Search

Recent advancements in the field of No-Reference Image Quality Assessment (NR-IQA) using deep learning techniques demonstrate high performance across multiple open-source datasets. However, such models are typically very large and complex making them not so suitable for real-world deployment, especially on resource- and battery-constrained mobile devices. To address this limitation, we propose a compact, lightweight NR-IQA model that achieves state-of-the-art (SOTA) performance on ECCV AIM UHD-IQA challenge validation and test datasets while being also nearly 5.7 times faster than the fastest SOTA model. Our model features a dual-branch architecture, with each branch separately trained on synthetically and authentically distorted images which enhances the model's generalizability across different distortion types. To improve robustness under diverse real-world visual conditions, we additionally incorporate multiple color spaces during the training process. We also demonstrate the higher accuracy of recently proposed Kolmogorov-Arnold Networks (KANs) for final quality regression as compared to the conventional Multi-Layer Perceptrons (MLPs). Our evaluation considering various open-source datasets highlights the practical, high-accuracy, and robust performance of our proposed lightweight model. Code: https://github.com/nasimjamshidi/LAR-IQA.

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., Comment: arXiv admin note: text overlap with arXiv:2308.08256

Humans naturally perform audiovisual speech recognition (AVSR), enhancing the accuracy and robustness by integrating auditory and visual information. Spiking neural networks (SNNs), which mimic the brain's information-processing mechanisms, are well-suited for emulating the human capability of AVSR. Despite their potential, research on SNNs for AVSR is scarce, with most existing audio-visual multimodal methods focused on object or digit recognition. These models simply integrate features from both modalities, neglecting their unique characteristics and interactions. Additionally, they often rely on future information for current processing, which increases recognition latency and limits real-time applicability. Inspired by human speech perception, this paper proposes a novel human-inspired SNN named HI-AVSNN for AVSR, incorporating three key characteristics: cueing interaction, causal processing and spike activity. For cueing interaction, we propose a visual-cued auditory attention module (VCA2M) that leverages visual cues to guide attention to auditory features. We achieve causal processing by aligning the SNN's temporal dimension with that of visual and auditory features and applying temporal masking to utilize only past and current information. To implement spike activity, in addition to using SNNs, we leverage the event camera to capture lip movement as spikes, mimicking the human retina and providing efficient visual data. We evaluate HI-AVSNN on an audiovisual speech recognition dataset combining the DVS-Lip dataset with its corresponding audio samples. Experimental results demonstrate the superiority of our proposed fusion method, outperforming existing audio-visual SNN fusion methods and achieving a 2.27% improvement in accuracy over the only existing SNN-based AVSR method.

Language models have been effectively applied to modeling natural signals, such as images, video, speech, and audio. A crucial component of these models is the codec tokenizer, which compresses high-dimensional natural signals into lower-dimensional discrete tokens. In this paper, we introduce WavTokenizer, which offers several advantages over previous SOTA acoustic codec models in the audio domain: 1)extreme compression. By compressing the layers of quantizers and the temporal dimension of the discrete codec, one-second audio of 24kHz sampling rate requires only a single quantizer with 40 or 75 tokens. 2)improved subjective quality. Despite the reduced number of tokens, WavTokenizer achieves state-of-the-art reconstruction quality with outstanding UTMOS scores and inherently contains richer semantic information. Specifically, we achieve these results by designing a broader VQ space, extended contextual windows, and improved attention networks, as well as introducing a powerful multi-scale discriminator and an inverse Fourier transform structure. We conducted extensive reconstruction experiments in the domains of speech, audio, and music. WavTokenizer exhibited strong performance across various objective and subjective metrics compared to state-of-the-art models. We also tested semantic information, VQ utilization, and adaptability to generative models. Comprehensive ablation studies confirm the necessity of each module in WavTokenizer. The related code, demos, and pre-trained models are available at https://github.com/jishengpeng/WavTokenizer., Comment: Working in progress. arXiv admin note: text overlap with arXiv:2402.12208

Adding proper background music helps complete a short video to be shared. Towards automating the task, previous research focuses on video-to-music retrieval (VMR), aiming to find amidst a collection of music the one best matching the content of a given video. Since music tracks are typically much longer than short videos, meaning the returned music has to be cut to a shorter moment, there is a clear gap between the practical need and VMR. In order to bridge the gap, we propose in this paper video to music moment retrieval (VMMR) as a new task. To tackle the new task, we build a comprehensive dataset Ad-Moment which contains 50K short videos annotated with music moments and develop a two-stage approach. In particular, given a test video, the most similar music is retrieved from a given collection. Then, a Transformer based music moment localization is performed. We term this approach Retrieval and Localization (ReaL). Extensive experiments on real-world datasets verify the effectiveness of the proposed method for VMMR.

No-Reference Image Quality Assessment (NR-IQA) remains a challenging task due to the diversity of distortions and the lack of large annotated datasets. Many studies have attempted to tackle these challenges by developing more accurate NR-IQA models, often employing complex and computationally expensive networks, or by bridging the domain gap between various distortions to enhance performance on test datasets. In our work, we improve the performance of a generic lightweight NR-IQA model by introducing a novel augmentation strategy that boosts its performance by almost 28\%. This augmentation strategy enables the network to better discriminate between different distortions in various parts of the image by zooming in and out. Additionally, the inclusion of test-time augmentation further enhances performance, making our lightweight network's results comparable to the current state-of-the-art models, simply through the use of augmentations.

Image captioning, which generates natural language descriptions of the visual information in an image, is a crucial task in vision-language research. Previous models have typically addressed this task by aligning the generative capabilities of machines with human intelligence through statistical fitting of existing datasets. While effective for normal images, they may struggle to accurately describe those where certain parts of the image are obscured or edited, unlike humans who excel in such cases. These weaknesses they exhibit, including hallucinations and limited interpretability, often hinder performance in scenarios with shifted association patterns. In this paper, we present a generic image captioning framework that employs causal inference to make existing models more capable of interventional tasks, and counterfactually explainable. Our approach includes two variants leveraging either total effect or natural direct effect. Integrating them into the training process enables models to handle counterfactual scenarios, increasing their generalizability. Extensive experiments on various datasets show that our method effectively reduces hallucinations and improves the model's faithfulness to images, demonstrating high portability across both small-scale and large-scale image-to-text models. The code is available at https://github.com/Aman-4-Real/See-or-Guess., Comment: Accepted by ACM MM 2024

Rapid advancements have been made in extending Large Language Models (LLMs) to Large Multi-modal Models (LMMs). However, extending input modality of LLMs to video data remains a challenging endeavor, especially for long videos. Due to insufficient access to large-scale high-quality video data and the excessive compression of visual features, current methods exhibit limitations in effectively processing long videos. In this paper, we introduce Kangaroo, a powerful Video LMM aimed at addressing these challenges. Confronted with issue of inadequate training data, we develop a data curation system to build a large-scale dataset with high-quality annotations for vision-language pre-training and instruction tuning. In addition, we design a curriculum training pipeline with gradually increasing resolution and number of input frames to accommodate long videos. Evaluation results demonstrate that, with 8B parameters, Kangaroo achieves state-of-the-art performance across a variety of video understanding benchmarks while exhibiting competitive results on others. Particularly, on benchmarks specialized for long videos, Kangaroo excels some larger models with over 10B parameters and proprietary models.

Referring image segmentation (RIS) requires dense vision-language interactions between visual pixels and textual words to segment objects based on a given description. However, commonly adapted dual-encoders in RIS, e.g., Swin transformer and BERT (uni-modal encoders) or CLIP (a multi-modal dual-encoder), lack dense multi-modal interactions during pre-training, leading to a gap with a pixel-level RIS task. To bridge this gap, existing RIS methods often rely on multi-modal fusion modules that interact two encoders, but this approach leads to high computational costs. In this paper, we present a novel RIS method with a single-encoder, i.e., BEiT-3, maximizing the potential of shared self-attention across all framework components. This enables seamless interactions of two modalities from input to final prediction, producing granularly aligned multi-modal features. Furthermore, we propose lightweight yet effective decoder modules, a Shared FPN and a Shared Mask Decoder, which contribute to the high efficiency of our model. Our simple baseline with a single encoder achieves outstanding performances on the RIS benchmark datasets while maintaining computational efficiency, compared to the most recent SoTA methods based on dual-encoders., Comment: ArXiv pre-print

With the advancements in singing voice generation and the growing presence of AI singers on media platforms, the inaugural Singing Voice Deepfake Detection (SVDD) Challenge aims to advance research in identifying AI-generated singing voices from authentic singers. This challenge features two tracks: a controlled setting track (CtrSVDD) and an in-the-wild scenario track (WildSVDD). The CtrSVDD track utilizes publicly available singing vocal data to generate deepfakes using state-of-the-art singing voice synthesis and conversion systems. Meanwhile, the WildSVDD track expands upon the existing SingFake dataset, which includes data sourced from popular user-generated content websites. For the CtrSVDD track, we received submissions from 47 teams, with 37 surpassing our baselines and the top team achieving a 1.65% equal error rate. For the WildSVDD track, we benchmarked the baselines. This paper reviews these results, discusses key findings, and outlines future directions for SVDD research.

Text-to-image generation models have achieved remarkable advancements in recent years, aiming to produce realistic images from textual descriptions. However, these models often struggle with generating anatomically accurate representations of human hands. The resulting images frequently exhibit issues such as incorrect numbers of fingers, unnatural twisting or interlacing of fingers, or blurred and indistinct hands. These issues stem from the inherent complexity of hand structures and the difficulty in aligning textual descriptions with precise visual depictions of hands. To address these challenges, we propose a novel approach named Hand1000 that enables the generation of realistic hand images with target gesture using only 1,000 training samples. The training of Hand1000 is divided into three stages with the first stage aiming to enhance the model's understanding of hand anatomy by using a pre-trained hand gesture recognition model to extract gesture representation. The second stage further optimizes text embedding by incorporating the extracted hand gesture representation, to improve alignment between the textual descriptions and the generated hand images. The third stage utilizes the optimized embedding to fine-tune the Stable Diffusion model to generate realistic hand images. In addition, we construct the first publicly available dataset specifically designed for text-to-hand image generation. Based on the existing hand gesture recognition dataset, we adopt advanced image captioning models and LLaMA3 to generate high-quality textual descriptions enriched with detailed gesture information. Extensive experiments demonstrate that Hand1000 significantly outperforms existing models in producing anatomically correct hand images while faithfully representing other details in the text, such as faces, clothing, and colors., Comment: Project page https://haozhuo-zhang.github.io/Hand1000-project-page/

Video-based apparent affect detection plays a crucial role in video understanding, as it encompasses various elements such as vision, audio, audio-visual interactions, and spatiotemporal information, which are essential for accurate video predictions. However, existing approaches often focus on extracting only a subset of these elements, resulting in the limited predictive capacity of their models. To address this limitation, we propose a novel LSTM-based network augmented with a Transformer co-attention mechanism for predicting apparent affect in videos. We demonstrate that our proposed Sec2Sec Co-attention Transformer surpasses multiple state-of-the-art methods in predicting apparent affect on two widely used datasets: LIRIS-ACCEDE and First Impressions. Notably, our model offers interpretability, allowing us to examine the contributions of different time points to the overall prediction. The implementation is available at: https://github.com/nestor-sun/sec2sec., Comment: 5 pages, 3 figures

Designs and artworks are ubiquitous across various creative fields, requiring graphic design skills and dedicated software to create compositions that include many graphical elements, such as logos, icons, symbols, and art scenes, which are integral to visual storytelling. Automating the generation of such visual elements improves graphic designers' productivity, democratizes and innovates the creative industry, and helps generate more realistic synthetic data for related tasks. These illustration elements are mostly RGBA images with irregular shapes and cutouts, facilitating blending and scene composition. However, most image generation models are incapable of generating such images and achieving this capability requires expensive computational resources, specific training recipes, or post-processing solutions. In this work, we propose a fully-automated approach for obtaining RGBA illustrations by modifying the inference-time behavior of a pre-trained Diffusion Transformer model, exploiting the prompt-guided controllability and visual quality offered by such models with no additional computational cost. We force the generation of entire subjects without sharp croppings, whose background is easily removed for seamless integration into design projects or artistic scenes. We show with a user study that, in most cases, users prefer our solution over generating and then matting an image, and we show that our generated illustrations yield good results when used as inputs for composite scene generation pipelines. We release the code at https://github.com/aimagelab/Alfie., Comment: Accepted at ECCV AI for Visual Arts Workshop and Challenges

The rise of Extended Reality (XR) requires efficient streaming of 3D online worlds, challenging current 3DGS representations to adapt to bandwidth-constrained environments. This paper proposes LapisGS, a layered 3DGS that supports adaptive streaming and progressive rendering. Our method constructs a layered structure for cumulative representation, incorporates dynamic opacity optimization to maintain visual fidelity, and utilizes occupancy maps to efficiently manage Gaussian splats. This proposed model offers a progressive representation supporting a continuous rendering quality adapted for bandwidth-aware streaming. Extensive experiments validate the effectiveness of our approach in balancing visual fidelity with the compactness of the model, with up to 50.71% improvement in SSIM, 286.53% improvement in LPIPS, and 318.41% reduction in model size, and shows its potential for bandwidth-adapted 3D streaming and rendering applications.

The conventional training approach for image captioning involves pre-training a network using teacher forcing and subsequent fine-tuning with Self-Critical Sequence Training to maximize hand-crafted captioning metrics. However, when attempting to optimize modern and higher-quality metrics like CLIP-Score and PAC-Score, this training method often encounters instability and fails to acquire the genuine descriptive capabilities needed to produce fluent and informative captions. In this paper, we propose a new training paradigm termed Direct CLIP-Based Optimization (DiCO). Our approach jointly learns and optimizes a reward model that is distilled from a learnable captioning evaluator with high human correlation. This is done by solving a weighted classification problem directly inside the captioner. At the same time, DiCO prevents divergence from the original model, ensuring that fluency is maintained. DiCO not only exhibits improved stability and enhanced quality in the generated captions but also aligns more closely with human preferences compared to existing methods, especially in modern metrics. Additionally, it maintains competitive performance in traditional metrics. Our source code and trained models are publicly available at https://github.com/aimagelab/DiCO., Comment: BMVC 2024

The explosive growth of multimedia content in the digital economy era has brought challenges in content recognition, copyright protection, and data management. As an emerging content management technology, perceptual hash-based digital fingerprints, serving as compact summaries of multimedia content, have been widely adopted for efficient multimedia content identification and retrieval across different modalities (e.g., text, image, video, audio), attracting significant attention from both academia and industry. Despite the increasing applications of digital fingerprints, there is a lack of systematic and comprehensive literature review on multimedia digital fingerprints. This survey aims to fill this gap and provide an important resource for researchers studying the details and related advancements of multimedia digital fingerprints. The survey first introduces the definition, characteristics, and related concepts (including hash functions, granularity, similarity measures, etc.) of digital fingerprints. It then focuses on analyzing and summarizing the algorithms for extracting unimodal fingerprints of different types of digital content, including text fingerprints, image fingerprints, video fingerprints, and audio fingerprints. Particularly, it provides an in-depth review and summary of deep learning-based fingerprints. Additionally, the survey elaborates on the various practical applications of digital fingerprints and outlines the challenges and potential future research directions. The goal is to promote the continued development of multimedia digital fingerprint research., Comment: Preprint. 5 figures, 7 tables

The Houma Alliance Book, one of history's earliest calligraphic examples, was unearthed in the 1970s. These artifacts were meticulously organized, reproduced, and copied by the Shanxi Provincial Institute of Cultural Relics. However, because of their ancient origins and severe ink erosion, identifying characters in the Houma Alliance Book is challenging, necessitating the use of digital technology. In this paper, we propose a new ancient handwritten character recognition database for the Houma alliance book, along with a novel benchmark based on deep learning architectures. More specifically, a collection of 26,732 characters samples from the Houma Alliance Book were gathered, encompassing 327 different types of ancient characters through iterative annotation. Furthermore, benchmark algorithms were proposed by combining four deep neural network classifiers with two data augmentation methods. This research provides valuable resources and technical support for further studies on the Houma Alliance Book and other ancient characters. This contributes to our understanding of ancient culture and history, as well as the preservation and inheritance of humanity's cultural heritage., Comment: 8 pages, 5 figures

This paper introduces SynthDoc, a novel synthetic document generation pipeline designed to enhance Visual Document Understanding (VDU) by generating high-quality, diverse datasets that include text, images, tables, and charts. Addressing the challenges of data acquisition and the limitations of existing datasets, SynthDoc leverages publicly available corpora and advanced rendering tools to create a comprehensive and versatile dataset. Our experiments, conducted using the Donut model, demonstrate that models trained with SynthDoc's data achieve superior performance in pre-training read tasks and maintain robustness in downstream tasks, despite language inconsistencies. The release of a benchmark dataset comprising 5,000 image-text pairs not only showcases the pipeline's capabilities but also provides a valuable resource for the VDU community to advance research and development in document image recognition. This work significantly contributes to the field by offering a scalable solution to data scarcity and by validating the efficacy of end-to-end models in parsing complex, real-world documents.

Online video streaming has evolved into an integral component of the contemporary Internet landscape. Yet, the disclosure of user requests presents formidable privacy challenges. As users stream their preferred online videos, their requests are automatically seized by video content providers, potentially leaking users' privacy. Unfortunately, current protection methods are not well-suited to preserving user request privacy from content providers while maintaining high-quality online video services. To tackle this challenge, we introduce a novel Privacy-Preserving Video Fetching (PPVF) framework, which utilizes trusted edge devices to pre-fetch and cache videos, ensuring the privacy of users' requests while optimizing the efficiency of edge caching. More specifically, we design PPVF with three core components: (1) \textit{Online privacy budget scheduler}, which employs a theoretically guaranteed online algorithm to select non-requested videos as candidates with assigned privacy budgets. Alternative videos are chosen by an online algorithm that is theoretically guaranteed to consider both video utilities and available privacy budgets. (2) \textit{Noisy video request generator}, which generates redundant video requests (in addition to original ones) utilizing correlated differential privacy to obfuscate request privacy. (3) \textit{Online video utility predictor}, which leverages federated learning to collaboratively evaluate video utility in an online fashion, aiding in video selection in (1) and noise generation in (2). Finally, we conduct extensive experiments using real-world video request traces from Tencent Video. The results demonstrate that PPVF effectively safeguards user request privacy while upholding high video caching performance.

This paper introduces StyleSpeech, a novel Text-to-Speech~(TTS) system that enhances the naturalness and accuracy of synthesized speech. Building upon existing TTS technologies, StyleSpeech incorporates a unique Style Decorator structure that enables deep learning models to simultaneously learn style and phoneme features, improving adaptability and efficiency through the principles of Lower Rank Adaptation~(LoRA). LoRA allows efficient adaptation of style features in pre-trained models. Additionally, we introduce a novel automatic evaluation metric, the LLM-Guided Mean Opinion Score (LLM-MOS), which employs large language models to offer an objective and robust protocol for automatically assessing TTS system performance. Extensive testing on benchmark datasets shows that our approach markedly outperforms existing state-of-the-art baseline methods in producing natural, accurate, and high-quality speech. These advancements not only pushes the boundaries of current TTS system capabilities, but also facilitate the application of TTS system in more dynamic and specialized, such as interactive virtual assistants, adaptive audiobooks, and customized voice for gaming. Speech samples can be found in https://style-speech.vercel.app

Recent breakthroughs in deep learning and generative systems have significantly fostered the creation of synthetic media, as well as the local alteration of real content via the insertion of highly realistic synthetic manipulations. Local image manipulation, in particular, poses serious challenges to the integrity of digital content and societal trust. This problem is not only confined to multimedia data, but also extends to biological images included in scientific publications, like images depicting Western blots. In this work, we address the task of localizing synthetic manipulations in Western blot images. To discriminate between pristine and synthetic pixels of an analyzed image, we propose a synthetic detector that operates on small patches extracted from the image. We aggregate patch contributions to estimate a tampering heatmap, highlighting synthetic pixels out of pristine ones. Our methodology proves effective when tested over two manipulated Western blot image datasets, one altered automatically and the other manually by exploiting advanced AI-based image manipulation tools that are unknown at our training stage. We also explore the robustness of our method over an external dataset of other scientific images depicting different semantics, manipulated through unseen generation techniques.

Speech deepfake detection has recently gained significant attention within the multimedia forensics community. Related issues have also been explored, such as the identification of partially fake signals, i.e., tracks that include both real and fake speech segments. However, generating high-quality spliced audio is not as straightforward as it may appear. Spliced signals are typically created through basic signal concatenation. This process could introduce noticeable artifacts that can make the generated data easier to detect. We analyze spliced audio tracks resulting from signal concatenation, investigate their artifacts and assess whether such artifacts introduce any bias in existing datasets. Our findings reveal that by analyzing splicing artifacts, we can achieve a detection EER of 6.16% and 7.36% on PartialSpoof and HAD datasets, respectively, without needing to train any detector. These results underscore the complexities of generating reliable spliced audio data and lead to discussions that can help improve future research in this area., Comment: Accepted at ASVspoof 5 Workshop (Interspeech2024 Satellite)

Speech-language multi-modal learning presents a significant challenge due to the fine nuanced information inherent in speech styles. Therefore, a large-scale dataset providing elaborate comprehension of speech style is urgently needed to facilitate insightful interplay between speech audio and natural language. However, constructing such datasets presents a major trade-off between large-scale data collection and high-quality annotation. To tackle this challenge, we propose an automatic speech annotation system for expressiveness interpretation that annotates in-the-wild speech clips with expressive and vivid human language descriptions. Initially, speech audios are processed by a series of expert classifiers and captioning models to capture diverse speech characteristics, followed by a fine-tuned LLaMA for customized annotation generation. Unlike previous tag/templet-based annotation frameworks with limited information and diversity, our system provides in-depth understandings of speech style through tailored natural language descriptions, thereby enabling accurate and voluminous data generation for large model training. With this system, we create SpeechCraft, a fine-grained bilingual expressive speech dataset. It is distinguished by highly descriptive natural language style prompts, containing approximately 2,000 hours of audio data and encompassing over two million speech clips. Extensive experiments demonstrate that the proposed dataset significantly boosts speech-language task performance in stylist speech synthesis and speech style understanding., Comment: Accepted by ACM Multimedia 2024

The metaverse has received much attention in the literature and industry in the last few years, but the lack of an open and cross-platform architecture has led to many distinct metaverses that cannot communicate with each other. This work proposes a WebXR-based cross-platform architecture for developing spatial web apps using the A-Frame and Networked-Aframe frameworks with a view to an open and interoperable metaverse, accessible from both the web and extended reality devices. A prototype was implemented and evaluated, supporting the capability of the technology stack to enable immersive experiences across different platforms and devices. Positive feedback on ease of use of the immersive environment further corroborates the proposed approach, underscoring its effectiveness in facilitating engaging and interactive virtual spaces. By adhering to principles of interoperability and inclusivity, it lives up to Tim Berners-Lee's vision of the World Wide Web as an open platform that transcends geographical and technical boundaries., Comment: arXiv admin note: substantial text overlap with arXiv:2404.05317

Due to the challenges in acquiring paired Text-3D data and the inherent irregularity of 3D data structures, combined representation learning of 3D point clouds and text remains unexplored. In this paper, we propose a novel Riemann-based Multi-scale Attention Reasoning Network (RMARN) for text-3D retrieval. Specifically, the extracted text and point cloud features are refined by their respective Adaptive Feature Refiner (AFR). Furthermore, we introduce the innovative Riemann Local Similarity (RLS) module and the Global Pooling Similarity (GPS) module. However, as 3D point cloud data and text data often possess complex geometric structures in high-dimensional space, the proposed RLS employs a novel Riemann Attention Mechanism to reflect the intrinsic geometric relationships of the data. Without explicitly defining the manifold, RMARN learns the manifold parameters to better represent the distances between text-point cloud samples. To address the challenges of lacking paired text-3D data, we have created the large-scale Text-3D Retrieval dataset T3DR-HIT, which comprises over 3,380 pairs of text and point cloud data. T3DR-HIT contains coarse-grained indoor 3D scenes and fine-grained Chinese artifact scenes, consisting of 1,380 and over 2,000 text-3D pairs, respectively. Experiments on our custom datasets demonstrate the superior performance of the proposed method. Our code and proposed datasets are available at \url{https://github.com/liwrui/RMARN}.

Text-driven 3D scene generation has seen significant advancements recently. However, most existing methods generate single-view images using generative models and then stitch them together in 3D space. This independent generation for each view often results in spatial inconsistency and implausibility in the 3D scenes. To address this challenge, we proposed a novel text-driven 3D-consistent scene generation model: SceneDreamer360. Our proposed method leverages a text-driven panoramic image generation model as a prior for 3D scene generation and employs 3D Gaussian Splatting (3DGS) to ensure consistency across multi-view panoramic images. Specifically, SceneDreamer360 enhances the fine-tuned Panfusion generator with a three-stage panoramic enhancement, enabling the generation of high-resolution, detail-rich panoramic images. During the 3D scene construction, a novel point cloud fusion initialization method is used, producing higher quality and spatially consistent point clouds. Our extensive experiments demonstrate that compared to other methods, SceneDreamer360 with its panoramic image generation and 3DGS can produce higher quality, spatially consistent, and visually appealing 3D scenes from any text prompt. Our codes are available at \url{https://github.com/liwrui/SceneDreamer360}.

Emotion recognition can enhance humanized machine responses to user commands, while voiceprint-based perception systems can be easily integrated into commonly used devices like smartphones and stereos. Despite having the largest number of speakers, there is a noticeable absence of high-quality corpus datasets for emotion recognition using Chinese voiceprints. Hence, this paper introduces the VCEMO dataset to address this deficiency. The proposed dataset is constructed from everyday conversations and comprises over 100 users and 7,747 textual samples. Furthermore, this paper proposes a multimodal-based model as a benchmark, which effectively fuses speech, text, and external knowledge using a co-attention structure. The system employs contrastive learning-based regulation for the uneven distribution of the dataset and the diversity of emotional expressions. The experiments demonstrate the significant improvement of the proposed model over SOTA on the VCEMO and IEMOCAP datasets. Code and dataset will be released for research., Comment: 12 pages, 4 figures

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., Comment: Accepted at ACM Multimedia 2024

Recent technological advancements have enhanced our ability to collect and analyze rich multimodal data (e.g., speech, video, and eye gaze) to better inform learning and training experiences. While previous reviews have focused on parts of the multimodal pipeline (e.g., conceptual models and data fusion), a comprehensive literature review on the methods informing multimodal learning and training environments has not been conducted. This literature review provides an in-depth analysis of research methods in these environments, proposing a taxonomy and framework that encapsulates recent methodological advances in this field and characterizes the multimodal domain in terms of five modality groups: Natural Language, Video, Sensors, Human-Centered, and Environment Logs. We introduce a novel data fusion category -- mid fusion -- and a graph-based technique for refining literature reviews, termed citation graph pruning. Our analysis reveals that leveraging multiple modalities offers a more holistic understanding of the behaviors and outcomes of learners and trainees. Even when multimodality does not enhance predictive accuracy, it often uncovers patterns that contextualize and elucidate unimodal data, revealing subtleties that a single modality may miss. However, there remains a need for further research to bridge the divide between multimodal learning and training studies and foundational AI research., Comment: Submitted to ACM Computing Surveys. Currently under review

We are living in a flourishing era of digital media, where everyone has the potential to become a personal filmmaker. Current research on cinematic transfer empowers filmmakers to reproduce and manipulate the visual elements (e.g., cinematography and character behaviors) from classic shots. However, characters in the reimagined films still rely on manual crafting, which involves significant technical complexity and high costs, making it unattainable for ordinary users. Furthermore, their estimated cinematography lacks smoothness due to inadequate capturing of inter-frame motion and modeling of physical trajectories. Fortunately, the remarkable success of 2D and 3D AIGC has opened up the possibility of efficiently generating characters tailored to users' needs, diversifying cinematography. In this paper, we propose DreamCinema, a novel cinematic transfer framework that pioneers generative AI into the film production paradigm, aiming at facilitating user-friendly film creation. Specifically, we first extract cinematic elements (i.e., human and camera pose) and optimize the camera trajectory. Then, we apply a character generator to efficiently create 3D high-quality characters with a human structure prior. Finally, we develop a structure-guided motion transfer strategy to incorporate generated characters into film creation and transfer it via 3D graphics engines smoothly. Extensive experiments demonstrate the effectiveness of our method for creating high-quality films with free camera and 3D characters., Comment: Project page: https://liuff19.github.io/DreamCinema

With the rapid development of deepfake technology, especially the deep audio fake technology, misinformation detection on the social media scene meets a great challenge. Social media data often contains multimodal information which includes audio, video, text, and images. However, existing multimodal misinformation detection methods tend to focus only on some of these modalities, failing to comprehensively address information from all modalities. To comprehensively address the various modal information that may appear on social media, this paper constructs a comprehensive multimodal misinformation detection framework. By employing corresponding neural network encoders for each modality, the framework can fuse different modality information and support the multimodal misinformation detection task. Based on the constructed framework, this paper explores the importance of the audio modality in multimodal misinformation detection tasks on social media. By adjusting the architecture of the acoustic encoder, the effectiveness of different acoustic feature encoders in the multimodal misinformation detection tasks is investigated. Furthermore, this paper discovers that audio and video information must be carefully aligned, otherwise the misalignment across different audio and video modalities can severely impair the model performance.

This paper presents MaVEn, an innovative Multi-granularity Visual Encoding framework designed to enhance the capabilities of Multimodal Large Language Models (MLLMs) in multi-image reasoning. Current MLLMs primarily focus on single-image visual understanding, limiting their ability to interpret and integrate information across multiple images. MaVEn addresses this limitation by combining discrete visual symbol sequences, which abstract coarse-grained semantic concepts, with traditional continuous representation sequences that model fine-grained features. This dual approach bridges the semantic gap between visual and textual data, thereby improving the model's ability to process and interpret information from multiple images effectively. Additionally, we design a dynamic reduction mechanism by for long-sequence continuous features to enhance multi-image processing efficiency. Experimental results demonstrate that MaVEn significantly enhances MLLMs' understanding in complex multi-image scenarios, while also improving performance in single-image contexts.

With the rapid growth of video data on the internet, video summarization is becoming a very important AI technology. However, due to the high labelling cost of video summarization, existing studies have to be conducted on small-scale datasets, leading to limited performance and generalization capacity. In this work, we introduce the use of dense video captions as a supervision signal to train video summarization models. Motivated by this, we propose Cap2Sum, a model that learns to summarize videos by generating captions, to exploit dense video caption annotations. This weakly-supervised approach allows us to train the models on large-scale dense video caption datasets to achieve better performance and generalization capacity. To further improve the generalization capacity, we introduce a CLIP (a strong vision-language model) Prior mechanism to enhance the learning of important objects that captions may ignore in the videos. In practice, Cap2Sum can perform zero-shot video summarization or be fine-tuned by the ground-truth summary or video caption of the target dataset. To examine the performance of Cap2Sum after weakly-supervised fine-tuning by the video captions, we propose two new datasets, TVSum-Caption and SumMe-Caption, which are derived from two common video summarization datasets and will be publicly released. We conduct extensive experiments and the results demonstrate that our method achieves significant improvements in performance and generalization capacity compared with previous methods., Comment: 13 pages, 4 figures

Biomedical data is inherently multimodal, consisting of electronic health records, medical imaging, digital pathology, genome sequencing, wearable sensors, and more. The application of artificial intelligence tools to these multifaceted sensing technologies has the potential to revolutionize the prognosis, diagnosis, and management of human health and disease. However, current approaches to biomedical AI typically only train and evaluate with one or a small set of medical modalities and tasks. This limitation hampers the development of comprehensive tools that can leverage the rich interconnected information across many heterogeneous biomedical sensors. To address this challenge, we present MultiMed, a benchmark designed to evaluate and enable large-scale learning across a wide spectrum of medical modalities and tasks. MultiMed consists of 2.56 million samples across ten medical modalities such as medical reports, pathology, genomics, and protein data, and is structured into eleven challenging tasks, including disease prognosis, protein structure prediction, and medical question answering. Using MultiMed, we conduct comprehensive experiments benchmarking state-of-the-art unimodal, multimodal, and multitask models. Our analysis highlights the advantages of training large-scale medical models across many related modalities and tasks. Moreover, MultiMed enables studies of generalization across related medical concepts, robustness to real-world noisy data and distribution shifts, and novel modality combinations to improve prediction performance. MultiMed will be publicly available and regularly updated and welcomes inputs from the community.

Automatic Video Dubbing (AVD) aims to take the given script and generate speech that aligns with lip motion and prosody expressiveness. Current AVD models mainly utilize visual information of the current sentence to enhance the prosody of synthesized speech. However, it is crucial to consider whether the prosody of the generated dubbing aligns with the multimodal context, as the dubbing will be combined with the original context in the final video. This aspect has been overlooked in previous studies. To address this issue, we propose a Multimodal Context-aware video Dubbing model, termed \textbf{MCDubber}, to convert the modeling object from a single sentence to a longer sequence with context information to ensure the consistency of the global context prosody. MCDubber comprises three main components: (1) A context duration aligner aims to learn the context-aware alignment between the text and lip frames; (2) A context prosody predictor seeks to read the global context visual sequence and predict the context-aware global energy and pitch; (3) A context acoustic decoder ultimately predicts the global context mel-spectrogram with the assistance of adjacent ground-truth mel-spectrograms of the target sentence. Through this process, MCDubber fully considers the influence of multimodal context on the prosody expressiveness of the current sentence when dubbing. The extracted mel-spectrogram belonging to the target sentence from the output context mel-spectrograms is the final required dubbing audio. Extensive experiments on the Chem benchmark dataset demonstrate that our MCDubber significantly improves dubbing expressiveness compared to all advanced baselines. The code and demos are available at https://github.com/XiaoYuanJun-zy/MCDubber.

Content moderation is a widely used strategy to prevent the dissemination of irregular information on social media platforms. Despite extensive research on developing automated models to support decision-making in content moderation, there remains a notable scarcity of studies that integrate the rules of online communities into content moderation. This study addresses this gap by proposing a community rule-based content moderation framework that directly integrates community rules into the moderation of user-generated content. Our experiment results with datasets collected from two domains demonstrate the superior performance of models based on the framework to baseline models across all evaluation metrics. In particular, incorporating community rules substantially enhances model performance in content moderation. The findings of this research have significant research and practical implications for improving the effectiveness and generalizability of content moderation models in online communities., Comment: 10 pages, 3 figures

Video quality assessment (VQA) is a crucial task in the development of video compression standards, as it directly impacts the viewer experience. This paper presents the results of the Compressed Video Quality Assessment challenge, held in conjunction with the Advances in Image Manipulation (AIM) workshop at ECCV 2024. The challenge aimed to evaluate the performance of VQA methods on a diverse dataset of 459 videos, encoded with 14 codecs of various compression standards (AVC/H.264, HEVC/H.265, AV1, and VVC/H.266) and containing a comprehensive collection of compression artifacts. To measure the methods performance, we employed traditional correlation coefficients between their predictions and subjective scores, which were collected via large-scale crowdsourced pairwise human comparisons. For training purposes, participants were provided with the Compressed Video Quality Assessment Dataset (CVQAD), a previously developed dataset of 1022 videos. Up to 30 participating teams registered for the challenge, while we report the results of 6 teams, which submitted valid final solutions and code for reproducing the results. Moreover, we calculated and present the performance of state-of-the-art VQA methods on the developed dataset, providing a comprehensive benchmark for future research. The dataset, results, and online leaderboard are publicly available at https://challenges.videoprocessing.ai/challenges/compressedvideo-quality-assessment.html.

Foley sound synthesis is crucial for multimedia production, enhancing user experience by synchronizing audio and video both temporally and semantically. Recent studies on automating this labor-intensive process through video-to-sound generation face significant challenges. Systems lacking explicit temporal features suffer from poor controllability and alignment, while timestamp-based models require costly and subjective human annotation. We propose Video-Foley, a video-to-sound system using Root Mean Square (RMS) as a temporal event condition with semantic timbre prompts (audio or text). RMS, a frame-level intensity envelope feature closely related to audio semantics, ensures high controllability and synchronization. The annotation-free self-supervised learning framework consists of two stages, Video2RMS and RMS2Sound, incorporating novel ideas including RMS discretization and RMS-ControlNet with a pretrained text-to-audio model. Our extensive evaluation shows that Video-Foley achieves state-of-the-art performance in audio-visual alignment and controllability for sound timing, intensity, timbre, and nuance. Code, model weights, and demonstrations are available on the accompanying website. (https://jnwnlee.github.io/video-foley-demo)

This paper presents our winning approach for the MER-NOISE and MER-OV tracks of the MER2024 Challenge on multimodal emotion recognition. Our system leverages the advanced emotional understanding capabilities of Emotion-LLaMA to generate high-quality annotations for unlabeled samples, addressing the challenge of limited labeled data. To enhance multimodal fusion while mitigating modality-specific noise, we introduce Conv-Attention, a lightweight and efficient hybrid framework. Extensive experimentation vali-dates the effectiveness of our approach. In the MER-NOISE track, our system achieves a state-of-the-art weighted average F-score of 85.30%, surpassing the second and third-place teams by 1.47% and 1.65%, respectively. For the MER-OV track, our utilization of Emotion-LLaMA for open-vocabulary annotation yields an 8.52% improvement in average accuracy and recall compared to GPT-4V, securing the highest score among all participating large multimodal models. The code and model for Emotion-LLaMA are available at https://github.com/ZebangCheng/Emotion-LLaMA., Comment: Ranked 1st in MER24@IJCAI and MRAC24@ACM MM (MER-NOISE & MER-OV (self-evaluated))

Text-to-video generation has been dominated by end-to-end diffusion-based or autoregressive models. On one hand, those novel models provide plausible versatility, but they are criticized for physical correctness, shading and illumination, camera motion, and temporal consistency. On the other hand, film industry relies on manually-edited Computer-Generated Imagery (CGI) using 3D modeling software. Human-directed 3D synthetic videos and animations address the aforementioned shortcomings, but it is extremely tedious and requires tight collaboration between movie makers and 3D rendering experts. In this paper, we introduce an automatic synthetic video generation pipeline based on Vision Large Language Model (VLM) agent collaborations. Given a natural language description of a video, multiple VLM agents auto-direct various processes of the generation pipeline. They cooperate to create Blender scripts which render a video that best aligns with the given description. Based on film making inspiration and augmented with Blender-based movie making knowledge, the Director agent decomposes the input text-based video description into sub-processes. For each sub-process, the Programmer agent produces Python-based Blender scripts based on customized function composing and API calling. Then, the Reviewer agent, augmented with knowledge of video reviewing, character motion coordinates, and intermediate screenshots uses its compositional reasoning ability to provide feedback to the Programmer agent. The Programmer agent iteratively improves the scripts to yield the best overall video outcome. Our generated videos show better quality than commercial video generation models in 5 metrics on video quality and instruction-following performance. Moreover, our framework outperforms other approaches in a comprehensive user study on quality, consistency, and rationality.

Capturing pupil diameter is essential for assessing psychological and physiological states such as stress levels and cognitive load. However, the low resolution of images in eye datasets often hampers precise measurement. This study evaluates the impact of various upscaling methods, ranging from bicubic interpolation to advanced super-resolution, on pupil diameter predictions. We compare several pre-trained methods, including CodeFormer, GFPGAN, Real-ESRGAN, HAT, and SRResNet. Our findings suggest that pupil diameter prediction models trained on upscaled datasets are highly sensitive to the selected upscaling method and scale. Our results demonstrate that upscaling methods consistently enhance the accuracy of pupil diameter prediction models, highlighting the importance of upscaling in pupilometry. Overall, our work provides valuable insights for selecting upscaling techniques, paving the way for more accurate assessments in psychological and physiological research.

Depth perception plays an essential role in the viewer experience for immersive virtual reality (VR) visual environments. However, previous research investigations in the depth quality of 3D/stereoscopic images are rather limited, and in particular, are largely lacking for 3D viewing of 360-degree omnidirectional content. In this work, we make one of the first attempts to develop an objective quality assessment model named depth quality index (DQI) for efficient no-reference (NR) depth quality assessment of stereoscopic omnidirectional images. Motivated by the perceptual characteristics of the human visual system (HVS), the proposed DQI is built upon multi-color-channel, adaptive viewport selection, and interocular discrepancy features. Experimental results demonstrate that the proposed method outperforms state-of-the-art image quality assessment (IQA) and depth quality assessment (DQA) approaches in predicting the perceptual depth quality when tested using both single-viewport and omnidirectional stereoscopic image databases. Furthermore, we demonstrate that combining the proposed depth quality model with existing IQA methods significantly boosts the performance in predicting the overall quality of 3D omnidirectional images., Comment: Accepted by IEEE TCSVT

Full-reference image quality assessment (FR-IQA) models generally operate by measuring the visual differences between a degraded image and its reference. However, existing FR-IQA models including both the classical ones (eg, PSNR and SSIM) and deep-learning based measures (eg, LPIPS and DISTS) still exhibit limitations in capturing the full perception characteristics of the human visual system (HVS). In this paper, instead of designing a new FR-IQA measure, we aim to explore a generalized human visual attention estimation strategy to mimic the process of human quality rating and enhance existing IQA models. In particular, we model human attention generation by measuring the statistical dependency between the degraded image and the reference image. The dependency is captured in a training-free manner by our proposed sliced maximal information coefficient and exhibits surprising generalization in different IQA measures. Experimental results verify the performance of existing IQA models can be consistently improved when our attention module is incorporated. The source code is available at https://github.com/KANGX99/SMIC., Comment: 6 pages, 5 figures, accepted by ICME2024

Extracting geometry features from photographic images independently of surface texture and transferring them onto different materials remains a complex challenge. In this study, we introduce Harmonizing Attention, a novel training-free approach that leverages diffusion models for texture-aware geometry transfer. Our method employs a simple yet effective modification of self-attention layers, allowing the model to query information from multiple reference images within these layers. This mechanism is seamlessly integrated into the inversion process as Texture-aligning Attention and into the generation process as Geometry-aligning Attention. This dual-attention approach ensures the effective capture and transfer of material-independent geometry features while maintaining material-specific textural continuity, all without the need for model fine-tuning., Comment: 10 pages, 6 figures

Traditional animation generation methods depend on training generative models with human-labelled data, entailing a sophisticated multi-stage pipeline that demands substantial human effort and incurs high training costs. Due to limited prompting plans, these methods typically produce brief, information-poor, and context-incoherent animations. To overcome these limitations and automate the animation process, we pioneer the introduction of large multimodal models (LMMs) as the core processor to build an autonomous animation-making agent, named Anim-Director. This agent mainly harnesses the advanced understanding and reasoning capabilities of LMMs and generative AI tools to create animated videos from concise narratives or simple instructions. Specifically, it operates in three main stages: Firstly, the Anim-Director generates a coherent storyline from user inputs, followed by a detailed director's script that encompasses settings of character profiles and interior/exterior descriptions, and context-coherent scene descriptions that include appearing characters, interiors or exteriors, and scene events. Secondly, we employ LMMs with the image generation tool to produce visual images of settings and scenes. These images are designed to maintain visual consistency across different scenes using a visual-language prompting method that combines scene descriptions and images of the appearing character and setting. Thirdly, scene images serve as the foundation for producing animated videos, with LMMs generating prompts to guide this process. The whole process is notably autonomous without manual intervention, as the LMMs interact seamlessly with generative tools to generate prompts, evaluate visual quality, and select the best one to optimize the final output., Comment: Accepted by SIGGRAPH Asia 2024, Project and Codes: https://github.com/HITsz-TMG/Anim-Director

Event extraction (EE) is a critical direction in the field of information extraction, laying an important foundation for the construction of structured knowledge bases. EE from text has received ample research and attention for years, yet there can be numerous real-world applications that require direct information acquisition from speech signals, online meeting minutes, interview summaries, press releases, etc. While EE from speech has remained under-explored, this paper fills the gap by pioneering a SpeechEE, defined as detecting the event predicates and arguments from a given audio speech. To benchmark the SpeechEE task, we first construct a large-scale high-quality dataset. Based on textual EE datasets under the sentence, document, and dialogue scenarios, we convert texts into speeches through both manual real-person narration and automatic synthesis, empowering the data with diverse scenarios, languages, domains, ambiences, and speaker styles. Further, to effectively address the key challenges in the task, we tailor an E2E SpeechEE system based on the encoder-decoder architecture, where a novel Shrinking Unit module and a retrieval-aided decoding mechanism are devised. Extensive experimental results on all SpeechEE subsets demonstrate the efficacy of the proposed model, offering a strong baseline for the task. At last, being the first work on this topic, we shed light on key directions for future research.

To address the limitation in multimodal emotion recognition (MER) performance arising from inter-modal information fusion, we propose a novel MER framework based on multitask learning where fusion occurs after alignment, called Foal-Net. The framework is designed to enhance the effectiveness of modality fusion and includes two auxiliary tasks: audio-video emotion alignment (AVEL) and cross-modal emotion label matching (MEM). First, AVEL achieves alignment of emotional information in audio-video representations through contrastive learning. Then, a modal fusion network integrates the aligned features. Meanwhile, MEM assesses whether the emotions of the current sample pair are the same, providing assistance for modal information fusion and guiding the model to focus more on emotional information. The experimental results conducted on IEMOCAP corpus show that Foal-Net outperforms the state-of-the-art methods and emotion alignment is necessary before modal fusion., Comment: The paper has been accepted by INTERSPEECH 2024

Talking head generation is a significant research topic that still faces numerous challenges. Previous works often adopt generative adversarial networks or regression models, which are plagued by generation quality and average facial shape problem. Although diffusion models show impressive generative ability, their exploration in talking head generation remains unsatisfactory. This is because they either solely use the diffusion model to obtain an intermediate representation and then employ another pre-trained renderer, or they overlook the feature decoupling of complex facial details, such as expressions, head poses and appearance textures. Therefore, we propose a Facial Decoupled Diffusion model for Talking head generation called FD2Talk, which fully leverages the advantages of diffusion models and decouples the complex facial details through multi-stages. Specifically, we separate facial details into motion and appearance. In the initial phase, we design the Diffusion Transformer to accurately predict motion coefficients from raw audio. These motions are highly decoupled from appearance, making them easier for the network to learn compared to high-dimensional RGB images. Subsequently, in the second phase, we encode the reference image to capture appearance textures. The predicted facial and head motions and encoded appearance then serve as the conditions for the Diffusion UNet, guiding the frame generation. Benefiting from decoupling facial details and fully leveraging diffusion models, extensive experiments substantiate that our approach excels in enhancing image quality and generating more accurate and diverse results compared to previous state-of-the-art methods., Comment: Accepted by ACM Multimedia 2024

Low-light image enhancement remains a challenging task in computer vision, with existing state-of-the-art models often limited by hardware constraints and computational inefficiencies, particularly in handling high-resolution images. Recent foundation models, such as transformers and diffusion models, despite their efficacy in various domains, are limited in use on edge devices due to their computational complexity and slow inference times. We introduce ExpoMamba, a novel architecture that integrates components of the frequency state space within a modified U-Net, offering a blend of efficiency and effectiveness. This model is specifically optimized to address mixed exposure challenges, a common issue in low-light image enhancement, while ensuring computational efficiency. Our experiments demonstrate that ExpoMamba enhances low-light images up to 2-3x faster than traditional models with an inference time of 36.6 ms and achieves a PSNR improvement of approximately 15-20% over competing models, making it highly suitable for real-time image processing applications.

Sign language serves as the primary meaning of communication for the deaf-mute community. Different from spoken language, it commonly conveys information by the collaboration of manual features, i.e., hand gestures and body movements, and non-manual features, i.e., facial expressions and mouth cues. To facilitate communication between the deaf-mute and hearing people, a series of sign language understanding (SLU) tasks have been studied in recent years, including isolated/continuous sign language recognition (ISLR/CSLR), gloss-free sign language translation (GF-SLT) and sign language retrieval (SL-RT). Sign language recognition and translation aims to understand the semantic meaning conveyed by sign languages from gloss-level and sentence-level, respectively. In contrast, SL-RT focuses on retrieving sign videos or corresponding texts from a closed-set under the query-by-example search paradigm. These tasks investigate sign language topics from diverse perspectives and raise challenges in learning effective representation of sign language videos. To advance the development of sign language understanding, exploring a generalized model that is applicable across various SLU tasks is a profound research direction., Comment: Sign language recognition; Sign language translation; Sign language retrieval