Cultural garments pose a unique challenge for visual retrieval systems, as their identity often depends on subtle structural and symbolic details that are poorly captured by standard AI models. We introduce VietFashion, a new benchmark for sketch–text composed image retrieval centered on the Ao Dai, a traditional Vietnamese garment. VietFashion enables designers and researchers to retrieve culturally meaningful outfits using a combination of hand-drawn sketches, which convey garment structure, and textual descriptions, which encode cultural semantics. The dataset is initialized with 650 sketches and expanded using generative models to produce over 21,000 photorealistic images with aligned captions. Textual prompts that describe detailed outfit attributes, which are extracted from fashion magazines to ensure authenticity and diversity. To better reflect the inherent ambiguity of design intent, VietFashion adopts a multi-target retrieval setting, where a single query may correspond to multiple valid results. We establish standardized evaluation protocols and benchmark state-of-the-art composed image retrieval methods. Experimental results reveal significant performance gaps in modeling fine-grained cultural semantics and multi-modal composition, positioning VietFashion as a challenging benchmark for fine-grained fashion retrieval. The dataset is publicly available at: https://hng0303.github.io/VietFashion.

The 2026 Grand Challenge on Multimedia Verification at ICMR 2026 invited participants to verify real-world multimedia content across various dimensions, such as verified evidence (source, location, time, entities, motivation) and forensic analysis. Four teams submitted complete solutions, evaluated by professional fact-checkers on a 110-point rubric across ten real-world cases. This paper presents an overview of the challenge, summarizes the participating methods, and reports the official scoreboard together with per-criterion analysis. We observe a clear trend toward multi-agent, tool-augmented LLM pipelines, but also recurring weaknesses in human oversight, reasoning grounding, and resistance to hallucination. As a result, no submission was declared a winner this year, and we outline concrete directions for the next edition.

The ACM Lifelog Search Challenge (LSC) is an annual comparative benchmarking exercise that brings together researchers in the field of multimedia retrieval to evaluate interactive search systems using a large-scale multimodal lifelog dataset. This paper presents an overview of the ninth edition of the challenge (LSC’26), held as a workshop during the ACM International Conference on Multimedia Retrieval (ICMR ’26) in Amsterdam. To broaden its scope, the workshop now features three submission tracks: the traditional Challenge Track for real-time search performance, a new General Lifelog Research Track for theoretical and architectural advancements, and an additional Open Source Track aimed at enhancing reproducibility and reducing barriers to entry for new participants.

Abscesses in the head and neck represent an acute infectious process that can potentially lead to sepsis or mortality if not diagnosed and managed promptly. Accurate detection and delineation of these lesions on imaging are essential for diagnosis, treatment planning, and surgical intervention. In this study, we introduce AbscessHeNe, a curated and comprehensively annotated dataset comprising 4,926 contrastenhanced CT slices with clinically confirmed head and neck abscesses. The dataset is designed to facilitate the development of robust semantic segmentation models that can accurately delineate abscess boundaries and evaluate deep neck space involvement, thereby supporting informed clinical decision-making. To establish performance baselines, we evaluate several state-of-the-art segmentation architectures, including CNN, Transformer, and Mamba-based models. The highestperforming model achieved a Dice Similarity Coefficient of 0.39, Intersection-over-Union of 0.27, and Normalized Surface Distance of 0.67, indicating the challenges of this task and the need for further research. Beyond segmentation, AbscessHeNe is structured for future applications in content-based multimedia indexing and case-based retrieval. Each CT scan is linked with pixel-level annotations and clinical metadata, providing a foundation for building intelligent retrieval systems and supporting knowledge-driven clinical workflows. The dataset will be made publicly available at https://github.com/drthaodao3101/AbscessHeNe.git.

Generative art unlocks boundless creative possibilities, yet its full potential remains untapped due to the technical expertise required for advanced architectural concepts and computational workflows. To bridge this gap, we present GenFlow, a novel modular framework that empowers users of all skill levels to generate images with precision and ease. Featuring a node-based editor for seamless customization and an intelligent assistant powered by natural language processing, GenFlow transforms the complexity of workflow creation into an intuitive and accessible experience. By automating deployment processes and minimizing technical barriers, our framework makes cutting-edge generative art tools available to everyone. A user study demonstrated GenFlow's ability to optimize workflows, reduce task completion times, and enhance user understanding through its intuitive interface and adaptive features. These results position GenFlow as a groundbreaking solution that redefines accessibility and efficiency in the realm of generative art.

The increasing sophistication of cheapfakes and deepfakes poses new challenges for maintaining information integrity in the digital age. While recent advances in deep learning classifiers and chatbot-assisted verification have greatly improved detection capabilities, there remains an opportunity to further strengthen these systems by incorporating contextual understanding from original source material. In this paper, we propose a multimedia verification framework that complements existing approaches by retrieving and leveraging contextual evidence associated with the target media to support more informed assessments of authenticity. For cheapfake detection, we analyze the relationship between image-caption pairs to determine if the caption is out-of-context (OOC). Using the COSMOS dataset, our model achieves a state-of-the-art accuracy of 93.6%. For deepfake detection, we segment videos by speaker using diarization, extract key frames, and apply the GenConViT model for face analysis. We further retrieve related news articles and contextual metadata (speaker identity, topic, time) to support chatbot reasoning. On the DF-W YouTube dataset, our system achieves an F1 score of 89%, surpassing existing benchmarks. Our results demonstrate the importance of integrating contextual retrieval and reasoning into multimedia verification pipelines, especially when verifying AI-generated or manipulated content.

For the eighth time since 2018, the ACM Lifelog Search Challenge (LSC) was run to compare interactive lifelog search systems in a live metrics-based challenge. The goal of the LSC workshop is to comparatively evaluate the capabilities of systems accessing a large multimodal lifelog. LSC'25 attracted eleven participating teams, each of which had developed an innovative interactive lifelog retrieval system. The benchmark was organised in a hybrid manner (due to political issues in 2025) at the LSC workshop at ACM ICMR'25 in Chicago, USA. This short paper summarises the LSC workshop setting and presents the participating lifelog search systems.

The 2025 Grand Challenge on Multimedia Verification addresses the challenges of verifying the authenticity and context of online multimedia content. Participants analyzed real-world cases of images and videos, assessed their sources, detected any potential manipulations, and submitted detailed verification reports. The main competition was structured into three stages: Training, Validation, and Real-World Verification, which included live test cases and welcomed solutions ranging from manual methods and OSINT practices to automated tools and novel AI techniques. A total of 32 teams from 11 countries registered. The submitted solutions presented diverse pipelines that integrated forensic analysis, multimodal reasoning, and large language models (LLMs). The results demonstrate significant progress toward semi-automated verification workflows, while also exposing challenges in scalability, consistency, and reliability. In this paper, we present the challenge design, datasets, evaluation criteria, and participant outcomes, providing insights to guide future research and practice in multimedia verification.

In many real-world applications, labeling an image ''a man riding a horse'' fails to satisfy demands for the who, when, where, and why. Although LVLMs excel at describing visual content, isolated images often lack the event context; users thus rely on related news articles or social posts to enrich them, but cropping or resizing complicates tracking back to their source. In this paper, we propose ENRIC, an innovative end-to-end system for the EVENTA Challenge Track 1, leveraging the OpenEvents-V1 dataset, comprising over 200,000 news articles paired with more than 400,000 images. Our system includes three components: (1) semantic retrieval filters candidate article images via vision-language embeddings, (2) uncertainty-guided re-ranking flags ambiguous queries using three confidence heuristics and re-ranks candidates by combining visual similarity with texture similarity, and (3) event-aware caption generation employs chain-of-thought prompting that aggregates five inputs from article, image, and CIDEr-derived contexts to guide the LLM in incorporating all necessary elements. ENRIC achieved the highest combined evaluation score of 0.5501, ranking first and outperforming other solutions across nearly all metrics. By combining semantic retrieval, uncertainty-guided re-ranking, and event-aware caption generation, ENRIC demonstrates the efficiency of its approach for event-enriched image analysis. GitHub repository: https://github.com/NamQuanProject/EVENTA25-ENRIC

Automated analysis of endoscopic imagery is a critical yet underdeveloped component of ENT (ear, nose, and throat) care, hindered by variability in devices and operators, subtle and localized findings, and fine-grained distinctions such as laterality and vocal-fold state. In addition to classification, clinicians require reliable retrieval of similar cases, both visually and through concise textual descriptions. These capabilities are rarely supported by existing public benchmarks. To this end, we introduce ENTRep, the ACM Multimedia 2025 Grand Challenge on ENT endoscopy analysis, which integrates fine-grained anatomical classification with image-to-image and text-to-image retrieval under bilingual (Vietnamese and English) clinical supervision. Specifically, the dataset comprises expert-annotated images, labeled for anatomical region and normal or abnormal status, and accompanied by dual-language narrative descriptions. In addition, we define three benchmark tasks, standardize the submission protocol, and evaluate performance on public and private test splits using server-side scoring. Moreover, we report results from the top-performing teams and provide an insightful discussion.

Image captioning systems often produce generic descriptions that fail to capture event-level semantics which are crucial for applications like news reporting and digital archiving. We present ReCap, a novel pipeline for event-enriched image retrieval and captioning that incorporates broader contextual information from relevant articles to generate narrative-rich, factually grounded captions. Our approach addresses the limitations of standard vision-language models that typically focus on visible content while missing temporal, social, and historical contexts. ReCap comprises three integrated components: (1) a robust two-stage article retrieval system using DINOv2 embeddings with global feature similarity for initial candidate selection followed by patch-level mutual nearest neighbor similarity re-ranking; (2) a context extraction framework that synthesizes information from article summaries, generic captions, and original source metadata; and (3) a large language model-based caption generation system with Semantic Gaussian Normalization to enhance fluency and relevance. Evaluated on the OpenEvents V1 dataset as part of Track 1 in the EVENTA 2025 Grand Challenge, ReCap achieved a strong overall score of 0.54666, ranking 2nd on the private test set. These results highlight ReCap's effectiveness in bridging visual perception with real-world knowledge, offering a practical solution for context-aware image understanding in high-stakes domains. The code is available at https://github.com/Noridom1/EVENTA2025-Event-Enriched-Image-Captioning.

We introduce OpenEvents V1, a large-scale benchmark dataset designed to advance event-centric vision-language understanding. Unlike conventional image captioning and retrieval datasets that focus on surface-level descriptions, OpenEvents V1 dataset emphasizes contextual and temporal grounding through three primary tasks: (1) generating rich, event-aware image captions, (2) retrieving event-relevant news articles from image queries, and (3) retrieving event-relevant images from narrative-style textual queries. The dataset comprises over 200,000 news articles and 400,000 associated images sourced from CNN and The Guardian, spanning diverse domains and time periods. We provide extensive baseline results and standardized evaluation protocols for all tasks. OpenEvents V1 establishes a robust foundation for developing multimodal AI systems capable of deep reasoning over complex real-world events. The dataset is publicly available at https://ltnghia.github.io/eventa/openevents-v1.

Egocentric video has seen increased interest in recent years, as it is used in a range of areas. However, most existing datasets are limited to a single perspective. In this paper, we present the CASTLE 2024 dataset, a multimodal collection containing ego- and exo-centric (i.e., first- and third-person perspective) video and audio from 15 time-aligned sources, as well as other sensor streams and auxiliary data. The dataset was recorded by volunteer participants over four days in a common location and includes the point of view of 10 participants, with an additional 5 fixed cameras providing an exocentric perspective. The entire dataset contains over 600 hours of UHD video recorded at 50 frames per second. In contrast to other datasets, CASTLE 2024 does not contain any partial censoring, such as blurred faces or distorted audio. The dataset is available via https://castle-dataset.github.io/.

Key Opinion Leaders (KOLs) play a crucial role in modern marketing by shaping consumer perceptions and enhancing brand credibility. However, collaborating with human KOLs often involves high costs and logistical challenges. To address this, we present GenKOL, an interactive system that empowers marketing professionals to efficiently generate high-quality virtual KOL images using generative AI. GenKOL enables users to dynamically compose promotional visuals through an intuitive interface that integrates multiple AI capabilities, including garment generation, makeup transfer, background synthesis, and hair editing. These capabilities are implemented as modular, interchangeable services that can be deployed flexibly on local machines or in the cloud. This modular architecture ensures adaptability across diverse use cases and computational environments. Our system can significantly streamline the production of branded content, lowering costs and accelerating marketing workflows through scalable virtual KOL creation. Video demo is available at https://youtu.be/uXpXmEbjg3M.

The Event-Enriched Image Analysis (EVENTA) Grand Challenge, hosted at ACM Multimedia 2025, introduces the first large-scale benchmark for event-level multimodal understanding. Traditional captioning and retrieval tasks largely focus on surface-level recognition of people, objects, and scenes, often overlooking the contextual and semantic dimensions that define real-world events. EVENTA addresses this gap by integrating contextual, temporal, and semantic information to capture the who, when, where, what, and why behind an image. Built upon the OpenEvents V1 dataset, the challenge features two tracks: Event-Enriched Image Retrieval and Captioning, and Event-Based Image Retrieval. A total of 45 teams from six countries participated, with evaluation conducted through Public and Private Test phases to ensure fairness and reproducibility. The top three teams were invited to present their solutions at ACM Multimedia 2025. EVENTA establishes a foundation for context-aware, narrative-driven multimedia AI, with applications in journalism, media analysis, cultural archiving, and accessibility. Further details about the challenge are available at the official homepage: https://ltnghia.github.io/eventa/eventa-2025.

Line sketches serve as the visual DNA of fashion design, forming the essential foundation where concepts take shape, yet today's digital tools often lack the fluidity, personalization, and intelligence needed to truly support this creative process. We present FashSketch, an interactive, multimedia-driven system that reimagines fashion sketching through the lens of generative AI. Designed with a layer-based creative interface, FashSketch empowers designers to ideate, customize, and iterate on sketches seamlessly. By integrating state-of-the-art generative models, sketch-based retrieval, and large language models, the system supports advanced functionalities such as text-to-sketch generation and context-aware sketch recommendation. FashSketch not only enhances the sketching experience but also opens new multimodal pathways for creative expression, making it a powerful co-creative partner in the early stages of fashion design. Video demo is available at https://youtu.be/BX-Edz7Z7ZY.

Event-based image retrieval from free-form captions presents a significant challenge: models must understand not only visual features but also latent event semantics, context, and real-world knowledge. Conventional vision-language retrieval approaches often fall short when captions describe abstract events, implicit causality, temporal context, or contain long, complex narratives. To tackle these issues, we introduce a multi-stage retrieval framework combining dense article retrieval, event-aware language model reranking, and efficient image collection, followed by caption-guided semantic matching and rank-aware selection. We leverage Qwen3 for article search, Qwen3-Reranker for contextual alignment, and Qwen2-VL for precise image scoring. To further enhance performance and robustness, we fuse outputs from multiple configurations using Reciprocal Rank Fusion (RRF). Our system achieves the top-1 score on the private test set of Track 2 in the EVENTA 2025 Grand Challenge, demonstrating the effectiveness of combining language-based reasoning and multimodal retrieval for complex, real-world image understanding. The code is available at https://github.com/vdkhoi20/EVENT-Retriever.

Large Language Models (LLMs) offer significant potential for integration with Virtual Reality (VR), but current AI systems struggle to generate accurate 3D environments and support semantic interaction. We present ChemersiveLLM, a VR-based chemistry learning platform that leverages LLMs for instruction sequencing, natural language grounding, and real-time guidance. Using a semantic action-mapping framework, the system translates AI-generated content into structured lab actions, enabling multimodal interaction, embodied experimentation, and intelligent feedback. Comparative evaluation across textbook, chatbot-based, and VR learning shows that our system improves engagement, comprehension, and satisfaction, underscoring its promise as a next-generation tool for science education.

Camouflaged object detection (COD) and camouflaged instance segmentation (CIS) aim to recognize and segment objects that are blended into their surroundings, respectively. While several deep neural network models have been proposed to tackle those tasks, augmentation methods for COD and CIS have not been thoroughly explored. strategies can help improve models' performance by increasing the size and diversity of the training data and exposing the model to a wider range of variations in the data. Besides, we aim to automatically learn transformations that help to reveal the underlying structure of camou-flaged objects and allow the model to learn to identify better and segment camouflaged objects. To achieve this, we pro-pose a learnable augmentation method in the frequency domain for COD and CIS via the Fourier transform approach, dubbed CamoFA. Our method leverages a conditional generative adversarial network and cross-attention mechanism to generate a reference image and an adaptive hybrid swapping with parameters to mix the low-frequency component of the reference image and the high-frequency component of the input image. This approach aims to make camouflaged objects more visible for detection and segmentation models. Without bells and whistles, our proposed augmentation method boosts the performance of camouflaged object detectors and instance segmenters by large margins.

Referring image segmentation is a challenging task that involves generating pixel-wise segmentation masks based on natural language descriptions. The complexity of this task increases with the intricacy of the sentences provided. Existing methods have relied mostly on visual features to generate the segmentation masks while treating text features as supporting components. However, this under-utilization of text understanding limits the model's capability to fully comprehend the given expressions. In this work, we propose a novel framework that specifically emphasizes object and context comprehension inspired by human cognitive processes through Vision-Aware Text Features. Firstly, we introduce a CLIP Prior module to localize the main object of interest and embed the object heatmap into the query initialization process. Secondly, we propose a combination of two components: Contextual Multimodal Decoder and Meaning Consistency Constraint, to further enhance the coherent and consistent interpretation of language cues with the contextual understanding obtained from the image. Our method achieves significant performance improvements on three benchmark datasets RefCOCO, RefCOCO+ and G-Ref Project page: https://vatex.hkustvgd.com/

Few-shot instance segmentation extends the few-shot learning paradigm to the instance segmentation task, which tries to segment instance objects from a query image with a few annotated examples of novel categories. Conventional approaches have attempted to address the task via prototype learning, known as point estimation. However, this mechanism depends on prototypes (e.g. mean of K-shot) for prediction, leading to performance instability. To overcome the disadvantage of the point estimation mechanism, we propose a novel approach, dubbed MaskDiff, which models the underlying conditional distribution of a binary mask, which is conditioned on an object region and K-shot information. Inspired by augmentation approaches that perturb data with Gaussian noise for populating low data density regions, we model the mask distribution with a diffusion probabilistic model. We also propose to utilize classifier-free guided mask sampling to integrate category information into the binary mask generation process. Without bells and whistles, our proposed method consistently outperforms state-of-the-art methods on both base and novel classes of the COCO dataset while simultaneously being more stable than existing methods. The source code is available at: https://github.com/minhquanlecs/MaskDiff.

Person Re-Identification (Re-ID) task seeks to enhance the tracking of multiple individuals by surveillance cameras. It supports multimodal tasks, including text-based person retrieval and human matching. One of the most significant challenges faced in Re-ID is clothes-changing, where the same person may appear in different outfits. While previous methods have made notable progress in maintaining clothing data consistency and handling clothing change data, they still rely excessively on clothing information, which can limit performance due to the dynamic nature of human appearances. To mitigate this challenge, we propose the Pose-Guidance Deep Supervision (PGDS), an effective framework for learning pose guidance within the Re-ID task. It consists of three modules: a human encoder, a pose encoder, and a Pose-to-Human Projection module(PHP). Our framework guides the human encoder, i.e., the main re-identification model, with pose information from the pose encoder through multiple layers via the knowledge transfer mechanism from the PHP module, helping the human encoder learn body parts information without increasing computation resources in the inference stage. Through extensive experiments, our method surpasses the performance of current state-of-the-art methods, demonstrating its robustness and effectiveness for real-world applications. Our code is available at https://github.com/huyquoctrinh/PGDS.

In recent years, video content has become increasingly popular due to the development of technologies, especially for recording devices. This explosion has driven the need for an advanced video-moment retrieval system that can accurately search for specific video segments matching the intentions of the user's queries. A prominent challenge in this field lies in the multimedia nature of the video data, which includes visual, auditory and even textual information. The accuracy and relevance of search results depend on how efficiently a retrieval system processes these types of metadata. In this paper, we introduce IMSearch, an interactive multimedia search system that can retrieve precise video-moment content by executing queries across various information types, such as text, audio, location of the objects, sketch, and human pose. Additionally, we implement a re-ranking mechanism based on user feedback to simultaneously improve and optimize the performance of our IMSearch system. We also explore two different vector libraries (FAISS and HNSW) for vector searching and report the retrieval accuracy and executed time to demonstrate our proposed paradigm.

Our paper introduces a novel middleware designed to enhance the user experience of novice users of video event retrieval systems. The middleware simplifies the search process while maintaining advanced semantic information-seeking features. It achieves this by refining sentence representation, rewriting the original query based on user intent and dataset metadata knowledge, reducing ambiguities, and increasing relevance with domain-specific terms. Our approach allows users to provide simplified descriptions, while the system automates query refinement and parameterizes these for different search functions. This reduces the difficulty of navigating complex user interfaces and selecting from available functionalities. Additionally, the multilingual feature supports non-native English speakers by helping them describe their queries more effectively. In general, our system is suitable for people who are not experienced in advanced retrieval tasks, specifically focusing on its applicability in the special session Interactive Video Retrieval for Beginners (IVR4B).

The person identification task aims to generate robust human representation embeddings. Traditional methods have achieved competitive results, but they face occlusion challenges, making it difficult to distinguish between humans occluded by objects or other humans. This paper proposes Pose-to-Human (P2H), a pose guidance framework via Gram matrix and knowledge transfer mechanism to tackle occlusion problems in Person Re-identification to address this issue. Our framework comprises four modules: Human Encoder, Pose Encoder, Compact Modules (CPM), and the Gram Matrix Guiding (GMG). The Pose Encoder generates pose information used to guide the human embedding models, facilitating learning of other parts of the human anatomy, which enables the model to focus on the unoccluded parts of the body, thus mitigating the reliance on the data for part-to-part matching, which is the first limitation of previous works. Additionally, it can reduce the demand for general appearance information from the human encoder model. Our method achieves competitive results through extensive experiments on five datasets compared to state-of-the-art methods, making it a promising framework for addressing the Re-Identification task.

Information disorder is one of the most typical challenges in the current era of science and technology. The amount of information on the internet is increasing, but its correctness and authenticity are not always guaranteed, leading to false information, fake news, etc. The mentioned problem negatively affects users' reception and use of information. Unlike deepfake, cheapfake is created using simple techniques and does not rely on AI to produce fake multimedia. Cheapfake is becoming increasingly popular due to its ease of creation. Thus, there is a growing need to develop techniques that can detect cheapfake content. Following previous events, the Grand Challenge on Detecting Cheapfakes at ACM ICMR 2024 continues to seek contributions from researchers on cheapfake detection with the goal of improving effectiveness and creativity in approach, and understanding the limitations of the current dataset. This challenge has accepted 6 new proposed methods from participants with the highest private test accuracies achieved at 72.2% for Task 1 and 54.84% for Task 2. The highest public test accuracies for the two tasks are 95.6% and 93% respectively. These new methods focus on incorporating new AI models such as Stable Diffusion, LLM. These new findings represent the latest advancements in cheapfake detection research and introduce new potential approaches for future research.

The explosive growth of social networks this decade has significantly impacted society, with digital technologies enabling anyone to create and disseminate fake news using simple editing tools. Media professionals and fact-checkers are now tasked with the complex challenge of verifying visual content, as both multimedia and associated text can be fabricated. Fact-checkers must thoroughly search for related information, such as the time and place of an image's capture, to uncover inconsistencies for content verification. This process demands expertise in journalism and image analysis and involves navigating vast information spaces with current computational and search tools. While AI can tackle specific tasks, it cannot yet replicate human reasoning and judgment. Our study aims to develop a comprehensive pipeline that employs computer science techniques to assist fact-checkers in working more efficiently and effectively, integrating advanced search tools, deep learning models, and additional data like weather conditions to streamline the verification process.

For the seventh time since 2018, the Lifelog Search Challenge (LSC) benchmarked interactive lifelog search systems in a live challenge. The LSC goal is to comparatively evaluate system capabilities to access large multimodal lifelogs comprising hundreds of thousands of records. LSC'24 attracted an unprecedented record number of twenty-one participating teams, where each team proposes innovative ideas implemented to new or already established interactive lifelog retrieval systems. The benchmark was organised in front of a live audience at the LSC workshop at ACM ICMR'24 in Phuket, Thailand. This short paper summarises the LSC workshop setting and presents the participating lifelog search systems.

In our modern world, the manipulation of digital content, especially the usage of out-of-context images known as Cheapfakes, has become a significant challenge for the endorsement of integrity and trustworthiness for information on the Internet. This highlights an urgent need for effective detection of the misuse of images and their accompanied captions. Motivated by this issue, our research presents an innovative approach to the solution of this problem. Participating in the ACM ICMR 2024 Grand Challenge on Detecting Cheapfakes, we leverage a unified end-to-end network, integrated with generative synthetic data for training. After complete evaluation, our proposed network demonstrated a remarkable accuracy of 95.60% on the public test dataset for Task 1, as well as efficiency in Task 2. This paper highlights the notable potential of employing an end-to-end network for Cheapfakes detection, which composes a significant contribution to the advancement of multimedia content integrity. Our source code is publicly available at https://github.com/thanhson28/cheapfakes_detection_icmr2024.git

Efficient polyp segmentation in healthcare plays a critical role in enabling early diagnosis of colorectal cancer. However, the segmentation of polyps presents numerous challenges, including the intricate distribution of backgrounds, variations in polyp sizes and shapes, and indistinct boundaries. Defining the boundary between the foreground (i.e. polyp itself) and the background (surrounding tissue) is difficult. To mitigate these challenges, we propose Multi-Scale Edge-Guided Attention Network (MEGANet) tailored specifically for polyp segmentation within colonoscopy images. This network draws inspiration from the fusion of a classical edge detection technique with an attention mechanism. By combining these techniques, MEGANet effectively preserves high-frequency information, notably edges and boundaries, which tend to erode as neural networks deepen. MEGANet is designed as an end-to-end framework, encompassing three key modules: an encoder, which is responsible for capturing and abstracting the features from the input image, a decoder, which focuses on salient features, and the Edge-Guided Attention module (EGA) that employs the Laplacian Operator to accentuate polyp boundaries. Extensive experiments, both qualitative and quantitative, on five benchmark datasets, demonstrate that our MEGANet outperforms other existing SOTA methods under six evaluation metrics. Our code is available at https://github.com/UARK-AICV/MEGANet.

For the sixth time since 2018, the Lifelog Search Challenge (LSC) was organized as a comparative benchmarking exercise for various interactive lifelog search systems. The goal of this international competition is to test system capabilities to access large multimodal lifelogs. LSC’23 attracted twelve participanting teams, each of whom had developed a competitive interactive lifelog retrieval system. The benchmark was organized in front of live audience at the LSC workshop at ACM ICMR’23. As in previous editions, this introductory paper presents the LSC workshop and introduces the participating lifelog search systems.

sponsorship: This research is funded by the University of Science, VNU-HCM, Vietnam under grant number CNTT 2023-05 (University of Science, VNU-HCM, Vietnam|CNTT 2023-05)

Accurately generating talking landmarks from audio is critical for creating authentic talking head animations. This is a significant issue in the field of landmark generation from audio and has potential applications in areas such as virtual assistants, education, and entertainment. Previous methods evaluate the effectiveness to generate the talking landmark from audio, however, these methods have limitations such as bias and inconsistencies in landmark generation due to the lack of visual information from the previous frames. In this research, we propose SpeechSyncNet, a baseline that integrates a fusion of the prior landmark information and the audio feature to provide the lack of visual information from audio, also this method aims to improve the consistency of the landmark motion. Our proposed method yields competitive results compared to existing state-of-the-art methods and helps to improve the quality of talking face landmark generation.

The timing of cell divisions in early embryos during the In-Vitro Fertilization (IVF) process is a key predictor of embryo viability. However, observing cell divisions in Time-Lapse Monitoring (TLM) is a time-consuming process and highly depends on experts. In this paper, we propose EmbryosFormer, a computational model to automatically detect and classify cell divisions from original time-lapse images. Our proposed network is designed as an encoder-decoder deformable transformer with collaborative heads. The transformer contracting path predicts per-image labels and is optimized by a classification head. The transformer expanding path models the temporal coherency between embryo images to ensure monotonic non-decreasing constraint and is optimized by a segmentation head. Both contracting and expanding paths are synergetically learned by a collaboration head. We have benchmarked our proposed EmbryosFormer on two datasets: a public dataset with mouse embryos with 8-cell stage and an in-house dataset with human embryos with 4-cell stage. Source code: https://github.com/UARK-AICV/Embryos.

Lifelogging was introduced as the process of passively capturing personal daily events via wearable devices. It ultimately creates a visual diary encoding every aspect of one's life with the aim of future sharing or recollecting. In this paper, we present LifeSeeker, a lifelog image retrieval system participating in the Lifelog Search Challenge (LSC) for 3 years, since 2019. Our objective is to support users to seek specific life moments using a combination of textual descriptions, spatial relationships, location information, and image similarities. In addition to the LSC challenge results, a further experiment was conducted in order to evaluate the power retrieval of our system on both expert and novice users. This experiment informed us about the effectiveness of the user's interaction with the system when involving non-experts.

In the age of rapid development of the Internet of Things (IoT) world, more and more cybersecurity incidents have emerged in many IoT devices and systems. Therefore, the need for cybercrime investigation, especially for IoT devices, has become more imperative than ever. Memory forensics, the approach that inspects the memory dump to understand the current state or behavior of the attacked machine, contributes an important position in digital forensics and incident response for IoT systems. However, memory forensics encounter various challenges, including virtual address space (VAS) reconstruction or extracting kernel data structure in a given memory image. Most current tools and approaches leverage the knowledge of the operating system or propose heuristics to evade the commission of rebuilding VAS. In this research, we present our novel methodology to reconstruct the VAS for the memory images by using the paging mechanism of the Central Processing Unit (CPU), primarily for the ARM architectures (32 and 64 bit), one of the most popular microprocessors in the IoT world. In addition, with the support of VAS, we extract the typical kernel data structure like the process linked list. Finally, we build a MemInspect2 toolset that gathers all algorithms, and we also test the tool in many standard OS kernels like Linux and BSD.

For the fifth time since 2018, the Lifelog Search Challenge (LSC) facilitated a benchmarking exercise to compare interactive search systems designed for multimodal lifelogs. LSC'22 attracted nine participating research groups who developed interactive lifelog retrieval systems enabling fast and effective access to lifelogs. The systems competed in front of a hybrid audience at the LSC workshop at ACM ICMR'22. This paper presents an introduction to the LSC workshop, the new (larger) dataset used in the competition, and introduces the participating lifelog search systems.

This paper pushes the envelope on decomposing camouflaged regions in an image into meaningful components, namely, camouflaged instances. To promote the new task of camouflaged instance segmentation of in-the-wild images, we introduce a dataset, dubbed CAMO++, that extends our preliminary CAMO dataset (camouflaged object segmentation) in terms of quantity and diversity. The new dataset substantially increases the number of images with hierarchical pixel-wise ground truths. We also provide a benchmark suite for the task of camouflaged instance segmentation. In particular, we present an extensive evaluation of state-of-the-art instance segmentation methods on our newly constructed CAMO++ dataset in various scenarios. We also present a camouflage fusion learning (CFL) framework for camouflaged instance segmentation to further improve the performance of state-of-the-art methods. The dataset, model, evaluation suite, and benchmark will be made publicly available on our project page.

In this paper, we investigate the interesting yet challenging problem of camouflaged instance segmentation. To this end, we first annotate the available CAMO dataset at the instance level. We also embed the data augmentation in order to increase the number of training samples. Then, we train different state-of-the-art instance segmentation on the CAMO-instance data. Last but not least, we develop an interactive user interface which demonstrates the performance of different state-of-the-art instance segmentation methods on the task of camouflaged instance segmentation. The users are able to compare the results of different methods on the given input images. Our work is expected to push the envelope of the camouflage analysis problem.

In this paper, we introduce a practical system for interactive video object mask annotation, which can support multiple back-end methods. To demonstrate the generalization of our system, we introduce a novel approach for video object annotation. Our proposed system takes scribbles at a chosen key-frame from the end-users via a user-friendly interface and produces masks of corresponding objects at the key-frame via the Control-Point-based Scribbles-to-Mask (CPSM) module. The object masks at the key-frame are then propagated to other frames and refined through the Multi-Referenced Guided Segmentation (MRGS) module. Last but not least, the user can correct wrong segmentation at some frames, and the corrected mask is continuously propagated to other frames in the video via the MRGS to produce the object masks at all video frames.

Language prior plays an important role in the way humans detect and recognize text in the wild. Current scene text recognition methods do use lexicons to improve recognition performance, but their naive approach of casting the output into a dictionary word based purely on the edit distance has many limitations. In this paper, we present a novel approach to incorporate a dictionary in both the training and inference stage of a scene text recognition system. We use the dictionary to generate a list of possible outcomes and find the one that is most compatible with the visual appearance of the text. The proposed method leads to a robust scene text recognition model, which is better at handling ambiguous cases encountered in the wild, and improves the overall performance of state-of-the-art scene text spotting frameworks. Our work suggests that incorporating language prior is a potential approach to advance scene text detection and recognition methods. Besides, we contribute VinText, a challenging scene text dataset for Vietnamese, where some characters are equivocal in the visual form due to accent symbols. This dataset will serve as a challenging benchmark for measuring the applicability and robustness of scene text detection and recognition algorithms. Code and dataset are available at https://github.com/VinAIResearch/dict-guided.

Multi-Camera Multiple Object Tracking (MC-MOT) is a significant computer vision problem due to its emerging applicability in several real-world applications. Despite a large number of existing works, solving the data association problem in any MC-MOT pipeline is arguably one of the most challenging tasks. Developing a robust MC-MOT system, however, is still highly challenging due to many practical issues such as inconsistent lighting conditions, varying object movement patterns, or the trajectory occlusions of the objects between the cameras. To address these problems, this work, therefore, proposes a new Dynamic Graph Model with Link Prediction (DyGLIP) approach1to solve the data association task. Compared to existing methods, our new model offers several advantages, including better feature representations and the ability to recover from lost tracks during camera transitions. Moreover, our model works gracefully regardless of the overlapping ratios between the cameras. Experimental results show that we out-perform existing MC-MOT algorithms by a large margin on several practical datasets. Notably, our model works favor-ably on online settings but can be extended to an incremental approach for large-scale datasets.

Temporal action proposal generation is an essential and challenging task that aims at localizing temporal intervals containing human actions in untrimmed videos. Most of existing approaches are unable to follow the human cognitive process of understanding the video context due to lack of attention mechanism to express the concept of an action or an agent who performs the action or the interaction between the agent and the environment. Based on the action definition that a human, known as an agent, interacts with the environment and performs an action that affects the environment, we propose a contextual Agent-Environment Network. Our proposed contextual AEN involves (i) agent pathway, operating at a local level to tell about which humans/agents are acting and (ii) environment pathway operating at a global level to tell about how the agents interact with the environment. Comprehensive evaluations on 20-action THUMOS-14 and 200-action ActivityNet-1.3 datasets with different backbone networks, i.e C3D and SlowFast, show that our method robustly exhibits outperformance against state-of-the-art methods regardless of the employed backbone network.

Cross-data analytics and retrieval have gained significant improvement recently. People can now extract more data insights precisely and quickly towards having many excellent applications serving human lives. Since people create multimedia and other types of data that reflect the diverse perspectives of human lives, these data are just pieces of the puzzle of the world's pictures. Hence, it is necessary to assembly all these pieces towards having a better solution for human-centered problems. Hence, the workshop welcomes those who work with multimedia and others and come from diverse research domains and disciplines to work on intelligent cross-data analytics and retrieval to bring a smart, sustainable society to human beings. The research domain can vary from well-being, disaster prevention and mitigation, mobility to food computing, to name a few.

The Lifelog Search Challenge (LSC) is an annual benchmarking challenge for comparing approaches to interactive retrieval from multi-modal lifelogs. LSC'21, the fourth challenge, attracted sixteen participants, each of which had developed interactive retrieval systems for large multimodal lifelogs. These interactive retrieval systems participated in a comparative evaluation in front of an online live-audience at the LSC workshop at ACM ICMR'21. This overview presents the motivation for LSC'21, the lifelog dataset used in the competition, and the participating systems.

Identifying stress level can provide valuable data for mental health analytics as well as labels for annotation systems. Although much research has been conducted into stress detection models using heart rate variability at a higher cost of data collection, there is a lack of research on the potential of using low-resolution Electrodermal Activity (EDA) signals from consumer-grade wearable devices to identify stress patterns. In this paper, we concentrate on performing statistical analyses on the stress detection capability of two popular approaches of training stress detection models with stress-related biometric signals: user-dependent and user-independent models. Our research manages to show that user-dependent models are statistically more accurate for stress detection. In terms of effectiveness assessment, the balanced accuracy (BA) metric is employed to evaluate the capability of distinguishing stress and non-stress conditions of the models trained on either low-resolution or high-resolution Electrodermal Activity (EDA) signals. The results from the experiment show that training the model with (comparatively low-cost) low-resolution EDA signal does not affect the stress detection accuracy of the model significantly compared to using a high-resolution EDA signal. Our research results demonstrate the potential of attaching the user-dependent stress detection model trained on personal low-resolution EDA signal recorded to collect data in daily life to provide users with personal stress level insight and analysis.

Gastrointestinal (GI) endoscopy has been an active field of research motivated by the large number of highly lethal GI cancers. Early GI cancer precursors are often missed during the endoscopic surveillance. The high missed rate of such abnormalities during endoscopy is thus a critical bottleneck. Lack of attentiveness due to tiring procedures, and requirement of training are few contributing factors. An automatic GI disease classification system can help reduce such risks by flagging suspicious frames and lesions. GI endoscopy consists of several multi-organ surveillance, therefore, there is need to develop methods that can generalize to various endoscopic findings. In this realm, we present a comprehensive analysis of the Medico GI challenges: Medical Multimedia Task at MediaEval 2017, Medico Multimedia Task at MediaEval 2018, and BioMedia ACM MM Grand Challenge 2019. These challenges are initiative to set-up a benchmark for different computer vision methods applied to the multi-class endoscopic images and promote to build new approaches that could reliably be used in clinics. We report the performance of 21 participating teams over a period of three consecutive years and provide a detailed analysis of the methods used by the participants, highlighting the challenges and shortcomings of the current approaches and dissect their credibility for the use in clinical settings. Our analysis revealed that the participants achieved an improvement on maximum Mathew correlation coefficient (MCC) from 82.68% in 2017 to 93.98% in 2018 and 95.20% in 2019 challenges, and a significant increase in computational speed over consecutive years.

The Lifelog Search Challenge (LSC) is an annual comparative benchmarking activity for comparing approaches to interactive retrieval from multi-modal lifelogs. LSC'20, the third such challenge, attracts fourteen participants with their interactive lifelog retrieval systems. These systems are comparatively evaluated in front of a live-audience at the LSC workshop at ACM ICMR'20 in Dublin, Ireland. This overview motivates the challenge, presents the dataset and system configuration used in the challenge, and briefly presents the participating teams.

It is essential to develop efficient methods to detect abnormal events, such as car-crashes or stalled vehicles, from surveillance cameras to provide in-time help. This motivates us to propose a novel method to detect traffic accidents in traffic videos. To tackle the problem where anomalies only occupy a small amount of data, we propose a semi-supervised method using Generative Adversarial Network trained on regular sequences to predict future frames. Our key idea is to model the ordinary world with a generative model, then compare a predicted frame with the real next frame to determine if an abnormal event occurs. We also propose a new idea of encoding motion descriptors and scaled intensity loss function to optimize GAN for fast-moving objects. Experiments on the Traffic Anomaly Detection dataset of AI City Challenge 2019 show that our method achieves the top 3 results with F1 score 0.9412 and RMSE 4.8088, and S3 score 0.9261. Our method can be applied to different related applications of anomaly and outlier detection in videos.

Floods are the most common natural and among the most dangerous disasters in the world. It is important to get up-to-date information about flooding and the flood level for flood preparation and prevention. In this paper, we propose an efficient method to determine the flood level from daily activity photos on social media. Our method is based on the idea of matching the water level with human pose to determine the level of severity of flooding. Extensive experiments conducted on the dataset of Multimodal Flood Level Estimation show the superiority of our proposed method. We achieve the first rank in MediaEval 2019 and this demonstrates the potential applications of our method to analyze flood information.

Nowadays, communication technologies are more and more strongly advanced, such as 4G or 5G. There are many useful online applications, and one of them is the telecare medical information system (TMIS). If the TMIS is widely deployed, patients and doctors will have more frequently connection. Clearly, this enhances our quality of life. One of the most important modules securely constructing this convenient TMIS is the user-authentication scheme. We should prevent user identity and related information from the adversary’s eavesdropping. Therefore, the authentication scheme could provide user anonymity and concern some kinds of attacks, such as impersonation or password-guessing attacks. Common solutions are a combination of hash function and public-key cryptosystem (RSA or elliptic curve cryptosystem, ECC), but current schemes do not consider identity protection as one main task necessary for medical information environment. In this paper, our results consist of some important analyses of previous works and a multiserver user-authentication scheme suitable for TMIS using Chebyshev polynomial with two models: random oracle and BAN-logic.

Generalized nucleus segmentation techniques can contribute greatly to reducing the time to develop and validate visual biomarkers for new digital pathology datasets. We summarize the results of MoNuSeg 2018 Challenge whose objective was to develop generalizable nuclei segmentation techniques in digital pathology. The challenge was an official satellite event of the MICCAI 2018 conference in which 32 teams with more than 80 participants from geographically diverse institutes participated. Contestants were given a training set with 30 images from seven organs with annotations of 21,623 individual nuclei. A test dataset with 14 images taken from seven organs, including two organs that did not appear in the training set was released without annotations. Entries were evaluated based on average aggregated Jaccard index (AJI) on the test set to prioritize accurate instance segmentation as opposed to mere semantic segmentation. More than half the teams that completed the challenge outperformed a previous baseline. Among the trends observed that contributed to increased accuracy were the use of color normalization as well as heavy data augmentation. Additionally, fully convolutional networks inspired by variants of U-Net, FCN, and Mask-RCNN were popularly used, typically based on ResNet or VGG base architectures. Watershed segmentation on predicted semantic segmentation maps was a popular post-processing strategy. Several of the top techniques compared favorably to an individual human annotator and can be used with confidence for nuclear morphometrics.

Inspired by recent advances in computer vision and deep learning, we propose new enhancements to tackle problems appearing in endoscopic image analysis, especially abnormality finding and anatomical landmark detection. In details, a combination of Residual Neural Network and Faster R-CNN are jointly applied in order to take all of their advantages and improve the overall performance. Nevertheless, novel data augmentation is designed and adapted to corresponding domains. Our approaches prove their competitive results in term of not only the accuracy but also the inference time in Medico: The 2018 Multimedia for Medicine Task and The Biomedia ACM MM Grand Challenge 2019. These results show the great potential of the collaborating between deep learning models and data augmentation in medical image analysis applications. Especially, more than 4900 bounding boxes localizing the symptom of some classes from KVASIR dataset that we annotated and used in this project are shared online for future research.

With nonstop development of communication technologies, all aspects of social life continuously change and so do network systems. When establishing connection is easy, the convenience of online-service receives many users’ attentions, for example, the patients directly access medical system to be advised by doctors at any time. Therefore, user authentication scheme is necessary when we want to provide privacy and security for working sessions. Storing a password list for verification is an old method and not secure. This list can be easily leaked, and adversary can launch an offline password-guessing attack. In addition, information exchanged between user and server needs being prevented from attacker’s decryption. It can be said that current authentication schemes are unsuitable for new security standard. We need a strong user authentication scheme using new approach to overcome existing limitations and guarantee time efficiency. In this paper, we make a design with Chebyshev polynomial to achieve our goals and resist some kinds of attacks.

Many categories of the illusion of self-motion have been widely studied with the potential support of virtual reality. However, the effects of directly and indirectly powering the movement on the possibility of perceiving changes in moving speed and their relationship with sensory feedback on users' speed change perception have not been investigated before. In this paper, we present the results of our user study on the difference in perceiving changes in moving speed between two different movement techniques: "pedaling" and "throttling". We also explore the effects of different velocity gains, accelerations and speeds of airflow, and their interactions with the movement techniques on users' perception of speed changes in addition to user performance and perception. We built a bike simulator that supports both of the movement techniques and provides sensory feedback. In general, "pedaling" gave users more possibility to perceive changes in moving velocity than "throttling".

At DAVIS-2016 Challenge, many state-of-art video segmentation methods achieve potential results, but they still much depend on annotated frames to distinguish between background and foreground. It takes a lot of time and efforts to create these frames exactly. In this paper, we introduce a method to segment objects from video based on keywords given by user. First, we use a real-time object detection system - YOLOv2 to identify regions containing objects that have labels match with the given keywords in the first frame. Then, for each region identified from the previous step, we use Pyramid Scene Parsing Network to assign each pixel as foreground or background. These frames can be used as input frames for Object Flow algorithm to perform segmentation on entire video. We conduct experiments on a subset of DAVIS-2016 dataset in half the size of its original size, which shows that our method can handle many popular classes in PASCAL VOC 2012 dataset with acceptable accuracy, about 75.03%. We suggest widely testing by combining other methods to improve this result in the future.

Recently, the telecare medicine information system (TMIS) is one of the most convenient health-care deliveries. It helps the patient and doctor keep frequent connection, so the quality of medical treatment is enhanced. Two main problems needed to be considered are the security and privacy of patient. Many schemes proposed to satisfy such requirements are not suitable for public medical environment because of their some limitations. For example, the patients identity and password are not protected, time consuming computations in such schemes take a lot of time in authentication phase. In this paper, we survey some typical previous results in this area to inherit some advantages. Afterward, we propose a provable lightweight dedicated scheme appropriate for TMIS in insecure channel.

People frequently post their photos on social network sites (e.g. Facebook, Instagram) as a way to share memorable moments, emotions, or locations visited. While sharing photos with the same subjects as past photos could lead to user reminiscence and potentially create valuable benefits, existing products still cannot support this adequately. Based on a survey on user habits in sharing and revisiting photos on social network sites, we propose NowAndThen, a photo recommendation concept and tool that assists reminiscence when sharing photos on social network sites. By combining visual features of the photos and associated tags, a prototype we developed can recommend old photos that have common subjects with the user's current photos of interest. Our study with the prototype shows that this approach can help users positively revive past memories and connections with their friends. In addition, our results include various design insights and implications for future reminiscence-support systems.

Combining Convolutional Neural Network and Deformable Part Models is a new trend in object detection area. Following this trend, we propose Adaptive WildNet Face network using Deformable Part Models structure to exploit advantages of two methods in face detection area. We evaluate the merit of our method on Face Detection Data Set and Benchmark. Experimental results show that our method achieves up to 86.22% true positive images in 1000 false positive images in FDDB. Our method becomes one of state-of-the-art methods in FDDB dataset and it opens a new way to detect faces of images in the wild.

Bag-of-Word based model is one of the state-of-the-art approaches for object retrieval or also known as instance search problem. Although this model and its extensions are good for rich-textured objects, it is still unsolved for searching on textureless ones. In this paper, we propose to combine this model with Deformable Part Models object detector using late fusion technique to improve final result. To find the optimal weights for each type of query objects, we further propose to use a neural network to learn query features including object area, number of shared visual words to get optimal weights for each model. Experimental results on TRECVID Instance Search (INS) dataset with queries in INS2013 and INS2014 show that our proposed method significantly improves 18.48% and 14.63% in mAP respectively comparing to standard BOW model and outperform other state-of-the-art methods. This method opens a new way of adaptively combining DPM, an object detector, in a hybrid model for visual instance search.

Time-related information in message posted on-line is one type of sensitive information targeted by attackers, one reason that sharing information online can be risky. Therefore, time information should be anonymized before it is posted in online social networks (OSNs). One approach to reducing the risk is to anonymize the personal information by removing temporal phrases, but this makes the anonymous message loses too much information. We have proposed a system for creating anonymous fingerprints about temporal phrases to cover most of potential cases of OSN disclosure. The fingerprints not only anonymize time-related information but also can be used to identify a person who has disclosed information about the user. In experiment with 16,647 different temporal phrases extracted from about 16 million tweets, the average number of fingerprints created for an OSN message is 526.05 fingerprints. This is significantly better than the 409.58 fingerprints of the state-of-the-art previous detection temporal phrases algorithm. Fingerprints are quantified using a modified normalized certainty penalty metric to ensure that an appropriate level of information anonymity is used for each user's friend. The algorithm works well not only for temporal phrases in message posted on social networks but also for other types of phrases (such as location and objective ones) or other areas (religion, politics, military, etc.).

The authors propose a novel pre-processing phase that can be integrated into conventional methods to detect and recognize planar visual objects in printed materials with low computational cost and higher accuracy. A simple yet efficient visual saliency estimation technique based on regional contrast is developed to quickly filter out low informative regions in printed materials. By eliminating noisy or unimportant keypoint candidates, our proposed method not only reduces unnecessary computational cost of keypoint descriptors but also increases robustness and accuracy of visual object recognition. Our experimental results show that the whole visual object recognition process can be speeded up 46 times and the accuracy can increase up to 23%. These are desirable advantages for an augmented reality system, especially on mobile devices. Furthermore, this pre-processing stage is independent of the choice of features and matching model in a general process. Therefore it can be used to boost the performance of existing systems into real-time manner.

The problems of digitalization and transformation of musical scores into machine-readable format are necessary to be solved since they help people to enjoy music, to learn music, to conserve music sheets, and even to assist music composers. However, the results of existing methods still require improvements for higher accuracy. Therefore, the authors propose lightweight algorithms for Optical Music Recognition to help people to recognize and automatically play musical scores. In our proposal, after removing staff lines and extracting symbols, each music symbol is represented as a grid of identical M ∗ N cells, and the features are extracted and classified with multiple lightweight SVM classifiers. Through experiments, the authors find that the size of 10 ∗ 12 cells yields the highest precision value. Experimental results on the dataset consisting of 4929 music symbols taken from 18 modern music sheets in the Synthetic Score Database show that our proposed method is able to classify printed musical scores with accuracy up to 99.56%.

To boost up power of unsupervised feature learning and deep learning, there has been a great effort in optimizing network structure to learn more efficient high level features. It is crucial for a network to have a sufficient amount of learnable parameters yet still be able to capture in variances in data. In this paper, the authors propose spatial boosting networks, which employ convolutional feature learning networks as learning components. Each component in a network is assigned to a certain spatial region. This allows the network learn more adaptive features for each region. In order to make spatial boosting networks to capture relationship between regions of the visual field, we also propose convolutional pooling procedure. By expanding pooling scope into overlapping regions, we expect the features pooled in higher level to be more robust to noises and more invariant to transformation. Experiments show that using spatial boosting networks boosts up accuracy up to 3% from conventional approaches in standard datasets CIFAR and STL. Moreover, these results are competitive in comparison with other methods by using only a basic feature learning algorithm.

Lateral connection is a fundamental element of human neural networks which enables sparse learning and topographical order in feature maps. Due to high complexity and computational cost, computer scientists tend to simplify it in practical implementations. To utilize the simplicity of traditional networks while preserving the effects of interconnections, the authors employ numerical filters in unsupervised learning networks. These filters suppress low activations and decorrelate high ones, which are similar to how inhibitory lateral connections behave. Inhibitory networks outperform conventional approach in both standard datasets CIFAR-10 and STL-10. Our method also yields competitive results in comparison with other single-layer unsupervised networks. Furthermore, it is promising to apply inhibitory networks into deep learning systems for complex recognition problem.

Because of non-stop applications' growth of network environment, making communications in such ambiance security is very important. Recently, Ashok Kumar Das has proposed a scheme to recover some pitfalls in Li et al.'s scheme. Das's protocol also utilizes biometrics and random value instead of time - stamp. Besides, storing temporary nonce to withstand replay attack is an inherited aspect of this scheme. However, in this paper, we show Das's scheme has many problems. To isolate them, we suggested a new design. Our scheme not only saves computational cost but also enhances security for transactions in insecure network channel.

One approach to overcoming the problem of too much information about a user being disclosed on social networking services (by the user or by the user's friends) through natural language texts (blogs, comments, status updates, etc.) is to anonymize the texts. However, determining which information is sensitive and should thus be anonymized is a challenging problem. Sensitive information is any information about a user that could be used to identify the user. We have developed an algorithm that anonymizes sensitive information in text to be posted by generalization. Synonyms for the anonymized information are used as fingerprints for detecting a discloser of the information. The fingerprints are quantified using the modified discernability metric to enable an appropriate level of anonymity to be used for each group of the user's friends. The fingerprints cannot be converted into another one to incorrectly identify a person who has revealed sensitive information. Use of the algorithm to control the disclosure of information on Facebook demonstrated that it works well not only in social networking but also in other areas (health, religion, politics, military, etc.) that store sensitive information.

Template matching is one of the significant methods used in most computer vision applications. However, one disadvantage of existing template matching methods is that a template must be a rectangular image. Several solutions can be used to overcome this problem, such as feature-based, edge-based, etc., but most of them do not meet the requirements of practical applications because of their slow speed or low accuracy. In this paper, the authors propose a process for matching a template with an arbitrary shape using the idea of coarse-fine and refining interesting regions. Variety of measures can be used to provide different levels of performance for each practical situation. Experiments show that the process performs an impressive performance in average. Using the same measures, the proposed process works 5 times faster than the FFT template matching method (implemented in OpenCV), while achieving the similar accuracy. Moreover, most parts of the proposed process can be executed in parallel on multi-core CPUs or GPUs.

We propose a binomial-mix-based location anonymizer system with global dummy generation to protect user location privacy in location-based services in the face of attacks from a global active adversary and even with untrusted location-based service providers. Our proposed system overcomes the disadvantages of high latency in general-purpose mix-net systems when they are applied to location-based services, and the imprecision of query result or inefficiency due to large number of candidates in query result of existing obfuscation or spatial cloaking techniques. In our system, dummies (false locations) are generated globally in order to reduce the latency of requests to location-based services. A centralized dummy generation mechanism exploits all users' activities to optimize the system's behavior and performance. Because of the randomness provided by a binomial mix, our system prevents an adversary from determining with certainty whether a user is at a specific location. Our system also lets users define and update their personal location privacy maps and satisfies a probabilistic real-time condition that ensures delivery of any request within a predefined duration with high probability.

We propose RPROB, an infinite family of anonymous communication systems, each of which corresponds to a binomial mix. Any instance of RPROB provides resistance against global active adversary with capabilities to monitor every external activity, to delay and to create messages in the system. Our proposal is to solve the limitation of APROB channel that concerns only global delaying adversary. Experimental evaluation shows that any instance of RPROB provides higher anonymity than APROB channel with the same environment and users' behaviors (rate and number of sent messages). Furthermore, because of the randomness provided by a binomial mix, an adversary cannot determine with certainty the probability of a user to be a sender of a delivered message in RPROB system as in pool-based APROB channel. The prefix `R' in RPROB is to emphasize the randomness of our proposal. RPROB also provides flexibility for users to justify their level of anonymity (and speed) and satisfies probabilistic real-time condition which ensures to deliver any message within a predefined duration with high probability.