Neural Radiance Fields (NeRFs) have revolutionized scene novel view synthesis, offering visually realistic, precise, and robust implicit reconstructions. While recent approaches enable NeRF editing, such as object removal, 3D shape modification, or material property manipulation, the manual annotation prior to such edits makes the process tedious. Additionally, traditional 2D interaction tools lack an accurate sense of 3D space, preventing precise manipulation and editing of scenes. In this paper, we introduce a novel approach, called Blueprint Neural Field (BluNF), to address these editing issues. BluNF provides a robust and user-friendly 2D blueprint, enabling intuitive scene editing. By leveraging implicit neural representation, BluNF constructs a blueprint of a scene using prior semantic and depth information. The generated blueprint allows effortless editing and manipulation of NeRF representations. We demonstrate BluNF's editability through an intuitive click-and-change mechanism, enabling 3D manipulations, such as masking, appearance modification, and object removal. Our approach significantly contributes to visual content creation, paving the way for further research in this area.
The correction of exposure-related issues is a pivotal component in enhancing the quality of images, offering substantial implications for various computer vision tasks. Historically, most methodologies have predominantly utilized spatial domain recovery, offering limited consideration to the potentialities of the frequency domain. Additionally, there has been a lack of a unified perspective towards low-light enhancement, exposure correction, and multi-exposure fusion, complicating and impeding the optimization of image processing. In response to these challenges, this paper proposes a novel methodology that leverages the frequency domain to improve and unify the handling of exposure correction tasks. Our method introduces Holistic Frequency Attention and Dynamic Frequency Feed-Forward Network, which replace conventional correlation computation in the spatial-domain. They form a foundational building block that facilitates a U-shaped Holistic Dynamic Frequency Transformer as a filter to extract global information and dynamically select important frequency bands for image restoration. Complementing this, we employ a Laplacian pyramid to decompose images into distinct frequency bands, followed by multiple restorers, each tuned to recover specific frequency-band information. The pyramid fusion allows a more detailed and nuanced image restoration process. Ultimately, our structure unifies the three tasks of low-light enhancement, exposure correction, and multi-exposure fusion, enabling comprehensive treatment of all classical exposure errors. Benchmarking on mainstream datasets for these tasks, our proposed method achieves state-of-the-art results, paving the way for more sophisticated and unified solutions in exposure correction.
This paper studies contextual biasing with Large Language Models (LLMs), where during second-pass rescoring additional contextual information is provided to a LLM to boost Automatic Speech Recognition (ASR) performance. We propose to leverage prompts for a LLM without fine tuning during rescoring which incorporate a biasing list and few-shot examples to serve as additional information when calculating the score for the hypothesis. In addition to few-shot prompt learning, we propose multi-task training of the LLM to predict both the entity class and the next token. To improve the efficiency for contextual biasing and to avoid exceeding LLMs' maximum sequence lengths, we propose dynamic prompting, where we select the most likely class using the class tag prediction, and only use entities in this class as contexts for next token prediction. Word Error Rate (WER) evaluation is performed on i) an internal calling, messaging, and dictation dataset, and ii) the SLUE-Voxpopuli dataset. Results indicate that biasing lists and few-shot examples can achieve 17.8% and 9.6% relative improvement compared to first pass ASR, and that multi-task training and dynamic prompting can achieve 20.0% and 11.3% relative WER improvement, respectively.
Discontinuous motion which is a motion composed of multiple continuous motions with sudden change in direction or velocity in between, can be seen in state-aware robotic tasks. Such robotic tasks are often coordinated with sensor information such as image. In recent years, Dynamic Movement Primitives (DMP) which is a method for generating motor behaviors suitable for robotics has garnered several deep learning based improvements to allow associations between sensor information and DMP parameters. While the implementation of deep learning framework does improve upon DMP's inability to directly associate to an input, we found that it has difficulty learning DMP parameters for complex motion which requires large number of basis functions to reconstruct. In this paper we propose a novel deep learning network architecture called Deep Segmented DMP Network (DSDNet) which generates variable-length segmented motion by utilizing the combination of multiple DMP parameters predicting network architecture, double-stage decoder network, and number of segments predictor. The proposed method is evaluated on both artificial data (object cutting & pick-and-place) and real data (object cutting) where our proposed method could achieve high generalization capability, task-achievement, and data-efficiency compared to previous method on generating discontinuous long-horizon motions.
Information access systems, such as search engines, recommender systems, and conversational assistants, have become integral to our daily lives as they help us satisfy our information needs. However, evaluating the effectiveness of these systems presents a long-standing and complex scientific challenge. This challenge is rooted in the difficulty of assessing a system's overall effectiveness in assisting users to complete tasks through interactive support, and further exacerbated by the substantial variation in user behaviour and preferences. To address this challenge, user simulation emerges as a promising solution. This book focuses on providing a thorough understanding of user simulation techniques designed specifically for evaluation purposes. We begin with a background of information access system evaluation and explore the diverse applications of user simulation. Subsequently, we systematically review the major research progress in user simulation, covering both general frameworks for designing user simulators, utilizing user simulation for evaluation, and specific models and algorithms for simulating user interactions with search engines, recommender systems, and conversational assistants. Realizing that user simulation is an interdisciplinary research topic, whenever possible, we attempt to establish connections with related fields, including machine learning, dialogue systems, user modeling, and economics. We end the book with a detailed discussion of important future research directions, many of which extend beyond the evaluation of information access systems and are expected to have broader impact on how to evaluate interactive intelligent systems in general.
The widespread emergence of the COVID-19 pandemic has transformed our lifestyle, and facial respirators have become an essential part of daily life. Nevertheless, the current respirators possess several limitations such as poor respirator fit because they are incapable of covering diverse human facial sizes and shapes, potentially diminishing the effect of wearing respirators. In addition, the current facial respirators do not inform the user of the air quality within the smart facepiece respirator in case of continuous long-term use. Here, we demonstrate the novel smart N-95 filtering facepiece respirator that incorporates the humidity sensor and pressure sensory feedback-enabled self-fit adjusting functionality for the effective performance of the facial respirator to prevent the transmission of airborne pathogens. The laser-induced graphene (LIG) constitutes the humidity sensor, and the pressure sensor array based on the dielectric elastomeric sponge monitors the respirator contact on the face of the user, providing the sensory information for a closed-loop feedback mechanism. As a result of the self-fit adjusting mode along with elastomeric lining, the fit factor is increased by 3.20 and 5 times at average and maximum respectively. We expect that the experimental proof-of-concept of this work will offer viable solutions to the current commercial respirators to address the limitations.
In prediction-based Neural Architecture Search (NAS), performance indicators derived from graph convolutional networks have shown significant success. These indicators, achieved by representing feed-forward structures as component graphs through one-hot encoding, face a limitation: their inability to evaluate architecture performance across varying search spaces. In contrast, handcrafted performance indicators (zero-shot NAS), which use the same architecture with random initialization, can generalize across multiple search spaces. Addressing this limitation, we propose a novel approach for zero-shot NAS using deep learning. Our method employs Fourier sum of sines encoding for convolutional kernels, enabling the construction of a computational feed-forward graph with a structure similar to the architecture under evaluation. These encodings are learnable and offer a comprehensive view of the architecture's topological information. An accompanying multi-layer perceptron (MLP) then ranks these architectures based on their encodings. Experimental results show that our approach surpasses previous methods using graph convolutional networks in terms of correlation on the NAS-Bench-201 dataset and exhibits a higher convergence rate. Moreover, our extracted feature representation trained on each NAS-Benchmark is transferable to other NAS-Benchmarks, showing promising generalizability across multiple search spaces. The code is available at: https://github.com/minh1409/DFT-NPZS-NAS
Recent works have demonstrated the superiority of supervised Convolutional Neural Networks (CNNs) in learning hierarchical representations from time series data for successful classification. These methods require sufficiently large labeled data for stable learning, however acquiring high-quality labeled time series data can be costly and potentially infeasible. Generative Adversarial Networks (GANs) have achieved great success in enhancing unsupervised and semi-supervised learning. Nonetheless, to our best knowledge, it remains unclear how effectively GANs can serve as a general-purpose solution to learn representations for time series recognition, i.e., classification and clustering. The above considerations inspire us to introduce a Time-series Convolutional GAN (TCGAN). TCGAN learns by playing an adversarial game between two one-dimensional CNNs (i.e., a generator and a discriminator) in the absence of label information. Parts of the trained TCGAN are then reused to construct a representation encoder to empower linear recognition methods. We conducted comprehensive experiments on synthetic and real-world datasets. The results demonstrate that TCGAN is faster and more accurate than existing time-series GANs. The learned representations enable simple classification and clustering methods to achieve superior and stable performance. Furthermore, TCGAN retains high efficacy in scenarios with few-labeled and imbalanced-labeled data. Our work provides a promising path to effectively utilize abundant unlabeled time series data.
Semantic communications (SC) have been expected to be a new paradigm shifting to catalyze the next generation communication, whose main concerns shift from accurate bit transmission to effective semantic information exchange in communications. However, the previous and widely-used metrics for images are not applicable to evaluate the image semantic similarity in SC. Classical metrics to measure the similarity between two images usually rely on the pixel level or the structural level, such as the PSNR and the MS-SSIM. Straightforwardly using some tailored metrics based on deep-learning methods in CV community, such as the LPIPS, is infeasible for SC. To tackle this, inspired by BERTScore in NLP community, we propose a novel metric for evaluating image semantic similarity, named Vision Transformer Score (ViTScore). We prove theoretically that ViTScore has 3 important properties, including symmetry, boundedness, and normalization, which make ViTScore convenient and intuitive for image measurement. To evaluate the performance of ViTScore, we compare ViTScore with 3 typical metrics (PSNR, MS-SSIM, and LPIPS) through 5 classes of experiments. Experimental results demonstrate that ViTScore can better evaluate the image semantic similarity than the other 3 typical metrics, which indicates that ViTScore is an effective performance metric when deployed in SC scenarios.
We introduce a novel training strategy for stereo matching and optical flow estimation that utilizes image-to-image translation between synthetic and real image domains. Our approach enables the training of models that excel in real image scenarios while relying solely on ground-truth information from synthetic images. To facilitate task-agnostic domain adaptation and the training of task-specific components, we introduce a bidirectional feature warping module that handles both left-right and forward-backward directions. Experimental results show competitive performance over previous domain translation-based methods, which substantiate the efficacy of our proposed framework, effectively leveraging the benefits of unsupervised domain adaptation, stereo matching, and optical flow estimation.