Search

Questioning is a fundamental aspect of education, as it helps assess students' understanding, promotes critical thinking, and encourages active engagement. With the rise of artificial intelligence in education, there is a growing interest in developing intelligent systems that can automatically generate and answer questions and facilitate interactions in both virtual and in-person education settings. However, to develop effective AI models for education, it is essential to have a fundamental understanding of questioning. In this study, we created the YouTube Learners' Questions on Bloom's Taxonomy Dataset (YouLeQD), which contains learner-posed questions from YouTube lecture video comments. Along with the dataset, we developed two RoBERTa-based classification models leveraging Large Language Models to detect questions and analyze their cognitive complexity using Bloom's Taxonomy. This dataset and our findings provide valuable insights into the cognitive complexity of learner-posed questions in educational videos and their relationship with interaction metrics. This can aid in the development of more effective AI models for education and improve the overall learning experience for students., Comment: 11pages. Extended version, Jan 2025. A shortened version was resubmitted and published in IEEE Conference on Semantic Computing Feb 2025

In recent years, semantic segmentation has flourished in various applications. However, the high computational cost remains a significant challenge that hinders its further adoption. The filter pruning method for structured network slimming offers a direct and effective solution for the reduction of segmentation networks. Nevertheless, we argue that most existing pruning methods, originally designed for image classification, overlook the fact that segmentation is a location-sensitive task, which consequently leads to their suboptimal performance when applied to segmentation networks. To address this issue, this paper proposes a novel approach, denoted as Spatial-aware Information Redundancy Filter Pruning~(SIRFP), which aims to reduce feature redundancy between channels. First, we formulate the pruning process as a maximum edge weight clique problem~(MEWCP) in graph theory, thereby minimizing the redundancy among the remaining features after pruning. Within this framework, we introduce a spatial-aware redundancy metric based on feature maps, thus endowing the pruning process with location sensitivity to better adapt to pruning segmentation networks. Additionally, based on the MEWCP, we propose a low computational complexity greedy strategy to solve this NP-hard problem, making it feasible and efficient for structured pruning. To validate the effectiveness of our method, we conducted extensive comparative experiments on various challenging datasets. The results demonstrate the superior performance of SIRFP for semantic segmentation tasks., Comment: Accepted by AAAI 2025

Class incremental semantic segmentation (CISS) aims to segment new classes during continual steps while preventing the forgetting of old knowledge. Existing methods alleviate catastrophic forgetting by replaying distributions of previously learned classes using stored prototypes or features. However, they overlook a critical issue: in CISS, the representation of class knowledge is updated continuously through incremental learning, whereas prototype replay methods maintain fixed prototypes. This mismatch between updated representation and fixed prototypes limits the effectiveness of the prototype replay strategy. To address this issue, we propose the Adaptive prototype replay (Adapter) for CISS in this paper. Adapter comprises an adaptive deviation compen sation (ADC) strategy and an uncertainty-aware constraint (UAC) loss. Specifically, the ADC strategy dynamically updates the stored prototypes based on the estimated representation shift distance to match the updated representation of old class. The UAC loss reduces prediction uncertainty, aggregating discriminative features to aid in generating compact prototypes. Additionally, we introduce a compensation-based prototype similarity discriminative (CPD) loss to ensure adequate differentiation between similar prototypes, thereby enhancing the efficiency of the adaptive prototype replay strategy. Extensive experiments on Pascal VOC and ADE20K datasets demonstrate that Adapter achieves state-of-the-art results and proves effective across various CISS tasks, particularly in challenging multi-step scenarios. The code and model is available at https://github.com/zhu-gl-ux/Adapter., Comment: Accepted by the Main Technical Track of the 39th Annual AAAI Conference on Artificial Intelligence (AAAI-2025)

The insufficient generalization of adaptive moment estimation (Adam) has hindered its broader application. Recent studies have shown that flat minima in loss landscapes are highly associated with improved generalization. Inspired by the filtering effect of integration operations on high-frequency signals, we propose multiple integral Adam (MIAdam), a novel optimizer that integrates a multiple integral term into Adam. This multiple integral term effectively filters out sharp minima encountered during optimization, guiding the optimizer towards flatter regions and thereby enhancing generalization capability. We provide a theoretical explanation for the improvement in generalization through the diffusion theory framework and analyze the impact of the multiple integral term on the optimizer's convergence. Experimental results demonstrate that MIAdam not only enhances generalization and robustness against label noise but also maintains the rapid convergence characteristic of Adam, outperforming Adam and its variants in state-of-the-art benchmarks.

In this paper, we present generalization bounds for the unsupervised risk in the Deep Contrastive Representation Learning framework, which employs deep neural networks as representation functions. We approach this problem from two angles. On the one hand, we derive a parameter-counting bound that scales with the overall size of the neural networks. On the other hand, we provide a norm-based bound that scales with the norms of neural networks' weight matrices. Ignoring logarithmic factors, the bounds are independent of $k$, the size of the tuples provided for contrastive learning. To the best of our knowledge, this property is only shared by one other work, which employed a different proof strategy and suffers from very strong exponential dependence on the depth of the network which is due to a use of the peeling technique. Our results circumvent this by leveraging powerful results on covering numbers with respect to uniform norms over samples. In addition, we utilize loss augmentation techniques to further reduce the dependency on matrix norms and the implicit dependence on network depth. In fact, our techniques allow us to produce many bounds for the contrastive learning setting with similar architectural dependencies as in the study of the sample complexity of ordinary loss functions, thereby bridging the gap between the learning theories of contrastive learning and DNNs., Comment: Accepted at AAAI 2025

How can we enable models to comprehend video anomalies occurring over varying temporal scales and contexts? Traditional Video Anomaly Understanding (VAU) methods focus on frame-level anomaly prediction, often missing the interpretability of complex and diverse real-world anomalies. Recent multimodal approaches leverage visual and textual data but lack hierarchical annotations that capture both short-term and long-term anomalies. To address this challenge, we introduce HIVAU-70k, a large-scale benchmark for hierarchical video anomaly understanding across any granularity. We develop a semi-automated annotation engine that efficiently scales high-quality annotations by combining manual video segmentation with recursive free-text annotation using large language models (LLMs). This results in over 70,000 multi-granular annotations organized at clip-level, event-level, and video-level segments. For efficient anomaly detection in long videos, we propose the Anomaly-focused Temporal Sampler (ATS). ATS integrates an anomaly scorer with a density-aware sampler to adaptively select frames based on anomaly scores, ensuring that the multimodal LLM concentrates on anomaly-rich regions, which significantly enhances both efficiency and accuracy. Extensive experiments demonstrate that our hierarchical instruction data markedly improves anomaly comprehension. The integrated ATS and visual-language model outperform traditional methods in processing long videos. Our benchmark and model are publicly available at https://github.com/pipixin321/HolmesVAU., Comment: 21 pages

Compute Express Link (CXL) serves as a rising industry standard, delivering high-speed cache-coherent links to a variety of devices, including host CPUs, computational accelerators, and memory devices. It is designed to promote system scalability, enable peer-to-peer exchanges, and accelerate data transmissions. To achieve these objectives, the most recent CXL protocol has brought forth several innovative features, such as port-focused routing, device-handled coherence, and PCIe 6.0 compatibility. However, due to the limited availability of hardware prototypes and simulators compatible with CXL, earlier CXL research has largely depended on emulating CXL devices using remote NUMA nodes. Unfortunately, these NUMA-based emulators have difficulties in accurately representing the new features due to fundamental differences in hardware and protocols. Moreover, the absence of support for non-tree topology and PCIe links makes it complex to merely adapt existing simulators for CXL simulation. To overcome these problems, we introduce ESF, a simulation framework specifically designed for CXL systems. ESF has been developed to accurately reflect the unique features of the latest CXL protocol from the ground up. It uses a specialized interconnect layer to facilitate connections within a wide range of system topologies and also includes key components to carry out specific functions required by these features. By utilizing ESF, we thoroughly investigate various aspects of CXL systems, including system topology, device-handled coherence, and the effects of PCIe characteristics, leading to important findings that can guide the creation of high-performance CXL systems. The ESF source codes are fully open-source and can be accessed at https://anonymous.4open.science/r/ESF-1CE3.

Liquid Crystal Elastomers with near-ambient temperature-responsiveness (NAT-LCEs) have been extensively studied for building bio-compatible, low-power consumption devices and robotics. However, conventional manufacturing methods face limitations in programmability (e.g., molding) or low nematic order (e.g., DIW printing). Here, a hybrid cooling strategy is proposed for programmable 3D printing of NAT-LCEs with enhanced nematic order, intricate shape forming, and morphing capability. By integrating a low-temperature nozzle and a cooling platform into a 3D printer, the resulting temperature field synergistically facilitates mesogen alignment during extrusion and disruption-free UV cross-linking. This method achieves a nematic order 3000% higher than NAT-LCEs fabricated using traditional room temperature 3D printing. Enabled by shifting of transition temperature during hybrid cooling printing, printed sheets spontaneously turn into 3D structures after release from the platform, exhibiting bidirectional deformation with heating and cooling. By adjusting the nozzle and plate temperatures, NAT-LCEs with graded properties can be fabricated for intricate shape morphing. A wristband system with enhanced heart rate monitoring is also developed based on 3D-printed NAT-LCE. Our method may open new possibilities for soft robotics, biomedical devices, and wearable electronics.

Compute eXpress Link (CXL) is a pivotal technology for memory disaggregation in future heterogeneous computing systems, enabling on-demand memory expansion and improved resource utilization. Despite its potential, CXL is in its early stages with limited market products, highlighting the need for a reliable system-level simulation tool. This paper introduces CXL-DMSim, an open-source, high-fidelity full-system simulator for CXL disaggregated memory systems, comparable in speed to gem5. CXL-DMSim includes a flexible CXL memory expander model, device driver, and support for CXL\.io and CXL\.mem protocols. It supports both app-managed and kernel-managed modes, with the latter featuring a NUMA-compatible mechanism. Rigorous verification against real hardware testbeds with FPGA-based and ASIC-based CXL memory prototypes confirms CXL-DMSim's accuracy, with an average simulation error of 4.1%. Benchmark results using LMbench and STREAM indicate that CXL-FPGA memory has approximately ~2.88x higher latency than local DDR, while CXL-ASIC latency is about ~2.18x. CXL-FPGA achieves 45-69% of local DDR's memory bandwidth, and CXL-ASIC reaches 82-83%. The performance of CXL memory is significantly more sensitive to Rd/Wr patterns than local DDR, with optimal bandwidth at a 74%:26% ratio rather than 50%:50% due to the current CXL+DDR controller design. The study also shows that CXL memory can markedly enhance the performance of memory-intensive applications, with the most improvement seen in Viper (~23x) and in bandwidth-sensitive scenarios like MERCI (16%). CXL-DMSim's observability and expandability are demonstrated through detailed case studies, showcasing its potential for research on future CXL-interconnected hybrid memory pools., Comment: 15 pages, 19 figures

We study the problem of fair allocation of a set of indivisible items among agents with additive valuations, under matroid constraints and two generalizations: $p$-extendible system and independence system constraints. The objective is to find fair and efficient allocations in which the subset of items assigned to every agent satisfies the given constraint. We focus on a common fairness notion of envy-freeness up to one item (EF1) and a well-known efficient (and fair) notion of the maximum Nash social welfare (Max-NSW). By using properties of matroids, we demonstrate that the Max-NSW allocation, implying Pareto optimality (PO), achieves a tight $1/2$-EF1 under matroid constraints. This result resolves an open question proposed in prior literature [26]. In particular, if agents have 2-valued ($\{1, a\}$) valuations, we prove that the Max-NSW allocation admits $\max\{1/a^2, 1/2\}$-EF1 and PO. Under strongly $p$-extendible system constraints, we show that the Max-NSW allocation guarantees $\max\{1/p, 1/4\}$-EF1 and PO for identical binary valuations. Indeed, the approximation of $1/4$ is the ratio for independence system constraints and additive valuations. Additionally, for lexicographic preferences, we study possibly feasible allocations other than Max-NSW admitting exactly EF1 and PO under the above constraints.

The pervasive use of the Internet and social media introduces significant challenges to automated sentiment analysis, particularly for sarcastic expressions in user-generated content. Sarcasm conveys negative emotions through ostensibly positive or exaggerated language, complicating its detection within natural language processing tasks. To address this, we propose an innovative sarcasm detection model integrating Convolutional Neural Networks (CNN), Gated Recurrent Units (GRU), Long Short-Term Memory (LSTM), and Multi-Head Attention mechanisms. The CNN component captures local n-gram features, while GRU and LSTM layers model sequential dependencies and contextual information. Multi-Head Attention enhances the model's focus on relevant parts of the input, improving interpretability. Experiments on two sarcasm detection datasets, Headlines and Riloff, demonstrate that the model achieves an accuracy of 81.20% and an F1 score of 80.77% on Headlines, and an accuracy of 79.72% with an F1 score of 61.39% on Riloff, outperforming traditional models. These results validate the effectiveness of our hybrid approach for sarcasm detection in social media texts.

We focus on improving the visual understanding capability for boosting the vision-language models. We propose \textbf{Arcana}, a multiModal language model, which introduces two crucial techniques. First, we present Multimodal LoRA (MM-LoRA), a module designed to enhance the decoder. Unlike traditional language-driven decoders, MM-LoRA consists of two parallel LoRAs -- one for vision and one for language -- each with its own parameters. This disentangled parameters design allows for more specialized learning in each modality and better integration of multimodal information. Second, we introduce the Query Ladder adapter (QLadder) to improve the visual encoder. QLadder employs a learnable ``\textit{ladder}'' structure to deeply aggregates the intermediate representations from the frozen pretrained visual encoder (e.g., CLIP image encoder). This enables the model to learn new and informative visual features, as well as remaining the powerful capabilities of the pretrained visual encoder. These techniques collectively enhance Arcana's visual perception power, enabling it to leverage improved visual information for more accurate and contextually relevant outputs across various multimodal scenarios. Extensive experiments and ablation studies demonstrate the effectiveness and generalization capability of our Arcana. The code and re-annotated data are available at \url{https://arcana-project-page.github.io}.

Interactive portrait matting refers to extracting the soft portrait from a given image that best meets the user's intent through their inputs. Existing methods often underperform in complex scenarios, mainly due to three factors. (1) Most works apply a tightly coupled network that directly predicts matting results, lacking interpretability and resulting in inadequate modeling. (2) Existing works are limited to a single type of user input, which is ineffective for intention understanding and also inefficient for user operation. (3) The multi-round characteristics have been under-explored, which is crucial for user interaction. To alleviate these limitations, we propose DFIMat, a decoupled framework that enables flexible interactive matting. Specifically, we first decouple the task into 2 sub-ones: localizing target instances by understanding scene semantics and the flexible user inputs, and conducting refinement for instance-level matting. We observe a clear performance gain from decoupling, as it makes sub-tasks easier to learn, and the flexible multi-type input further enhances both effectiveness and efficiency. DFIMat also considers the multi-round interaction property, where a contrastive reasoning module is designed to enhance cross-round refinement. Another limitation for multi-person matting task is the lack of training data. We address this by introducing a new synthetic data generation pipeline that can generate much more realistic samples than previous arts. A new large-scale dataset SMPMat is subsequently established. Experiments verify the significant superiority of DFIMat. With it, we also investigate the roles of different input types, providing valuable principles for users. Our code and dataset can be found at https://github.com/JiaoSiyi/DFIMat., Comment: Accepted by ACCV 2024

Recent advancements in controllable human-centric video generation, particularly with the rise of diffusion models, have demonstrated considerable progress. However, achieving precise and localized control over human motion, e.g., replacing or inserting individuals into videos while exhibiting desired motion patterns, still remains challenging. In this work, we propose the ReplaceAnyone framework, which focuses on localizing and manipulating human motion in videos with diverse and intricate backgrounds. Specifically, we formulate this task as an image-conditioned pose-driven video inpainting paradigm, employing a unified video diffusion architecture that facilitates image-conditioned pose-driven video generation and inpainting within masked video regions. Moreover, we introduce diverse mask forms involving regular and irregular shapes to avoid shape leakage and allow granular local control. Additionally, we implement a two-stage training methodology, initially training an image-conditioned pose driven video generation model, followed by joint training of the video inpainting within masked areas. In this way, our approach enables seamless replacement or insertion of characters while maintaining the desired pose motion and reference appearance within a single framework. Experimental results demonstrate the effectiveness of our method in generating realistic and coherent video content., Comment: Work in progress

Recent researches have proven that pre-training on large-scale person images extracted from internet videos is an effective way in learning better representations for person re-identification. However, these researches are mostly confined to pre-training at the instance-level or single-video tracklet-level. They ignore the identity-invariance in images of the same person across different videos, which is a key focus in person re-identification. To address this issue, we propose a Cross-video Identity-cOrrelating pre-traiNing (CION) framework. Defining a noise concept that comprehensively considers both intra-identity consistency and inter-identity discrimination, CION seeks the identity correlation from cross-video images by modeling it as a progressive multi-level denoising problem. Furthermore, an identity-guided self-distillation loss is proposed to implement better large-scale pre-training by mining the identity-invariance within person images. We conduct extensive experiments to verify the superiority of our CION in terms of efficiency and performance. CION achieves significantly leading performance with even fewer training samples. For example, compared with the previous state-of-the-art~\cite{ISR}, CION with the same ResNet50-IBN achieves higher mAP of 93.3\% and 74.3\% on Market1501 and MSMT17, while only utilizing 8\% training samples. Finally, with CION demonstrating superior model-agnostic ability, we contribute a model zoo named ReIDZoo to meet diverse research and application needs in this field. It contains a series of CION pre-trained models with spanning structures and parameters, totaling 32 models with 10 different structures, including GhostNet, ConvNext, RepViT, FastViT and so on. The code and models will be made publicly available at https://github.com/Zplusdragon/CION_ReIDZoo., Comment: NeurIPS 2024 Accepted Paper

A knee point on a curve is the one where the curve levels off after an increase. In a computer system, it marks the point at which the system's performance is no longer improving significantly despite adding extra resources. Thus a knee point often represents an optimal point for decision. However, identifying knee points in noisy data is a challenging task. All previous works defined knee points based on the data in the original scale. However, in this work, we define knee points based on normalized data and provide a mathematical definition of curvature for normalized discrete data points, based on the mathematical definition of curvature for continuous functions. The impact of normalization exerted on curvature and the location of knee points are also discussed. Nevertheless, assessing the effectiveness of methods is difficult in the absence of ground truth data and benchmark datasets, which makes comparing existing methods challenging. In view of this, we create synthetic data that simulate real-world scenarios. We achieve this by selecting a set of functions that possess the required characteristics in this research and then introducing noise that satisfies the underlying distribution. In addition, we present a deep-learning approach and employ a Convolutional Neural Network (CNN) with a U-Net-like architecture, to accurately detect the knee point(s) of the underlying true distribution. The proposed model is evaluated against state-of-the-art methods. Experiments show that our network outperforms existing methods in all synthetic datasets, regardless of whether the samples have single or multiple knee points. In fact, our model achieves the best $F_{1}$ scores among all existing methods in all the test sets.

The mechanisms by which media inhomogeneity affects the three wave parametric instability (PI), including the wave number mismatch and the parameter gradients, are investigated using an approach based on the Wentzel-Kramers-Brillouin-Jeffreys (WKBJ) approximation. This approach transforms the coupling wave equations into an amplitude equation and iteratively solves its characteristic polynomials. By analyzing the solutions, we proposed that the wave number of the quasi-mode, a key term in the wave number mismatch of non-resonant type PI, should be a complex root of the quasi-mode's linear dispersion equation. Based on this, we derive a unified amplification factor formula that covers the resonant and non-resonant, the forward-scattered and backward-scattered types of PI. The impact of parameter gradients on the local spatial growth rate becomes significant when the inhomogeneity exceeds 10^{-3}. Considering parameter gradients extends our approach's validity to an inhomogeneity of about 10^{-2}. This approach holds promise for more specific PI modeling in the future., Comment: 33 pages, 5 figures, preprint version

Timely and effective vulnerability patching is essential for cybersecurity defense, for which various approaches have been proposed yet still struggle to generate valid and correct patches for real-world vulnerabilities. In this paper, we leverage the power and merits of pre-trained large language models (LLMs) to enable automated vulnerability patching using no test input/exploit evidence and without model training/fine-tuning. To elicit LLMs to effectively reason about vulnerable code behaviors, which is essential for quality patch generation, we introduce adaptive prompting on LLMs and instantiate the methodology as LLMPATCH, an automated LLM-based patching system. Our evaluation of LLMPATCH on real-world vulnerable code including zeroday vulnerabilities demonstrates its superior performance to both existing prompting methods and state-of-the-art non-LLM-based techniques (by 98.9% and 65.4% in F1 over the best baseline performance). LLMPATCH has also successfully patched 7 out of 11 zero-day vulnerabilities, including 2 that none of the four baselines compared were able to.

Detecting vulnerabilities is vital for software security, yet deep learning-based vulnerability detectors (DLVD) face a data shortage, which limits their effectiveness. Data augmentation can potentially alleviate the data shortage, but augmenting vulnerable code is challenging and requires a generative solution that maintains vulnerability. Previous works have only focused on generating samples that contain single statements or specific types of vulnerabilities. Recently, large language models (LLMs) have been used to solve various code generation and comprehension tasks with inspiring results, especially when fused with retrieval augmented generation (RAG). Therefore, we propose VulScribeR, a novel LLM-based solution that leverages carefully curated prompt templates to augment vulnerable datasets. More specifically, we explore three strategies to augment both single and multi-statement vulnerabilities, with LLMs, namely Mutation, Injection, and Extension. Our extensive evaluation across three vulnerability datasets and DLVD models, using two LLMs, show that our approach beats two SOTA methods Vulgen and VGX, and Random Oversampling (ROS) by 27.48%, 27.93%, and 15.41% in f1-score with 5K generated vulnerable samples on average, and 53.84%, 54.10%, 69.90%, and 40.93% with 15K generated vulnerable samples. Our approach demonstrates its feasibility for large-scale data augmentation by generating 1K samples at as cheap as US$ 1.88., Comment: 13 pages, 6 figures, 5 tables, 3 prompt templates, 1 algorithm

Automated Machine Learning (AutoML) offers a promising approach to streamline the training of machine learning models. However, existing AutoML frameworks are often limited to unimodal scenarios and require extensive manual configuration. Recent advancements in Large Language Models (LLMs) have showcased their exceptional abilities in reasoning, interaction, and code generation, presenting an opportunity to develop a more automated and user-friendly framework. To this end, we introduce AutoM3L, an innovative Automated Multimodal Machine Learning framework that leverages LLMs as controllers to automatically construct multimodal training pipelines. AutoM3L comprehends data modalities and selects appropriate models based on user requirements, providing automation and interactivity. By eliminating the need for manual feature engineering and hyperparameter optimization, our framework simplifies user engagement and enables customization through directives, addressing the limitations of previous rule-based AutoML approaches. We evaluate the performance of AutoM3L on six diverse multimodal datasets spanning classification, regression, and retrieval tasks, as well as a comprehensive set of unimodal datasets. The results demonstrate that AutoM3L achieves competitive or superior performance compared to traditional rule-based AutoML methods. Furthermore, a user study highlights the user-friendliness and usability of our framework, compared to the rule-based AutoML methods., Comment: Accpeted by ACMMM2024

In this paper, we utilize recent observational data from gamma-ray bursts (GRBs) and Pantheon+ supernovae Ia (SNe Ia) sample to explore the interacting dark energy (IDE) model in a phenomenological scenario. Results from GRBs alone, SNe Ia and GRBs+SNe Ia indicate that the energy is transferred from dark energy to dark matter and the coincidence problem is alleviated. The value of $H_0$ from GRBs+SNe Ia in the IDE scenario shows agreement with the SH0ES measurement. Considering the age estimate of the quasar APM 08279+5255 at $z = 3.91$, we find that the phenomenological IDE scenario can predict a cosmic age greater than that of the $\Lambda$CDM model, thus the cosmic age problem can be alleviated., Comment: 12 pages,3 figures. Res. Astron. Astrophys. in press. https://doi.org/10.1088/1674-4527/ad8a07

Currently, the integration of mobile Graphical User Interfaces (GUIs) is ubiquitous in most people's daily lives. And the ongoing evolution of multimodal large-scale models, such as GPT-4v, Qwen-VL-Max, has significantly bolstered the capabilities of GUI comprehension and user action analysis, showcasing the potentiality of intelligent GUI assistants. However, current GUI Agents often need to access page layout information through calling system APIs, which may pose privacy risks. Fixing GUI (such as mobile interfaces) to a certain low resolution might result in the loss of fine-grained image details. At the same time, the multimodal large models built for GUI Agents currently have poor understanding and decision-making abilities for Chinese GUI interfaces, making them difficult to apply to a large number of Chinese apps. This paper introduces MobileFlow, a multimodal large language model meticulously crafted for mobile GUI agents. Transforming from the open-source model Qwen-VL-Chat into GUI domain, MobileFlow contains approximately 21 billion parameters and is equipped with novel hybrid visual encoders, making it possible for variable resolutions of image inputs and good support for multilingual GUI. By incorporating Mixture of Experts (MoE) expansions and pioneering alignment training strategies, MobileFlow has the capacity to fully interpret image data and comprehend user instructions for GUI interaction tasks. Finally, MobileFlow outperforms Qwen-VL-Max and GPT-4v in terms of task execution by GUI agents on both public and our proposed evaluation metrics, and has been successfully deployed in real-world business contexts, proving its effectiveness for practical applications.

In the rise of climate change, land cover mapping has become such an urgent need in environmental monitoring. The accuracy of land cover classification has gotten increasingly based on the improvement of remote sensing data. Land cover classification using satellite imageries has been explored and become more prevalent in recent years, but the methodologies remain some drawbacks of subjective and time-consuming. Some deep learning techniques have been utilized to overcome these limitations. However, most studies implemented just one image type to evaluate algorithms for land cover mapping. Therefore, our study conducted deep learning semantic segmentation in multispectral, hyperspectral, and high spatial aerial image datasets for landcover mapping. This research implemented a semantic segmentation method such as Unet, Linknet, FPN, and PSPnet for categorizing vegetation, water, and others (i.e., soil and impervious surface). The LinkNet model obtained high accuracy in IoU (Intersection Over Union) at 0.92 in all datasets, which is comparable with other mentioned techniques. In evaluation with different image types, the multispectral images showed higher performance with the IoU, and F1-score are 0.993 and 0.997, respectively. Our outcome highlighted the efficiency and broad applicability of LinkNet and multispectral image on land cover classification. This research contributes to establishing an approach on landcover segmentation via open source for long-term future application., Comment: conference, This preprint is based on the following published conference article: Panuntun, I. A., Chen, Y.-N., Jamaluddin, I., & Tran, T. L. C., 2023. Evaluation of Deep Learning Semantic Segmentation for Land Cover Mapping on Multispectral, Hyperspectral and High Spatial Aerial Imagery. 44th Asian Conference on Remote Sensing, ACRS 2023. Code 198676

Towards open-ended Video Anomaly Detection (VAD), existing methods often exhibit biased detection when faced with challenging or unseen events and lack interpretability. To address these drawbacks, we propose Holmes-VAD, a novel framework that leverages precise temporal supervision and rich multimodal instructions to enable accurate anomaly localization and comprehensive explanations. Firstly, towards unbiased and explainable VAD system, we construct the first large-scale multimodal VAD instruction-tuning benchmark, i.e., VAD-Instruct50k. This dataset is created using a carefully designed semi-automatic labeling paradigm. Efficient single-frame annotations are applied to the collected untrimmed videos, which are then synthesized into high-quality analyses of both abnormal and normal video clips using a robust off-the-shelf video captioner and a large language model (LLM). Building upon the VAD-Instruct50k dataset, we develop a customized solution for interpretable video anomaly detection. We train a lightweight temporal sampler to select frames with high anomaly response and fine-tune a multimodal large language model (LLM) to generate explanatory content. Extensive experimental results validate the generality and interpretability of the proposed Holmes-VAD, establishing it as a novel interpretable technique for real-world video anomaly analysis. To support the community, our benchmark and model will be publicly available at https://holmesvad.github.io., Comment: 19 pages, 9 figures

Open-vocabulary semantic segmentation is a challenging task, which requires the model to output semantic masks of an image beyond a close-set vocabulary. Although many efforts have been made to utilize powerful CLIP models to accomplish this task, they are still easily overfitting to training classes due to the natural gaps in semantic information between training and new classes. To overcome this challenge, we propose a novel framework for openvocabulary semantic segmentation called EBSeg, incorporating an Adaptively Balanced Decoder (AdaB Decoder) and a Semantic Structure Consistency loss (SSC Loss). The AdaB Decoder is designed to generate different image embeddings for both training and new classes. Subsequently, these two types of embeddings are adaptively balanced to fully exploit their ability to recognize training classes and generalization ability for new classes. To learn a consistent semantic structure from CLIP, the SSC Loss aligns the inter-classes affinity in the image feature space with that in the text feature space of CLIP, thereby improving the generalization ability of our model. Furthermore, we employ a frozen SAM image encoder to complement the spatial information that CLIP features lack due to the low training image resolution and image-level supervision inherent in CLIP. Extensive experiments conducted across various benchmarks demonstrate that the proposed EBSeg outperforms the state-of-the-art methods. Our code and trained models will be here: https://github.com/slonetime/EBSeg., Comment: CVPR2024

Recent diffusion-based human image animation techniques have demonstrated impressive success in synthesizing videos that faithfully follow a given reference identity and a sequence of desired movement poses. Despite this, there are still two limitations: i) an extra reference model is required to align the identity image with the main video branch, which significantly increases the optimization burden and model parameters; ii) the generated video is usually short in time (e.g., 24 frames), hampering practical applications. To address these shortcomings, we present a UniAnimate framework to enable efficient and long-term human video generation. First, to reduce the optimization difficulty and ensure temporal coherence, we map the reference image along with the posture guidance and noise video into a common feature space by incorporating a unified video diffusion model. Second, we propose a unified noise input that supports random noised input as well as first frame conditioned input, which enhances the ability to generate long-term video. Finally, to further efficiently handle long sequences, we explore an alternative temporal modeling architecture based on state space model to replace the original computation-consuming temporal Transformer. Extensive experimental results indicate that UniAnimate achieves superior synthesis results over existing state-of-the-art counterparts in both quantitative and qualitative evaluations. Notably, UniAnimate can even generate highly consistent one-minute videos by iteratively employing the first frame conditioning strategy. Code and models will be publicly available. Project page: https://unianimate.github.io/., Comment: Project page: https://unianimate.github.io/