With advances in optical sensor technology, heterogeneous camera systems are increasingly used for high-resolution (HR) video acquisition and analysis. However, motion transfer across multiple cameras poses challenges. To address this, we propose a algorithm based on time series analysis that identifies motion seasonality and constructs an additive model to extract transferable patterns. Validated on real-world data, our algorithm demonstrates effectiveness and interpretability. Notably, it improves pose estimation in low-resolution videos by leveraging patterns derived from HR counterparts, enhancing practical utility. Code is available at: //github.com/IndigoPurple/TSAMT
相關內容
Large foundation models are becoming ubiquitous, but training them from scratch is prohibitively expensive. Thus, efficiently adapting these powerful models to downstream tasks is increasingly important. In this paper, we study a principled finetuning paradigm -- Orthogonal Finetuning (OFT) -- for downstream task adaptation. Despite demonstrating good generalizability, OFT still uses a fairly large number of trainable parameters due to the high dimensionality of orthogonal matrices. To address this, we start by examining OFT from an information transmission perspective, and then identify a few key desiderata that enable better parameter-efficiency. Inspired by how the Cooley-Tukey fast Fourier transform algorithm enables efficient information transmission, we propose an efficient orthogonal parameterization using butterfly structures. We apply this parameterization to OFT, creating a novel parameter-efficient finetuning method, called Orthogonal Butterfly (BOFT). By subsuming OFT as a special case, BOFT introduces a generalized orthogonal finetuning framework. Finally, we conduct an extensive empirical study of adapting large vision transformers, large language models, and text-to-image diffusion models to various downstream tasks in vision and language.
Subjective assessment tests are often employed to evaluate image processing systems, notably image and video compression, super-resolution among others and have been used as an indisputable way to provide evidence of the performance of an algorithm or system. While several methodologies can be used in a subjective quality assessment test, pairwise comparison tests are nowadays attracting a lot of attention due to their accuracy and simplicity. However, the number of comparisons in a pairwise comparison test increases quadratically with the number of stimuli and thus often leads to very long tests, which is impractical for many cases. However, not all the pairs contribute equally to the final score and thus, it is possible to reduce the number of comparisons without degrading the final accuracy. To do so, pairwise sampling methods are often used to select the pairs which provide more information about the quality of each stimuli. In this paper, a reliable and much-needed evaluation procedure is proposed and used for already available methods in the literature, especially considering the case of subjective evaluation of image and video codecs. The results indicate that an appropriate selection of the pairs allows to achieve very reliable scores while requiring the comparison of a much lower number of pairs.
Virtual reality (VR) renderers driving CAVEs and similar immersive environments use the off-axis stereo camera model so that a tracked user can move freely in front of the projection plane. Geometrically, off-axis projection results in asymmetric viewing frusta and generalizes the ubiquitous perspective camera model to support positioning off the center of the projection plane. VR renderers often integrate with larger visualization systems that rely on libraries for position tracking and pose estimates, for ray tracing-based rendering, and for user interaction. We demonstrate different strategies to implement off-axis stereo projection within the constraints of given VR applications and ray tracing libraries. We aim for minimal to no adjustments required to the internal camera representation of such libraries. We include host and shader code with the article that can be directly integrated in custom applications.
Matching a source to a target probability measure is often solved by instantiating a linear optimal transport (OT) problem, parameterized by a ground cost function that quantifies discrepancy between points. When these measures live in the same metric space, the ground cost often defaults to its distance. When instantiated across two different spaces, however, choosing that cost in the absence of aligned data is a conundrum. As a result, practitioners often resort to solving instead a quadratic Gromow-Wasserstein (GW) problem. We exploit in this work a parallel between GW and cost-regularized OT, the regularized minimization of a linear OT objective parameterized by a ground cost. We use this cost-regularized formulation to match measures across two different Euclidean spaces, where the cost is evaluated between transformed source points and target points. We show that several quadratic OT problems fall in this category, and consider enforcing structure in linear transform (e.g. sparsity), by introducing structure-inducing regularizers. We provide a proximal algorithm to extract such transforms from unaligned data, and demonstrate its applicability to single-cell spatial transcriptomics/multiomics matching tasks.
We introduce an improved solution to the neural image-based rendering problem in computer vision. Given a set of images taken from a freely moving camera at train time, the proposed approach could synthesize a realistic image of the scene from a novel viewpoint at test time. The key ideas presented in this paper are (i) Recovering accurate camera parameters via a robust pipeline from unposed day-to-day images is equally crucial in neural novel view synthesis problem; (ii) It is rather more practical to model object's content at different resolutions since dramatic camera motion is highly likely in day-to-day unposed images. To incorporate the key ideas, we leverage the fundamentals of scene rigidity, multi-scale neural scene representation, and single-image depth prediction. Concretely, the proposed approach makes the camera parameters as learnable in a neural fields-based modeling framework. By assuming per view depth prediction is given up to scale, we constrain the relative pose between successive frames. From the relative poses, absolute camera pose estimation is modeled via a graph-neural network-based multiple motion averaging within the multi-scale neural-fields network, leading to a single loss function. Optimizing the introduced loss function provides camera intrinsic, extrinsic, and image rendering from unposed images. We demonstrate, with examples, that for a unified framework to accurately model multiscale neural scene representation from day-to-day acquired unposed multi-view images, it is equally essential to have precise camera-pose estimates within the scene representation framework. Without considering robustness measures in the camera pose estimation pipeline, modeling for multi-scale aliasing artifacts can be counterproductive. We present extensive experiments on several benchmark datasets to demonstrate the suitability of our approach.
We present a large-scale study on unsupervised spatiotemporal representation learning from videos. With a unified perspective on four recent image-based frameworks, we study a simple objective that can easily generalize all these methods to space-time. Our objective encourages temporally-persistent features in the same video, and in spite of its simplicity, it works surprisingly well across: (i) different unsupervised frameworks, (ii) pre-training datasets, (iii) downstream datasets, and (iv) backbone architectures. We draw a series of intriguing observations from this study, e.g., we discover that encouraging long-spanned persistency can be effective even if the timespan is 60 seconds. In addition to state-of-the-art results in multiple benchmarks, we report a few promising cases in which unsupervised pre-training can outperform its supervised counterpart. Code is made available at //github.com/facebookresearch/SlowFast
The rapid advancements in machine learning, graphics processing technologies and availability of medical imaging data has led to a rapid increase in use of machine learning models in the medical domain. This was exacerbated by the rapid advancements in convolutional neural network (CNN) based architectures, which were adopted by the medical imaging community to assist clinicians in disease diagnosis. Since the grand success of AlexNet in 2012, CNNs have been increasingly used in medical image analysis to improve the efficiency of human clinicians. In recent years, three-dimensional (3D) CNNs have been employed for analysis of medical images. In this paper, we trace the history of how the 3D CNN was developed from its machine learning roots, brief mathematical description of 3D CNN and the preprocessing steps required for medical images before feeding them to 3D CNNs. We review the significant research in the field of 3D medical imaging analysis using 3D CNNs (and its variants) in different medical areas such as classification, segmentation, detection, and localization. We conclude by discussing the challenges associated with the use of 3D CNNs in the medical imaging domain (and the use of deep learning models, in general) and possible future trends in the field.
Video captioning is a challenging task that requires a deep understanding of visual scenes. State-of-the-art methods generate captions using either scene-level or object-level information but without explicitly modeling object interactions. Thus, they often fail to make visually grounded predictions, and are sensitive to spurious correlations. In this paper, we propose a novel spatio-temporal graph model for video captioning that exploits object interactions in space and time. Our model builds interpretable links and is able to provide explicit visual grounding. To avoid unstable performance caused by the variable number of objects, we further propose an object-aware knowledge distillation mechanism, in which local object information is used to regularize global scene features. We demonstrate the efficacy of our approach through extensive experiments on two benchmarks, showing our approach yields competitive performance with interpretable predictions.
The low resolution of objects of interest in aerial images makes pedestrian detection and action detection extremely challenging tasks. Furthermore, using deep convolutional neural networks to process large images can be demanding in terms of computational requirements. In order to alleviate these challenges, we propose a two-step, yes and no question answering framework to find specific individuals doing one or multiple specific actions in aerial images. First, a deep object detector, Single Shot Multibox Detector (SSD), is used to generate object proposals from small aerial images. Second, another deep network, is used to learn a latent common sub-space which associates the high resolution aerial imagery and the pedestrian action labels that are provided by the human-based sources
Recent advancements in deep neural networks for graph-structured data have led to state-of-the-art performance on recommender system benchmarks. However, making these methods practical and scalable to web-scale recommendation tasks with billions of items and hundreds of millions of users remains a challenge. Here we describe a large-scale deep recommendation engine that we developed and deployed at Pinterest. We develop a data-efficient Graph Convolutional Network (GCN) algorithm PinSage, which combines efficient random walks and graph convolutions to generate embeddings of nodes (i.e., items) that incorporate both graph structure as well as node feature information. Compared to prior GCN approaches, we develop a novel method based on highly efficient random walks to structure the convolutions and design a novel training strategy that relies on harder-and-harder training examples to improve robustness and convergence of the model. We also develop an efficient MapReduce model inference algorithm to generate embeddings using a trained model. We deploy PinSage at Pinterest and train it on 7.5 billion examples on a graph with 3 billion nodes representing pins and boards, and 18 billion edges. According to offline metrics, user studies and A/B tests, PinSage generates higher-quality recommendations than comparable deep learning and graph-based alternatives. To our knowledge, this is the largest application of deep graph embeddings to date and paves the way for a new generation of web-scale recommender systems based on graph convolutional architectures.
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