Unconditional video generation is a challenging task that involves synthesizing high-quality videos that are both coherent and of extended duration. To address this challenge, researchers have used pretrained StyleGAN image generators for high-quality frame synthesis and focused on motion generator design. The motion generator is trained in an autoregressive manner using heavy 3D convolutional discriminators to ensure motion coherence during video generation. In this paper, we introduce a novel motion generator design that uses a learning-based inversion network for GAN. The encoder in our method captures rich and smooth priors from encoding images to latents, and given the latent of an initially generated frame as guidance, our method can generate smooth future latent by modulating the inversion encoder temporally. Our method enjoys the advantage of sparse training and naturally constrains the generation space of our motion generator with the inversion network guided by the initial frame, eliminating the need for heavy discriminators. Moreover, our method supports style transfer with simple fine-tuning when the encoder is paired with a pretrained StyleGAN generator. Extensive experiments conducted on various benchmarks demonstrate the superiority of our method in generating long and high-resolution videos with decent single-frame quality and temporal consistency.
相關內容
Networking：IFIP International Conferences on Networking。
Explanation：國際網絡會(hui)議。
Publisher：IFIP。
SIT：
Multimedia content has become ubiquitous on social media platforms, leading to the rise of multimodal misinformation (MM) and the urgent need for effective strategies to detect and prevent its spread. In recent years, the challenge of multimodal misinformation detection (MMD) has garnered significant attention by researchers and has mainly involved the creation of annotated, weakly annotated, or synthetically generated training datasets, along with the development of various deep learning MMD models. However, the problem of unimodal bias has been overlooked, where specific patterns and biases in MMD benchmarks can result in biased or unimodal models outperforming their multimodal counterparts on an inherently multimodal task; making it difficult to assess progress. In this study, we systematically investigate and identify the presence of unimodal bias in widely-used MMD benchmarks, namely VMU-Twitter and COSMOS. To address this issue, we introduce the "VERification of Image-TExt pairs" (VERITE) benchmark for MMD which incorporates real-world data, excludes "asymmetric multimodal misinformation" and utilizes "modality balancing". We conduct an extensive comparative study with a Transformer-based architecture that shows the ability of VERITE to effectively address unimodal bias, rendering it a robust evaluation framework for MMD. Furthermore, we introduce a new method -- termed Crossmodal HArd Synthetic MisAlignment (CHASMA) -- for generating realistic synthetic training data that preserve crossmodal relations between legitimate images and false human-written captions. By leveraging CHASMA in the training process, we observe consistent and notable improvements in predictive performance on VERITE; with a 9.2% increase in accuracy. We release our code at: //github.com/stevejpapad/image-text-verification
Volumetric video has emerged as a prominent medium within the realm of eXtended Reality (XR) with the advancements in computer graphics and depth capture hardware. Users can fully immersive themselves in volumetric video with the ability to switch their viewport in six degree-of-freedom (DOF), including three rotational dimensions (yaw, pitch, roll) and three translational dimensions (X, Y, Z). Different from traditional 2D videos that are composed of pixel matrices, volumetric videos employ point clouds, meshes, or voxels to represent a volumetric scene, resulting in significantly larger data sizes. While previous works have successfully achieved volumetric video streaming in video-on-demand scenarios, the live streaming of volumetric video remains an unresolved challenge due to the limited network bandwidth and stringent latency constraints. In this paper, we for the first time propose a holistic live volumetric video streaming system, LiveVV, which achieves multi-view capture, scene segmentation \& reuse, adaptive transmission, and rendering. LiveVV contains multiple lightweight volumetric video capture modules that are capable of being deployed without prior preparation. To reduce bandwidth consumption, LiveVV processes static and dynamic volumetric content separately by reusing static data with low disparity and decimating data with low visual saliency. Besides, to deal with network fluctuation, LiveVV integrates a volumetric video adaptive bitrate streaming algorithm (VABR) to enable fluent playback with the maximum quality of experience. Extensive real-world experiment shows that LiveVV can achieve live volumetric video streaming at a frame rate of 24 fps with a latency of less than 350ms.
The dramatic increase in the use of social media platforms for information sharing has also fueled a steep growth in online abuse. A simple yet effective way of abusing individuals or communities is by creating memes, which often integrate an image with a short piece of text layered on top of it. Such harmful elements are in rampant use and are a threat to online safety. Hence it is necessary to develop efficient models to detect and flag abusive memes. The problem becomes more challenging in a low-resource setting (e.g., Bengali memes, i.e., images with Bengali text embedded on it) because of the absence of benchmark datasets on which AI models could be trained. In this paper we bridge this gap by building a Bengali meme dataset. To setup an effective benchmark we implement several baseline models for classifying abusive memes using this dataset. We observe that multimodal models that use both textual and visual information outperform unimodal models. Our best-performing model achieves a macro F1 score of 70.51. Finally, we perform a qualitative error analysis of the misclassified memes of the best-performing text-based, image-based and multimodal models.
Over the past few years, the explosion in sparse tensor algebra workloads has led to a corresponding rise in domain-specific accelerators to service them. Due to the irregularity present in sparse tensors, these accelerators employ a wide variety of novel solutions to achieve good performance. At the same time, prior work on design-flexible sparse accelerator modeling does not express this full range of design features, making it difficult to understand the impact of each design choice and compare or extend the state-of-the-art. To address this, we propose TeAAL: a language and simulator generator for the concise and precise specification and evaluation of sparse tensor algebra accelerators. We use TeAAL to represent and evaluate four disparate state-of-the-art accelerators -- ExTensor, Gamma, OuterSPACE, and SIGMA -- and verify that it reproduces their performance with high accuracy. Finally, we demonstrate the potential of TeAAL as a tool for designing new accelerators by showing how it can be used to speed up vertex-centric programming accelerators -- achieving $1.9\times$ on BFS and $1.2\times$ on SSSP over GraphDynS.
Despite remarkable research advances in diffusion-based video editing, existing methods are limited to short-length videos due to the contradiction between long-range consistency and frame-wise editing. Recent approaches attempt to tackle this challenge by introducing video-2D representations to degrade video editing to image editing. However, they encounter significant difficulties in handling large-scale motion- and view-change videos especially for human-centric videos. This motivates us to introduce the dynamic Neural Radiance Fields (NeRF) as the human-centric video representation to ease the video editing problem to a 3D space editing task. As such, editing can be performed in the 3D spaces and propagated to the entire video via the deformation field. To provide finer and direct controllable editing, we propose the image-based 3D space editing pipeline with a set of effective designs. These include multi-view multi-pose Score Distillation Sampling (SDS) from both 2D personalized diffusion priors and 3D diffusion priors, reconstruction losses on the reference image, text-guided local parts super-resolution, and style transfer for 3D background space. Extensive experiments demonstrate that our method, dubbed as DynVideo-E, significantly outperforms SOTA approaches on two challenging datasets by a large margin of 50% ~ 95% in terms of human preference. Compelling video comparisons are provided in the project page //showlab.github.io/DynVideo-E/. Our code and data will be released to the community.
Building models that generate textual responses to user instructions for videos is a practical and challenging topic, as it requires both vision understanding and knowledge reasoning. Compared to language and image modalities, training efficiency remains a serious problem as existing studies train models on massive sparse videos aligned with brief descriptions. In this paper, we introduce BiLL-VTG, a fast adaptive framework that leverages large language models (LLMs) to reasoning on videos based on essential lightweight visual tools. Specifically, we reveal the key to response specific instructions is the concentration on relevant video events, and utilize two visual tools of structured scene graph generation and descriptive image caption generation to gather and represent the events information. Thus, a LLM equipped with world knowledge is adopted as the reasoning agent to achieve the response by performing multiple reasoning steps on specified video events.To address the difficulty of specifying events from agent, we further propose an Instruction-oriented Video Events Recognition (InsOVER) algorithm based on the efficient Hungarian matching to localize corresponding video events using linguistic instructions, enabling LLMs to interact with long videos. Extensive experiments on two typical video-based texts generations tasks show that our tuning-free framework outperforms the pre-trained models including Flamingo-80B, to achieve the state-of-the-art performance.
The increasing popularity of exercises including yoga and Pilates has created a greater demand for professional exercise video datasets in the realm of artificial intelligence. In this study, we developed 3DYoga901, which is organized within a three-level label hierarchy. We have expanded the number of poses from an existing state-of-the-art dataset, increasing it from 82 to 90 poses. Our dataset includes meticulously curated RGB yoga pose videos and 3D skeleton sequences. This dataset was created by a dedicated team of six individuals, including yoga instructors. It stands out as one of the most comprehensive open datasets, featuring the largest collection of RGB videos and 3D skeleton sequences among publicly available resources. This contribution has the potential to significantly advance the field of yoga action recognition and pose assessment. Additionally, we conducted experiments to evaluate the practicality of our proposed dataset. We employed three different model variants for benchmarking purposes.
Although supervised image denoising networks have shown remarkable performance on synthesized noisy images, they often fail in practice due to the difference between real and synthesized noise. Since clean-noisy image pairs from the real world are extremely costly to gather, self-supervised learning, which utilizes noisy input itself as a target, has been studied. To prevent a self-supervised denoising model from learning identical mapping, each output pixel should not be influenced by its corresponding input pixel; This requirement is known as J-invariance. Blind-spot networks (BSNs) have been a prevalent choice to ensure J-invariance in self-supervised image denoising. However, constructing variations of BSNs by injecting additional operations such as downsampling can expose blinded information, thereby violating J-invariance. Consequently, convolutions designed specifically for BSNs have been allowed only, limiting architectural flexibility. To overcome this limitation, we propose PUCA, a novel J-invariant U-Net architecture, for self-supervised denoising. PUCA leverages patch-unshuffle/shuffle to dramatically expand receptive fields while maintaining J-invariance and dilated attention blocks (DABs) for global context incorporation. Experimental results demonstrate that PUCA achieves state-of-the-art performance, outperforming existing methods in self-supervised image denoising.
Anomaly detection in multivariate time series has emerged as a crucial challenge in time series research, with significant research implications in various fields such as fraud detection, fault diagnosis, and system state estimation. Reconstruction-based models have shown promising potential in recent years for detecting anomalies in time series data. However, due to the rapid increase in data scale and dimensionality, the issues of noise and Weak Identity Mapping (WIM) during time series reconstruction have become increasingly pronounced. To address this, we introduce a novel Adaptive Dynamic Neighbor Mask (ADNM) mechanism and integrate it with the Transformer and Denoising Diffusion Model, creating a new framework for multivariate time series anomaly detection, named Denoising Diffusion Mask Transformer (DDMT). The ADNM module is introduced to mitigate information leakage between input and output features during data reconstruction, thereby alleviating the problem of WIM during reconstruction. The Denoising Diffusion Transformer (DDT) employs the Transformer as an internal neural network structure for Denoising Diffusion Model. It learns the stepwise generation process of time series data to model the probability distribution of the data, capturing normal data patterns and progressively restoring time series data by removing noise, resulting in a clear recovery of anomalies. To the best of our knowledge, this is the first model that combines Denoising Diffusion Model and the Transformer for multivariate time series anomaly detection. Experimental evaluations were conducted on five publicly available multivariate time series anomaly detection datasets. The results demonstrate that the model effectively identifies anomalies in time series data, achieving state-of-the-art performance in anomaly detection.
Answering complex questions about images is an ambitious goal for machine intelligence, which requires a joint understanding of images, text, and commonsense knowledge, as well as a strong reasoning ability. Recently, multimodal Transformers have made great progress in the task of Visual Commonsense Reasoning (VCR), by jointly understanding visual objects and text tokens through layers of cross-modality attention. However, these approaches do not utilize the rich structure of the scene and the interactions between objects which are essential in answering complex commonsense questions. We propose a Scene Graph Enhanced Image-Text Learning (SGEITL) framework to incorporate visual scene graphs in commonsense reasoning. To exploit the scene graph structure, at the model structure level, we propose a multihop graph transformer for regularizing attention interaction among hops. As for pre-training, a scene-graph-aware pre-training method is proposed to leverage structure knowledge extracted in the visual scene graph. Moreover, we introduce a method to train and generate domain-relevant visual scene graphs using textual annotations in a weakly-supervised manner. Extensive experiments on VCR and other tasks show a significant performance boost compared with the state-of-the-art methods and prove the efficacy of each proposed component.
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