/lhaof/MDDP

Stanislav Frolov, Brian B. Moser, Sebastian Palacio, Andreas Dengel 0001

We present ObjBlur, a novel curriculum learning approach to improve layout-to-image generation models, where the task is to produce realistic images from layouts composed of boxes and labels. Our method, based on progressive object-level blurring, effectively stabilizes training and enhances the quality of generated images. This strategy systematically applies varying degrees of blurring to individual objects or the background during training, starting with strong blurring to progressively cleaner images. Our findings reveal significant performance improvements, stabilized training, smoother convergence, and reduced variance between multiple runs. Moreover, our technique is compatible with generative adversarial networks and diffusion models, highlighting its versatility across generative modeling paradigms. We reach new state-of-the-art results on the complex COCO and Visual Genome datasets.

Zhaoda Ye, Xinhan Zheng, Yang Liu 0105, Yuxin Peng 0001

Text-driven 3D indoor scene generation aims to automatically generate and arrange the objects, which form a 3D scene that accurately captures the semantics detailed in the given text description. Recent works have shown the potential to generate 3D scenes guided by specific object categories and room layouts but lack a robust mechanism to maintain consistent spatial relationships in alignment with the provided text description during the 3D scene generation. Besides, the annotations of the object and relationships of the 3D scenes are usually time- and cost-consuming, which are not easily obtained for the model training. Thus, in this paper, we conduct a dataset and benchmark for assessing spatial relations in text-driven 3D scene generation, which contains a comprehensive collection of 3D scenes, including textual descriptions, annotating object spatial relations, and providing both template and free-form natural language descriptions. We also provide a pseudo description feature generation method to address the 3D scenes without language annotations. We design an aligned latent space for spatial relation in 3D scenes and text description, in which we can sample the features according to the spatial relation for the few-shot learning. We also propose new metrics to investigate the ability of the approach to generate correct spatial relationships among objects.

Henglei Lv, Jiayu Xiao, Liang Li 0003

Diffusion-based text-to-image personalization has achieved great success in generating user-specified subjects in various contexts. However, finetuning-based methods often suffer from model overfitting, leading to reduced generative diversity, particularly when the provided subject images are limited. To address this issue, we introduce Pick-and-Draw, a training-free semantic guidance approach that enhances identity consistency and generative diversity. Our method comprises two key components: appearance-picking guidance and layout-drawing guidance. In the appearance-picking phase, we create an appearance palette from visual features of the reference image, selecting local patterns to maintain consistent subject identity. In the layout-drawing phase, we use a generative template from the base diffusion model to sketch the subject shape and scene outline, leveraging its strong image prior to produce diverse contexts based on various text prompts. Pick-and-Draw can be seamlessly integrated with any personalized diffusion model and requires only a single reference image. Both qualitative and quantitative evaluations demonstrate that our approach significantly improves identity consistency and generative diversity, establishing a new Pareto frontier in the balance between subject fidelity and image-text alignment.

Zhongwei Xuan, Zunjie Zhu, Shuai Wang 0003, Haibing Yin, Hongkui Wang, Ming Lu 0002

In recent years, neural field-based methods for synthesizing novel views have gained popularity due to their exceptional rendering quality and fast training speed. However, the computational cost of volumetric rendering has significantly increased with the advancement of camera technology and the subsequent rise in average camera resolution. Despite extensive efforts to accelerate the training process, the training duration remains unacceptable for high-resolution inputs. Therefore, it's crucial to develop efficient sampling methods to optimize the learning process of neural fields from large inputs. In this paper, we present a new technique called Superpixel-based Efficient Sampling (SES) to improve the learning efficiency of neural fields. Our approach optimizes pixel-level ray sampling by segmenting the error map into multiple superpixels and dynamically updating their errors during training to increase ray sampling in superpixel areas with higher rendering errors. Compared with other methods, our approach leverages the flexibility of superpixels, effectively reducing redundant sampling while considering local information. Our method not only speeds up the learning process but also enhances the rendering quality learned from large inputs. We conduct extensive experiments to evaluate the effectiveness of our method across several baselines and datasets. The code will be released.