This paper presents a real-time segmentation and reconstruction system that utilizes RGB-D images to generate accurate and detailed individual 3D models of objects within a captured scene. Leveraging state-of-the-art instance segmentation techniques, the system performs pixel-level segmentation on RGB-D data, effectively separating foreground objects from the background. The segmented objects are then reconstructed into distinct 3D models in a high-performance computation platform. The real-time 3D modelling can be applied across various domains, including augmented/virtual reality, interior design, urban planning, road assistance, security systems, and more. To achieve real-time performance, the paper proposes a method that effectively samples consecutive frames to reduce network load while ensuring reconstruction quality. Additionally, a multi-process SLAM pipeline is adopted for parallel 3D reconstruction, enabling efficient cutting of the clustering objects into individuals. This system employs the industry-leading framework YOLO for instance segmentation. To improve YOLO's performance and accuracy, modifications were made to resolve duplicated or false detection of similar objects, ensuring the reconstructed models align with the targets. Overall, this work establishes a robust real-time system with a significant enhancement for object segmentation and reconstruction in the indoor environment. It can potentially be extended to the outdoor scenario, opening up numerous opportunities for real-world applications.
We study Merton's expected utility maximization problem in an incomplete market, characterized by a factor process in addition to the stock price process, where all the model primitives are unknown. We take the reinforcement learning (RL) approach to learn optimal portfolio policies directly by exploring the unknown market, without attempting to estimate the model parameters. Based on the entropy-regularization framework for general continuous-time RL formulated in Wang et al. (2020), we propose a recursive weighting scheme on exploration that endogenously discounts the current exploration reward by the past accumulative amount of exploration. Such a recursive regularization restores the optimality of Gaussian exploration. However, contrary to the existing results, the optimal Gaussian policy turns out to be biased in general, due to the interwinding needs for hedging and for exploration. We present an asymptotic analysis of the resulting errors to show how the level of exploration affects the learned policies. Furthermore, we establish a policy improvement theorem and design several RL algorithms to learn Merton's optimal strategies. At last, we carry out both simulation and empirical studies with a stochastic volatility environment to demonstrate the efficiency and robustness of the RL algorithms in comparison to the conventional plug-in method.
Given a set of observations, feature acquisition is about finding the subset of unobserved features which would enhance accuracy. Such problems have been explored in a sequential setting in prior work. Here, the model receives feedback from every new feature acquired and chooses to explore more features or to predict. However, sequential acquisition is not feasible in some settings where time is of the essence. We consider the problem of feature acquisition in batch, where the subset of features to be queried in batch is chosen based on the currently observed features, and then acquired as a batch, followed by prediction. We solve this problem using several technical innovations. First, we use a feature generator to draw a subset of the synthetic features for some examples, which reduces the cost of oracle queries. Second, to make the feature acquisition problem tractable for the large heterogeneous observed features, we partition the data into buckets, by borrowing tools from locality sensitive hashing and then train a mixture of experts model. Third, we design a tractable lower bound of the original objective. We use a greedy algorithm combined with model training to solve the underlying problem. Experiments with four datasets show that our approach outperforms these methods in terms of trade-off between accuracy and feature acquisition cost.
Gradient inversion attacks can leak data privacy when clients share weight updates with the server in federated learning (FL). Existing studies mainly use L2 or cosine distance as the loss function for gradient matching in the attack. Our empirical investigation shows that the vulnerability ranking varies with the loss function used. Gradient norm, which is commonly used as a vulnerability proxy for gradient inversion attack, cannot explain this as it remains constant regardless of the loss function for gradient matching. In this paper, we propose a loss-aware vulnerability proxy (LAVP) for the first time. LAVP refers to either the maximum or minimum eigenvalue of the Hessian with respect to gradient matching loss at ground truth. This suggestion is based on our theoretical findings regarding the local optimization of the gradient inversion in proximity to the ground truth, which corresponds to the worst case attack scenario. We demonstrate the effectiveness of LAVP on various architectures and datasets, showing its consistent superiority over the gradient norm in capturing sample vulnerabilities. The performance of each proxy is measured in terms of Spearman's rank correlation with respect to several similarity scores. This work will contribute to enhancing FL security against any potential loss functions beyond L2 or cosine distance in the future.
While generating realistic body movements, e.g., for avatars in virtual reality, is widely studied in computer vision and graphics, the generation of eye movements that exhibit realistic coordination with the body remains under-explored. We first report a comprehensive analysis of the coordination of human eye and full-body movements during everyday activities based on data from the MoGaze and GIMO datasets. We show that eye gaze has strong correlations with head directions and also full-body motions and there exists a noticeable time delay between body and eye movements. Inspired by the analyses, we then present Pose2Gaze -- a novel eye-body coordination model that first uses a convolutional neural network and a spatio-temporal graph convolutional neural network to extract features from head directions and full-body poses respectively and then applies a convolutional neural network to generate realistic eye movements. We compare our method with state-of-the-art methods that predict eye gaze only from head movements for three different generation tasks and demonstrate that Pose2Gaze significantly outperforms these baselines on both datasets with an average improvement of 26.4% and 21.6% in mean angular error, respectively. Our findings underline the significant potential of cross-modal human gaze behaviour analysis and modelling.
Human motion forecasting, with the goal of estimating future human behavior over a period of time, is a fundamental task in many real-world applications. However, existing works typically concentrate on predicting the major joints of the human body without considering the delicate movements of the human hands. In practical applications, hand gesture plays an important role in human communication with the real world, and expresses the primary intention of human beings. In this work, we are the first to formulate a whole-body human pose forecasting task, which jointly predicts the future body and hand activities. Correspondingly, we propose a novel Encoding-Alignment-Interaction (EAI) framework that aims to predict both coarse (body joints) and fine-grained (gestures) activities collaboratively, enabling expressive and cross-facilitated forecasting of 3D whole-body human motions. Specifically, our model involves two key constituents: cross-context alignment (XCA) and cross-context interaction (XCI). Considering the heterogeneous information within the whole-body, XCA aims to align the latent features of various human components, while XCI focuses on effectively capturing the context interaction among the human components. We conduct extensive experiments on a newly-introduced large-scale benchmark and achieve state-of-the-art performance. The code is public for research purposes at https://github.com/Dingpx/EAI.
Videos are highly redundant data source and it is often enough to identify a few key moments to solve any given task. In this paper, we present a text-conditioned video resampler (TCR) module that uses a pre-trained and frozen visual encoder and large language model (LLM) to process long video sequences for a task. TCR localises relevant visual features from the video given a text condition and provides them to a LLM to generate a text response. Due to its lightweight design and use of cross-attention, TCR can process more than 100 frames at a time allowing the model to use much longer chunks of video than earlier works. We make the following contributions: (i) we design a transformer-based sampling architecture that can process long videos conditioned on a task, together with a training method that enables it to bridge pre-trained visual and language models; (ii) we empirically validate its efficacy on a wide variety of evaluation tasks, and set a new state-of-the-art on NextQA, EgoSchema, and the EGO4D-LTA challenge; and (iii) we determine tasks which require longer video contexts and that can thus be used effectively for further evaluation of long-range video models.
Quantitative phase imaging (QPI) through multi-core fibers (MCFs) has been an emerging in vivo label-free endoscopic imaging modality with minimal invasiveness. However, the computational demands of conventional iterative phase retrieval algorithms have limited their real-time imaging potential. We demonstrate a learning-based MCF phase imaging method, that significantly reduced the phase reconstruction time to 5.5 ms, enabling video-rate imaging at 181 fps. Moreover, we introduce an innovative optical system that automatically generated the first open-source dataset tailored for MCF phase imaging, comprising 50,176 paired speckle and phase images. Our trained deep neural network (DNN) demonstrates robust phase reconstruction performance in experiments with a mean fidelity of up to 99.8\%. Such an efficient fiber phase imaging approach can broaden the applications of QPI in hard-to-reach areas.
In this project, we have implemented a model to recognize real-time facial emotions given the camera images. Current approaches would read all data and input it into their model, which has high space complexity. Our model is based on the Convolutional Neural Network utilizing the PyTorch library. We believe our implementation will significantly improve the space complexity and provide a useful contribution to facial emotion recognition. Our motivation is to understanding clearly about deep learning, particularly in CNNs, and analysis real-life scenarios. Therefore, we tunned the hyper parameter of model such as learning rate, batch size, and number of epochs to meet our needs. In addition, we also used techniques to optimize the networks, such as activation function, dropout and max pooling. Finally, we analyzed the result from two optimizer to observe the relationship between number of epochs and accuracy.
Current multichannel speech enhancement algorithms typically assume a stationary sound source, a common mismatch with reality that limits their performance in real-world scenarios. This paper focuses on attention-driven spatial filtering techniques designed for dynamic settings. Specifically, we study the application of linear and nonlinear attention-based methods for estimating time-varying spatial covariance matrices used to design the filters. We also investigate the direct estimation of spatial filters by attention-based methods without explicitly estimating spatial statistics. The clean speech clips from WSJ0 are employed for simulating speech signals of moving speakers in a reverberant environment. The experimental dataset is built by mixing the simulated speech signals with multichannel real noise from CHiME-3. Evaluation results show that the attention-driven approaches are robust and consistently outperform conventional spatial filtering approaches in both static and dynamic sound environments.