Multimodal Emotion Recognition in Conversations (ERC) is a typical multimodal learning task in exploiting various data modalities concurrently. Prior studies on effective multimodal ERC encounter challenges in addressing modality imbalances and optimizing learning across modalities. Dealing with these problems, we present a novel framework named Ada2I, which consists of two inseparable modules namely Adaptive Feature Weighting (AFW) and Adaptive Modality Weighting (AMW) for feature-level and modality-level balancing respectively via leveraging both Inter- and Intra-modal interactions. Additionally, we introduce a refined disparity ratio as part of our training optimization strategy, a simple yet effective measure to assess the overall discrepancy of the model's learning process when handling multiple modalities simultaneously. Experimental results validate the effectiveness of Ada2I with state-of-the-art performance compared to baselines on three benchmark datasets, particularly in addressing modality imbalances.
论文检索
输入标题、作者或关键词，从 12,319 篇学术成果中精准定位
Large-scale pre-trained audio-language models excel in general multi-modal representation, facilitating their adaptation to downstream audio recognition tasks in a data-efficient manner. However, existing few-shot audio recognition methods based on audio-language models primarily focus on learning coarse-grained correlations, which are not sufficient to capture the intricate matching patterns between the multi-level information of audio and the diverse characteristics of category concepts. To address this gap, we propose multi-grained correspondence learning for bootstrapping audio-language models to improve audio recognition with few training samples. This approach leverages generative models to enrich multi-modal representation learning, mining the multi-level information of audio alongside the diverse characteristics of category concepts. Multi-grained matching patterns are then established through multi-grained key-value cache and multi-grained cross-modal contrast, enhancing the alignment between audio and category concepts. Additionally, we incorporate optimal transport to tackle temporal misalignment and semantic intersection issues in fine-grained correspondence learning, enabling flexible fine-grained matching. Our method achieves state-of-the-art results on multiple benchmark datasets for few-shot audio recognition, with comprehensive ablation experiments validating its effectiveness.
Video moment localization (VML) aims to identify the temporal boundary semantically matching the given query. Point-supervised VML balances localization accuracy and annotation cost but is still immature due to granularity alignment and scale perception issues. To this end, we propose a Semantic Granularity and Scale Correspondence Integration (SG-SCI) framework aimed at leveraging limited single-frame annotation for correspondence learning. It explicitly models semantic relations of different feature granularities and adaptively mines the implicit semantic scale, thereby enhancing feature representations of varying granularities and scales. SG-SCI uses granularity correspondence alignment to align semantics via latent prior knowledge and a scale correspondence learning to identify and address semantic scale differences. Extensive experiments on benchmark datasets have demonstrated the promising performance of our model over several state-of-the-art competitors.
Image-text retrieval stands as a pivotal task within information retrieval, gaining increasing importance with the rapid advancements in Visual-Language Pretraining models. However, current benchmarks for evaluating these models face limitations, exemplified by instances such as BLIP2 achieving near-perfect performance on existing benchmarks. In response, this paper advocates for a more robust evaluation benchmark for image-text retrieval, one that embraces several essential characteristics. Firstly, a comprehensive benchmark should cover a diverse range of tasks in both perception and cognition-based retrieval. Recognizing this need, we introduce ReCoS, a novel benchmark specifically designed for cross-modal image-text retrieval in complex real-life scenarios. Unlike existing benchmarks, ReCoS encompasses 12 retrieval tasks, with a particular focus on three cognition-based tasks, providing a more holistic assessment of model capabilities. To ensure the novelty of the benchmark, we emphasize the use of original data sources, steering clear of reliance on existing publicly available datasets to minimize the risk of data leakage. Additionally, to strike a balance between the complexity of the real world and benchmark usability, ReCoS includes text descriptions that are neither overly detailed, making retrieval overly simplistic, nor under-detailed to the point where retrieval becomes impossible. Our evaluation results shed light on the challenges faced by existing methods, especially in cognition-based retrieval tasks within ReCoS. This underscores the necessity for innovative approaches in addressing the complexities of image-text retrieval in real-world scenarios. Our code and benchmark datasets are available for further research and development in this field https://github.com/Bruce-XJChen/ReCos
Reducing the atmospheric haze and enhancing image clarity is crucial for computer vision applications. The lack of real-life hazy ground truth images necessitates synthetic datasets, which often lack diverse haze types, impeding effective haze type classification and dehazing algorithm selection. This research introduces the HazeSpace2M dataset, a collection of over 2 million images designed to enhance dehazing through haze type classification. HazeSpace2M includes diverse scenes with 10 haze intensity levels, featuring Fog, Cloud, and Environmental Haze (EH). Using the dataset, we introduce a technique of haze type classification followed by specialized dehazers to clear hazy images. Unlike conventional methods, our approach classifies haze types before applying type-specific dehazing, improving clarity in real-life hazy images. Benchmarking with state-of-the-art (SOTA) models, ResNet50 and AlexNet achieve 92.75% and 92.50% accuracy, respectively, against existing synthetic datasets. However, these models achieve only 80% and 70% accuracy, respectively, against our Real Hazy Testset (RHT), highlighting the challenging nature of our HazeSpace2M dataset. Additional experiments show that haze type classification followed by specialized dehazing improves results by 2.41% in PSNR, 17.14% in SSIM, and 10.2% in MSE over general dehazers. Moreover, when testing with SOTA dehazing models, we found that applying our proposed framework significantly improves their performance. These results underscore the significance of HazeSpace2M and our proposed framework in addressing atmospheric haze in multimedia processing. Complete code and dataset is available on GitHub (https://github.com/tanvirnwu/HazeSpace2M).
Detecting out-of-distribution (OOD) inputs is a principal task for ensuring the safety of deploying deep-neural-network classifiers in open-set scenarios. OOD samples can be drawn from arbitrary distributions and exhibit deviations from in-distribution (ID) data in various dimensions, such as foreground features (e.g., objects in CIFAR100 images vs. those in CIFAR10 images) and background features (e.g., textural images vs. objects in CIFAR10). Existing methods can confound foreground and background features in training, failing to utilize the background features for OOD detection. This paper considers the importance of feature disentanglement in out-of-distribution detection and proposes the simultaneous exploitation of both foreground and background features to support the detection of OOD inputs in in out-of-distribution detection. To this end, we propose a novel framework that first disentangles foreground and background features from ID training samples via a dense prediction approach, and then learns a new classifier that can evaluate the OOD scores of test images from both foreground and background features. It is a generic framework that allows for a seamless combination with various existing OOD detection methods. Extensive experiments show that our approach 1) can substantially enhance the performance of four different state-of-the-art (SotA) OOD detection methods on multiple widely-used OOD datasets with diverse background features, and 2) achieves new SotA performance on these benchmarks. Code is available at https://github.com/mala-lab/DFB.
Visual abduction reasoning aims to find the most plausible explanation for incomplete observations, and suffers from inherent uncertainties and ambiguities, which mainly stem from the latent causal relations, incomplete observations, and the reasoning itself. To address this, we propose a probabilistic model named Uncertainty-Guided Probabilistic Distillation Transformer (UPD-Trans) to model uncertainties for Visual Abductive Reasoning. In order to better discover the correct cause-effect chain, we model all the potential causal relations into a unified reasoning framework, thus both the direct relations and latent relations are considered. In order to reduce the effect of the stochasticity and uncertainty for reasoning: 1) we extend the deterministic Transformer to a probabilistic Transformer by considering those uncertain factors as Gaussian random variables and explicitly modeling their distribution; 2) we introduce a distillation mechanism between the posterior branch with complete observations and the prior branch with incomplete observations to transfer posterior knowledge. Evaluation results on the benchmark datasets, consistently demonstrate the commendable performance of our UPD-Trans, with significant improvements after latent relation modeling and uncertainty modeling.
Recently, the Parameter Efficient Fine-Tuning (PEFT) method, which adjusts or introduces fewer trainable parameters to calibrate pre-trained models on downstream tasks, has been a hot research topic. However, existing PEFT methods within the traditional fine-tuning framework have two main shortcomings: 1) They overlook the explicit association between trainable parameters and downstream knowledge. 2) They neglect the interaction between the intrinsic task-agnostic knowledge of pre-trained models and the task-specific knowledge of downstream tasks. These oversights lead to insufficient utilization of knowledge and suboptimal performance. To address these issues, we propose a novel fine-tuning framework, named GIST, that can be seamlessly integrated into the current PEFT methods in a plug-and-play manner. Specifically, our framework first introduces a trainable token, called the Gist token, when applying PEFT methods on downstream tasks. This token serves as an aggregator of the task-specific knowledge learned by the PEFT methods and builds an explicit association with downstream tasks. Furthermore, to facilitate explicit interaction between task-agnostic and task-specific knowledge, we introduce the concept of knowledge interaction via a Bidirectional Kullback-Leibler Divergence objective. As a result, PEFT methods within our framework can enable the pre-trained model to understand downstream tasks more comprehensively by fully leveraging both types of knowledge. Extensive experiments on the 35 datasets demonstrate the universality and scalability of our framework. Notably, the PEFT method within our GIST framework achieves up to a 2.25% increase on the VTAB-1K benchmark with an addition of just 0.8K parameters (0.009 of ViT-B/16). The code is available at https://github.com/JCruan519/GIST.
Multilingual text recognition (MLTR) is increasingly essential for facilitating cultural communication. However, existing methods often struggle with retaining previous knowledge when learning new languages. A straightforward solution is performing incremental learning (IL) on MLTR tasks. However, it ignores the shared words and characters across incremental languages, which we first term as an incremental sharing problem. Motivated by this observation, we propose HierArchicalMulti-label learning framework for Multilingual tExt Recognition, termed HAMMER. An online knowledge analysis is designed to identify shared knowledge and provide corresponding multi-label language supervision. Specifically, only words and characters appearing simultaneously in multiple languages are considered shared knowledge. Additionally, to further capture language dependencies, we introduce a hierarchical language evaluation mechanism to predict language scores at word and character levels. These scores, supervised by the knowledge analysis, guide the specific recognizers to effectively utilize both old and new language knowledge, thereby mitigating catastrophic forgetting caused by imbalanced rehearsal sets. Extensive experiments conducted on benchmark datasets, MLT17 and MLT19, show that HAMMER exhibits remarkable results and outperforms other state-of-the-art approaches.
In recent years, multi-view outlier detection (MVOD) methods have advanced significantly, aiming to identify outliers within multi-view datasets. A key point is to better detect class outliers and class-attribute outliers, which only exist in multi-view data. However, existing methods either is not able to reduce the impact of outliers when learning view-consistent information, or struggle in cases with varying neighborhood structures. Moreover, most of them do not apply to partial multi-view data in real-world scenarios. To overcome these drawbacks, we propose a novel method named Regularized Contrastive Partial Multi-view Outlier Detection (RCPMOD). In this framework, we utilize contrastive learning to learn view-consistent information and distinguish outliers by the degree of consistency. Specifically, we propose (1) An outlier-aware contrastive loss with a potential outlier memory bank to eliminate their bias motivated by a theoretical analysis. (2) A neighbor alignment contrastive loss to capture the view-shared local structural correlation. (3) A spreading regularization loss to prevent the model from overfitting over outliers. With the Cross-view Relation Transfer technique, we could easily impute the missing view samples based on the features of neighbors. Experimental results on four benchmark datasets demonstrate that our proposed approach could outperform state-of-the-art competitors under different settings.
Enhancing Images with Coupled Low-Resolution and Ultra-Dark Degradations: A Tri-level Learning Framework
PDF ↗Due to device constraints and lighting conditions, captured images frequently exhibit coupled low-resolution and ultra-dark degradations. Enhancing the visibility and resolution of ultra-dark images simultaneously is crucial for practical applications. Current approaches often address both tasks in isolation or through simplistic cascading strategies, while also relying heavily on empirical and manually designed composite loss constraints, which inevitably results in compromised training efficacy, increased artifacts, and diminished detail fidelity. To address these issues, we propose TriCo, the first to adopt a Tri -level learning framework that explicitly formulates the bidirectional Co operative relationship and devises algorithms to tackle coupled degradation factors. In the optimization across Upper (U)-Middle (M)-Lower (L) levels, we model the synergistic dependencies between illumination learning and super-resolution tasks within the M-L levels. Moving to the U-M levels, we introduce hyper-variables to automate the learning of beneficial constraints for both learning tasks, moving beyond the traditional trial-and-error pitfalls of the learning process. Algorithmically, we establish a Phased Gradient-Response (PGR) algorithm as our training mechanism, which facilitates a dynamic, inter-variable gradient feedback and ensures efficient and rapid convergence. Moreover, we merge inherent illumination priors with universal semantic model features to adaptively guide pixel-level high-frequency detail recovery. Extensive experimentation validates the framework's broad generalizability across challenging ultra-dark scenarios, outperforming current state-of-the-art methods across 4 real and synthetic benchmark datasets over 6 metrics (e.g., 5.8%← in PSNR and 26.6%← in LPIPS).
Video harmonization aims to address the discrepancy in color and lighting between foreground and background elements within video compositions, thereby enhancing the innate coherence of composite video content. Nevertheless, existing methods struggle to effectively handle video composite tasks with excessively large-scale foregrounds. In this paper, we propose Video Harmonization Masked Autoencoders (VHMAE), a simple yet powerful end-to-end video harmonization method designed to tackle this challenge once and for all. Unlike other typically MAE-based methods employing random or tube masking strategies, we innovative treat all foregrounds in each frame required for harmonization as prediction regions, which are designated as masked tokens and fed into our network to produce the final refinement video. To this end, the network is optimized to prioritize the harmonization task, proficiently reconstructing the masked region despite the limited background information. Specifically, we introduce the Pattern Alignment Module (PAM) to extract content information from the extensive masked foreground region, aligning the latent semantic features of the masked foreground content with the background context while disregarding the impact of various colors or illumination. Moreover, We propose the Patch Balancing Loss, which effectively mitigates the undesirable grid-like artifacts commonly observed in MAE-based approaches for image generation, thereby ensuring consistency between the predicted foreground and the visible background. Additionally, we introduce a real-composited video harmonization dataset named RCVH, which serves as a valuable benchmark for assessing the efficacy of techniques aimed at video harmonization across different real video sources. Comprehensive experiments demonstrate that our VHMAE outperforms state-of-the-art techniques on both RCVH and HYouTube datasets.
Remarkable progresses have been made in hyperspectral image (HSI) denoising. However, the majority of existing methods are predominantly confined to the spatial-spectral domain, overlooking the untapped potential inherent in the Fourier domain. This paper presents a novel approach to address HSI denoising by bridging the information from the Fourier and spatial-spectral domains. Our method highlights key insights into the Fourier properties within spatial and spectral domains through the Fourier transform. Specifically, we note that the amplitude inherently embody noise and photon reflection characteristics, while the phase holds structural information. These insights unveil new perspectives on the physical properties of HSIs, motivating us to leverage complementary information exchange between Fourier and spatial-spectral domains. To this end, we introduce the Fourier-prior Integration Denoising Network (FIDNet), a potent yet straightforward approach that utilizes Fourier insights to synergistically interact with spatial-spectral domains for superior HSI denoising. In FIDNet, we independently extract spatial and Fourier features through dual branches and merge these representations to enhance spectral evolution modeling through the inherent structure consistency constraints and continuing reflection variation revealed in Fourier prior. Our proposed method demonstrates robust generalization across synthetic and real-world benchmark datasets, achieves comparable results with state-of-the-art methods in both quantitative quality and visual results. The code is available at https://github.com/MIV-XJTU/FIDNet.
Large pre-trained vision-language models like CLIP have shown amazing zero-shot recognition performance. To adapt pre-trained vision-language models to downstream tasks, recent studies have focused on the learnable context + class name paradigm, which learns continuous prompt contexts on downstream datasets. In practice, the learned prompt context tends to overfit the base categories and cannot generalize well to novel categories out of the training data. Recent works have also noticed this problem and have proposed several improvements. In this work, we draw a new insight based on empirical analysis, that is, uninformative class names lead to degraded base-to-novel generalization performance in prompt learning, which is usually overlooked by existing works. Under this motivation, we advocate to improve the base-to-novel generalization performance of prompt learning by enhancing the semantic richness of class names. We coin our approach as the Information Disengagement based Associative Prompt Learning (IDAPL) mechanism which considers the associative, meanwhile, decoupled learning of prompt context and class name embedding. IDAPL can effectively alleviate the phenomenon of learnable context overfitting to base classes, meanwhile, learning more informative semantic representation of base classes by fine-tuning the class name embedding, leading to improved performance on both base and novel classes. Experimental results on eleven widely used few-shot learning benchmarks clearly validate the effectiveness of our proposed approach. Code is available at https://github.com/tiggers23/IDAPL
In recent years, the Few-Shot Fine-Grained Image Classification (FS-FGIC) problem has gained widespread attention. A number of effective methods have been proposed that focus on extracting discriminative information within high-level features in a single episode/task. However, this is insufficient for addressing the cross-task challenges of FS-FGIC, which is represented in two aspects. On the one hand, from the perspective of the Fine-Grained Image Classification (FGIC) task, there is a need to supplement the model with mid-level features containing rich fine-grained information. On the other hand, from the perspective of the Few-Shot Learning (FSL) task, explicit modeling of cross-task general knowledge is required. In this paper, we propose a novel Bi-directional Task-Guided Network (BTG-Net) to tackle these issues. Specifically, from the FGIC task perspective, we design the Semantic-Guided Noise Filtering (SGNF) module to filter noise on mid-level features rich in detailed information. Further, from the FSL task perspective, the General Knowledge Prompt Modeling (GKPM) module is proposed to retain the cross-task general knowledge by utilizing the prompting mechanism, thereby enhancing the model's generalization performance on novel classes. We have conducted extensive experiments on five fine-grained benchmark datasets, and the results demonstrate that BTG-Net outperforms state-of-the-art methods comprehensively.
We propose a method for lighting and shadow editing of outdoor disharmonious composite images, including foreground harmonization and cast shadow generation. Most existing works can only perform foreground appearance editing task or only focus on shadow generation. In fact, lighting not only affects the brightness and color of objects, but also produces corresponding cast shadows. In recent years, diffusion models have demonstrated their strong generative capabilities, and due to their iterative denoising properties, they have a significant advantage in image restoration task. But it fails to preserve content structure of image. To this end, we propose an effective model to tackle the problem of foreground lighting-shadow editing. Specifically, we use a coarse shadow prediction module (SP) to generate coarse shadows for foreground objects. Then, we use the predicted results as prior knowledge to guide the generation of harmony diffusion model. In this process, the primary task is to learn lighting variation to harmonize foreground regions, the secondary task is to generate high-quality cast shadow containing more details. Considering that existing datasets do not support the dual tasks of image harmonization and shadow generation, we construct a real outdoor dataset, named IH-SG, covering various lighting conditions. Extensive experiments conducted on existing benchmark datasets and the IH-SG dataset demonstrate the superiority of our method.
Learning to Correction: Explainable Feedback Generation for Visual Commonsense Reasoning Distractor
PDF ↗Large multimodal models (LMMs) have shown remarkable performance in the visual commonsense reasoning (VCR) task, which aims to answer a multiple-choice question based on visual commonsense within an image. However, the ability of LMMs to correct potential visual commonsense errors in the distractor upon their occurrence is yet under-explored. Drawing inspiration from how a human teacher crafts challenging distractors to test students' comprehension of the concepts or skills and assists them in identifying and correcting errors toward the answer, we are the pioneering research for LMMs to simulate this error correction process. To this end, we employ GPT-4 as a ''teacher'' to collect the explainable feedback dataset VCR-DF for error correction, which serves as a benchmark to evaluate the ability of LMMs to identify misconceptions and clarify reasons behind the error in VCR distractors toward final answers. In addition, we propose an LMM-based Pedagogical Expert Instructed Feedback Generation (PEIFG) model to incorporate the learnable expert prompts and multimodal instruction as guidance for feedback generation. Experimental results show that our PEIFG significantly outperforms existing LMMs. We believe that our benchmark provides a new direction for evaluating the capabilities of LMMs.
As a widely explored multi-modal task, 3D object grounding endeavors to localize a unique pre-existing object within a single 3D scene given a natural language description. However, such a strict setting is unnatural as it is not always possible to know whether a target object exists in a specific 3D scene. In real-world scenarios, a collection of 3D scenes is generally available, some of which may not contain the described object while some potentially contain multiple target objects. To this end, we introduce a more realistic setting, named Group-wise 3D Object Grounding, to simultaneously process a group of related 3D scenes, allowing a flexible number of target objects to exist in each scene. Instead of localizing target objects in each scene individually, we argue that ignoring the rich visual information contained in other related 3D scenes within the same group may lead to sub-optimal results. To achieve more accurate localization, we propose a baseline method named GNL3D, a Grouped Neural Listener for 3D grounding in the group-wise setting, which extends the traditional 3D object grounding pipeline with a novel language-guided consensus aggregation and distribution mechanism to explicitly exploit the intra-group visual connections. Specifically, based on context-aware spatial-semantic alignment, a language-guided consensus aggregation module is developed to aggregate the visual features of target objects in each 3D scene to form a visual consensus representation, which is then distributed and injected into a consensus-modulated feature refinement module for refining visual features, thus benefiting the subsequent multi-modal reasoning. To validate the effectiveness of the proposed method, we reorganize and enhance the ReferIt3D dataset and propose evaluation metrics to benchmark prior work and GNL3D. Extensive experiments demonstrate that GNL3D achieves state-of-the-art results on the group-wise setting and the traditional 3D object grounding task.
Temporal Automatic White Balance (TAWB) corrects the color cast within each frame, while ensuring consistent illumination across consecutive frames. Unlike conventional AWB, there has been limited research conducted on TAWB for an extended period. However, the growing popularity of short-form videos has increased focus on video color experiences. To further advance research on TAWB, we aim to address the bottlenecks associated with datasets, models, and benchmarks. 1) Dataset challenge: Currently, only one TAWB dataset (BCC), captured with a single camera, is available. It lacks temporal continuity due to challenges in capturing realistic illuminations and dynamic raw data. In response, we meticulously designed an acquisition strategy based on the actual distribution pattern of illuminations and created a comprehensive TAWB dataset named CTA comprising 6 cameras that offer 12K continuous illuminations. Furthermore, we employed video frame interpolation techniques, extending the captured static raw data into dynamic form and ensuring continuous illumination. 2) Model challenge: Among the two prevailing TAWB methods, both rely on LSTM. However, the fixed gating mechanism of LSTM often fails to adapt to varying content or illuminations, resulting in unstable illumination estimation. In response, we propose CTANet, which integrates cross-frame attention and RepViT for self-adjustment to content and illumination variations. Additionally, the mobile-friendly design of RepViT enhances the portability of CTANet. 3) Benchmark challenge: Currently, there is no benchmark of TAWB methods on illumination and camera types to date. Addressing this, a benchmark has been proposed by conducting a comparative analysis of 8 cutting-edge AWB and TAWB methods with CTANet across 3 typical illumination scenes and 7 cameras from two representative datasets. The dataset and code are available in https://github.com/ChunxiaoLe/CTA-Dataset.
3D facial animation has attracted considerable attention due to its extensive applications in the multimedia field. Audio-driven 3D facial animation has been widely explored with promising results. However, multi-modal 3D facial animation, especially text-guided 3D facial animation is rarely explored due to the lack of multi-modal 3D facial animation dataset. To fill this gap, we first construct a large-scale multi-modal 3D facial animation dataset, MMHead, which consists of 49 hours of 3D facial motion sequences, speech audios, and rich hierarchical text annotations. Each text annotation contains abstract action and emotion descriptions, fine-grained facial and head movements (i.e., expression and head pose) descriptions, and three possible scenarios that may cause such emotion. Concretely, we integrate five public 2D portrait video datasets, and propose an automatic pipeline to 1) reconstruct 3D facial motion sequences from monocular videos; and 2) obtain hierarchical text annotations with the help of AU detection and ChatGPT. Based on the MMHead dataset, we establish benchmarks for two new tasks: text-induced 3D talking head animation and text-to-3D facial motion generation. Moreover, a simple but efficient VQ-VAE-based method named MM2Face is proposed to unify the multi-modal information and generate diverse and plausible 3D facial motions, which achieves competitive results on both benchmarks. Extensive experiments and comprehensive analysis demonstrate the significant potential of our dataset and benchmarks in promoting the development of multi-modal 3D facial animation. The dataset will be released at: https://wsj-sjtu.github.io/MMHead/.