As users conveniently stream their favored online videos, video request records will be automatically seized by video content providers, which may leak users' privacy. Unfortunately, most existing privacy-enhancing approaches are not applicable for protecting users' privacy in requests, which cannot be easily altered or distorted by users and must be visible for content providers to stream correct videos. To preserve request privacy in online video services, it is possible to request additional videos irrelevant to users' interests so that content providers cannot precisely infer users' interest information. However, a naive redundant requesting approach will significantly degrade the performance of edge caches and increase bandwidth overhead accordingly. In this paper, we are among the first to propose a Cache-Friendly Redundant Video Requesting (cRVR) algorithm for User Devices (UDs) and its corresponding caching algorithm for the Edge Cache (EC), which can effectively mitigate the problem of request privacy leakage with minimal impact on the EC's performance. To solve the problem, we develop a Stackelberg game to analyze the dedicated interaction between UDs and EC and obtain their optimal strategies to maximize their respective utility. For UDs, the utility function is a combination of both video playback utility and privacy protection utility. We theoretically prove the existence and uniqueness of the equilibrium of the Stackelberg game. In the end, extensive experiments are conducted with real traces to demonstrate that cRVR can effectively protect video request privacy by reducing up to 57.96\% of privacy disclosure compared to baseline algorithms. Meanwhile, the caching performance of ECs is only slightly affected.
相關內容
Motions in a video primarily consist of camera motion, induced by camera movement, and object motion, resulting from object movement. Accurate control of both camera and object motion is essential for video generation. However, existing works either mainly focus on one type of motion or do not clearly distinguish between the two, limiting their control capabilities and diversity. Therefore, this paper presents MotionCtrl, a unified and flexible motion controller for video generation designed to effectively and independently control camera and object motion. The architecture and training strategy of MotionCtrl are carefully devised, taking into account the inherent properties of camera motion, object motion, and imperfect training data. Compared to previous methods, MotionCtrl offers three main advantages: 1) It effectively and independently controls camera motion and object motion, enabling more fine-grained motion control and facilitating flexible and diverse combinations of both types of motion. 2) Its motion conditions are determined by camera poses and trajectories, which are appearance-free and minimally impact the appearance or shape of objects in generated videos. 3) It is a relatively generalizable model that can adapt to a wide array of camera poses and trajectories once trained. Extensive qualitative and quantitative experiments have been conducted to demonstrate the superiority of MotionCtrl over existing methods.
Achieving high-quality versatile image inpainting, where user-specified regions are filled with plausible content according to user intent, presents a significant challenge. Existing methods face difficulties in simultaneously addressing context-aware image inpainting and text-guided object inpainting due to the distinct optimal training strategies required. To overcome this challenge, we introduce PowerPaint, the first high-quality and versatile inpainting model that excels in both tasks. First, we introduce learnable task prompts along with tailored fine-tuning strategies to guide the model's focus on different inpainting targets explicitly. This enables PowerPaint to accomplish various inpainting tasks by utilizing different task prompts, resulting in state-of-the-art performance. Second, we demonstrate the versatility of the task prompt in PowerPaint by showcasing its effectiveness as a negative prompt for object removal. Additionally, we leverage prompt interpolation techniques to enable controllable shape-guided object inpainting. Finally, we extensively evaluate PowerPaint on various inpainting benchmarks to demonstrate its superior performance for versatile image inpainting. We release our codes and models on our project page: //powerpaint.github.io/.
Deploying unmanned aerial vehicle (UAV) networks to provide coverage for outdoor users has attracted great attention during the last decade. However, outdoor coverage is challenging due to the high mobility of crowds and the diverse terrain configurations causing building blockage. Most studies use stochastic channel models to characterize the impact of building blockage on user performance and do not take into account terrain information. On the other hand, real-time search methods use terrain information, but they are only practical when a single UAV serves a single user.In this paper, we put forward two methods to avoid building blockage in a multi-user system by collecting prior terrain information and using real-time search.We proposed four algorithms related to the combinations of the above methods and their performances are evaluated and compared in different scenarios.By adjusting the height of the UAV based on terrain information collected before networking, the performance is significantly enhanced compared to the one when no terrain information is available.The algorithm based on real-time search further improves the coverage performance by avoiding the shadow of buildings. During the execution of the real-time search algorithm, the search distance is reduced using the collected terrain information.
Image Retrieval aims to retrieve corresponding images based on a given query. In application scenarios, users intend to express their retrieval intent through various query styles. However, current retrieval tasks predominantly focus on text-query retrieval exploration, leading to limited retrieval query options and potential ambiguity or bias in user intention. In this paper, we propose the Style-Diversified Query-Based Image Retrieval task, which enables retrieval based on various query styles. To facilitate the novel setting, we propose the first Diverse-Style Retrieval dataset, encompassing diverse query styles including text, sketch, low-resolution, and art. We also propose a light-weighted style-diversified retrieval framework. For various query style inputs, we apply the Gram Matrix to extract the query's textural features and cluster them into a style space with style-specific bases. Then we employ the style-init prompt tuning module to enable the visual encoder to comprehend the texture and style information of the query. Experiments demonstrate that our model, employing the style-init prompt tuning strategy, outperforms existing retrieval models on the style-diversified retrieval task. Moreover, style-diversified queries~(sketch+text, art+text, etc) can be simultaneously retrieved in our model. The auxiliary information from other queries enhances the retrieval performance within the respective query.
Video dubbing aims to translate the original speech in a film or television program into the speech in a target language, which can be achieved with a cascaded system consisting of speech recognition, machine translation and speech synthesis. To ensure the translated speech to be well aligned with the corresponding video, the length/duration of the translated speech should be as close as possible to that of the original speech, which requires strict length control. Previous works usually control the number of words or characters generated by the machine translation model to be similar to the source sentence, without considering the isochronicity of speech as the speech duration of words/characters in different languages varies. In this paper, we propose a machine translation system tailored for the task of video dubbing, which directly considers the speech duration of each token in translation, to match the length of source and target speech. Specifically, we control the speech length of generated sentence by guiding the prediction of each word with the duration information, including the speech duration of itself as well as how much duration is left for the remaining words. We design experiments on four language directions (German -> English, Spanish -> English, Chinese <-> English), and the results show that the proposed method achieves better length control ability on the generated speech than baseline methods. To make up the lack of real-world datasets, we also construct a real-world test set collected from films to provide comprehensive evaluations on the video dubbing task.
Recent advancements in language-model-based video understanding have been progressing at a remarkable pace, spurred by the introduction of Large Language Models (LLMs). However, the focus of prior research has been predominantly on devising a projection layer that maps video features to tokens, an approach that is both rudimentary and inefficient. In our study, we introduce a cutting-edge framework, VaQuitA, designed to refine the synergy between video and textual information. At the data level, instead of sampling frames uniformly, we implement a sampling method guided by CLIP-score rankings, which enables a more aligned selection of frames with the given question. At the feature level, we integrate a trainable Video Perceiver alongside a Visual-Query Transformer (abbreviated as VQ-Former), which bolsters the interplay between the input question and the video features. We also discover that incorporating a simple prompt, "Please be critical", into the LLM input can substantially enhance its video comprehension capabilities. Our experimental results indicate that VaQuitA consistently sets a new benchmark for zero-shot video question-answering tasks and is adept at producing high-quality, multi-turn video dialogues with users.
This work proposes TimeChat, a time-sensitive multimodal large language model specifically designed for long video understanding. Our model incorporates two key architectural contributions: (1) a timestamp-aware frame encoder that binds visual content with the timestamp of each frame, and (2) a sliding video Q-Former that produces a video token sequence of varying lengths to accommodate videos of various durations. Additionally, we construct an instruction-tuning dataset, encompassing 6 tasks and a total of 125K instances, to further enhance TimeChat's instruction-following performance. Experiment results across various video understanding tasks, such as dense captioning, temporal grounding, and highlight detection, demonstrate TimeChat's strong zero-shot temporal localization and reasoning capabilities. For example, it achieves +9.2 F1 score and +2.8 CIDEr on YouCook2, +5.8 HIT@1 on QVHighlights, and +27.5 R@1 (IoU=0.5) on Charades-STA, compared to state-of-the-art video large language models, holding the potential to serve as a versatile video assistant for long-form video comprehension tasks and satisfy realistic user requirements.
Surveillance videos are an essential component of daily life with various critical applications, particularly in public security. However, current surveillance video tasks mainly focus on classifying and localizing anomalous events. Existing methods are limited to detecting and classifying the predefined events with unsatisfactory semantic understanding, although they have obtained considerable performance. To address this issue, we propose a new research direction of surveillance video-and-language understanding, and construct the first multimodal surveillance video dataset. We manually annotate the real-world surveillance dataset UCF-Crime with fine-grained event content and timing. Our newly annotated dataset, UCA (UCF-Crime Annotation), contains 23,542 sentences, with an average length of 20 words, and its annotated videos are as long as 110.7 hours. Furthermore, we benchmark SOTA models for four multimodal tasks on this newly created dataset, which serve as new baselines for surveillance video-and-language understanding. Through our experiments, we find that mainstream models used in previously publicly available datasets perform poorly on surveillance video, which demonstrates the new challenges in surveillance video-and-language understanding. To validate the effectiveness of our UCA, we conducted experiments on multimodal anomaly detection. The results demonstrate that our multimodal surveillance learning can improve the performance of conventional anomaly detection tasks. All the experiments highlight the necessity of constructing this dataset to advance surveillance AI. The link to our dataset is provided at: //xuange923.github.io/Surveillance-Video-Understanding.
Traditional 3D content creation tools empower users to bring their imagination to life by giving them direct control over a scene's geometry, appearance, motion, and camera path. Creating computer-generated videos, however, is a tedious manual process, which can be automated by emerging text-to-video diffusion models. Despite great promise, video diffusion models are difficult to control, hindering a user to apply their own creativity rather than amplifying it. To address this challenge, we present a novel approach that combines the controllability of dynamic 3D meshes with the expressivity and editability of emerging diffusion models. For this purpose, our approach takes an animated, low-fidelity rendered mesh as input and injects the ground truth correspondence information obtained from the dynamic mesh into various stages of a pre-trained text-to-image generation model to output high-quality and temporally consistent frames. We demonstrate our approach on various examples where motion can be obtained by animating rigged assets or changing the camera path.
Detecting malicious URLs is a crucial aspect of web search and mining, significantly impacting internet security. Though advancements in machine learning have improved the effectiveness of detection methods, these methods still face significant challenges in their capacity to generalize and their resilience against evolving threats. In this paper, we propose PyraTrans, an approach that combines the strengths of pretrained Transformers and pyramid feature learning for improving malicious URL detection. We implement PyraTrans by leveraging a pretrained CharBERT as the base and augmenting it with 3 connected feature modules: 1) The Encoder Feature Extraction module, which extracts representations from each encoder layer of CharBERT to obtain multi-order features; 2) The Multi-Scale Feature Learning Module, which captures multi-scale local contextual insights and aggregate information across different layer-levels; and 3) The Pyramid Spatial Attention Module, which learns hierarchical and spatial feature attentions, highlighting critical classification signals while reducing noise. The proposed approach addresses the limitations of the Transformer in local feature learning and spatial awareness, and enabling us to extract multi-order, multi-scale URL feature representations with enhanced attentional focus. PyraTrans is evaluated using 4 benchmark datasets, where it demonstrated significant advancements over prior baseline methods. Particularly, on the imbalanced dataset, our method, with just 10% of the data for training, the TPR is 3.3-6.5 times and the F1-score is 2.9-4.5 times that of the baseline. Our approach also demonstrates robustness against adversarial attacks. Codes and data are available at //github.com/Alixyvtte/PyraTrans.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191