Current large multimodal models (LMMs) face significant challenges in processing and comprehending long-duration or high-resolution videos, which is mainly due to the lack of high-quality datasets. To address this issue from a Average Accuracy data-centric perspective, we propose VISTA, a simple yet effective VIdeo SpatioTemporal Augmentation framework that synthesizes long-duration and high-resolution video instruction-following pairs from existing video-caption datasets. VISTA spatially and temporally combines videos to create new synthetic videos with extended durations and enhanced resolutions, and subsequently produces question-answer pairs pertaining to these newly synthesized videos. Based on this paradigm, we develop seven video augmentation methods and curate VISTA-400K, a video instruction-following dataset aimed at enhancing long-duration and high-resolution video understanding. Finetuning various video LMMs on our data resulted in an average improvement of 3.3% across four challenging benchmarks for long-video understanding. Furthermore, we introduce the first comprehensive high-resolution video understanding benchmark HRVideoBench, on which our finetuned models achieve a 6.5% performance gain. These results highlight the effectiveness of our framework.

The success of image generative models has enabled us to build methods that can edit images based on text or other user input. However, these methods are imprecise, require additional information, or are limited to only 2D image edits. We present GeoDiffuser, a zero-shot optimization-based method that unifies common 2D and 3D image-based object editing capabilities into a single method. Our key insight is to view image editing operations as geometric transformations. We show that these transformations can be directly incorporated into the attention layers in diffusion models to implicitly perform editing operations. Our training-free optimization method uses an objective function that seeks to preserve object style but generate plausible images, for instance with accurate lighting and shadows. It also inpaints disoccluded parts of the image where the object was originally located. Given a natural image and user input, we segment the foreground object [27] and estimate a corresponding transform which is used by our optimization approach for editing. Figure 1 shows that GeoDiffuser can perform common 2D and 3D edits like object translation, 3D rotation, and removal. We present quantitative results, including a perceptual study, that shows how our approach is better than existing methods.

Unmanned aerial vehicle (UAV)-aided large-scale Internet of Things (UAV-LIoT) are widely used but lack a balanced data collection (DC) scheme. To address this, we propose DC- nonorthogonal multiple access (NOMA), a new DC scheme that combines machine learning clustering with NOMA. We introduce an optimization algorithm for peak density clustering and a new LIoT clustering method. Our approach dynamically adjusts cluster size and formulates the energy-time efficiency problem as a tradeoff between energy minimization and data rate maximization. We propose a heuristic algorithm based on NOMA and an intracluster DC protocol. Experimental results show that DC- NOMA achieves balanced DC time, energy efficiency, load balance, and network lifespan extension, outperforming its benchmarks.

This paper reports on an experimental study that examined user perceptions of Amazon Alexa's personality, as well as influences of stressful or non-stressful interactions on personality perceptions. The study relied on the Five-Factor Model and the Stereotype Content Model personality frameworks. An online data collection instrument was designed to give Alexa's users (N=50) stressful and non-stressful tasks followed by questions related to Alexa's personality. The assumption was that stressful and non-stressful tasks would frame a user's preference for Alexa's personality. Quantitative data of the participants? ratings of Alexa's responses, and qualitative comments about their ratings, experiences, and thoughts about Alexa were collected and analyzed using descriptive statistics, tests of association, and thematic content analysis. The findings indicated that while the majority of users appreciate Alexa's personality as a way of making interactions more personal and enjoyable, some users prefer their conversational agent to be efficient, robotic-like, and devoid of a personality that might cause attachment. The participants described Alexa as competent in terms of information content and usability, and warm in terms of its personality manifestation, but wanted their ideal Alexa to be even more competent and warm. After experiencing stressful and non-stressful experimental conditions, the participants appreciated Alexa's highly competent and highly warm responses, while disparaging low-warmth/high-competence responses. The participants' comments indicated that after stressful tasks, they were more generous in their assessment of Alexa's performance, and valued manifestations of Alexa's warmth higher than after non-stressful tasks. Additionally, after the second group of tasks/towards the end of the study, the participants tended to score low warmth/high competence responses higher, which might indicate a slight preference for competence after longer interactions or a user's fatigued state. The implications of the findings on the design of conversational interfaces and study limitations are discussed.

With the emergence of the fog computing and the sensor-cloud computing paradigms, end users can retrieve the desired sensory data generated by any wireless sensor network (WSN) in a fog-based sensor-cloud system transparently. However, the fog nodes and the cloud servers may suffer from many kinds of attacks on the Internet and become semitrusted, which threatens the security of query processing in the system. In this paper, we investigated the problem of secure, fine-grained spatial-temporal Top- k query in fog-based mobile sensor-cloud systems (FMSCSs) and proposed a novel scheme named STQ-SCS to tackle the problem based on the virtual grid construction and the size-order encryption-binding techniques. STQ-SCS can preserve the privacy of the sensed data items and their scores and make end users verify the completeness of the query results of fine-grained spatial-temporal Top- k queries with a 100% successful rate even if the fog nodes and the cloud servers are not totally trustworthy. Besides the good security performance, simulation results indicate that STQ-SCS is also an efficient scheme that incurs a much lower communication cost than the state-of-the-art schemes on securing fine-grained spatial-temporal Top- k query in FMSCSs.

We propose an image synthesis approach that provides stratified navigation in the latent code space. With a tiny amount of partial or very low-resolution image, our approach can consistently out-perform state-of-the-art counterparts in terms of generating the closest sampled image to the ground truth. We achieve this through scale-independent editing while expanding scale-specific diversity. Scale-independence is achieved with a nested scale disentanglement loss. Scale-specific diversity is created by incorporating a progressive diversification constraint. We introduce semantic persistency across the scales by sharing common latent codes. Together they provide better control of the image synthesis process. We evaluate the effectiveness of our proposed approach through various tasks, including image outpainting, image superresolution, and cross-domain image translation.

We tackle the human motion imitation, appearance transfer, and novel view synthesis within a unified framework, which means that the model once being trained can be used to handle all these tasks. The existing task-specific methods mainly use 2D keypoints (pose) to estimate the human body structure. However, they only expresses the position information with no abilities to characterize the personalized shape of the individual person and model the limbs rotations. In this paper, we propose to use a 3D body mesh recovery module to disentangle the pose and shape, which can not only model the joint location and rotation but also characterize the personalized body shape. To preserve the source information, such as texture, style, color, and face identity, we propose a Liquid Warping GAN with Liquid Warping Block (LWB) that propagates the source information in both image and feature spaces, and synthesizes an image with respect to the reference. Specifically, the source features are extracted by a denoising convolutional auto-encoder for characterizing the source identity well. Furthermore, our proposed method is able to support a more flexible warping from multiple sources. In addition, we build a new dataset, namely Impersonator (iPER) dataset, for the evaluation of human motion imitation, appearance transfer, and novel view synthesis. Extensive experiments demonstrate the effectiveness of our method in several aspects, such as robustness in occlusion case and preserving face identity, shape consistency and clothes details. All codes and datasets are available on https://svip-lab.github.io/project/impersonator.html.