Search

Let $\pi : X \to B$ be a projective Lagrangian fibration of a smooth symplectic variety $X$ to a smooth variety $B$. Denote the complement of the discriminant locus by $B_0 = B \setminus \operatorname{Disc}(\pi)$, its preimage by $X_0 = \pi^{-1}(B_0)$, and the complement of the critical locus by $X' = X \setminus \operatorname{Sing}(\pi)$. Under an assumption that the morphism $X' \to B$ is surjective, we construct (1) the N\'eron model of the abelian fibration $\pi_0 : X_0 \to B_0$ and (2) the N\'eron model of its automorphism abelian scheme $\operatorname{Aut}^{\circ}_{\pi_0} \to B_0$. Contrary to the case of elliptic fibrations, $X'$ may not be the N\'eron model of $X_0$; this is precisely because of the existence of flops in higher-dimensional symplectic varieties. Using such techniques, we analyze when $X' \to B$ is a torsor under a smooth group scheme and also revisit some known results in literature., Comment: 85 pages; comments welcome

In this paper, we present a new method for designing wavelet filter banks for any dilation matrices and in any dimension. Our approach utilizes extended Laplacian pyramid matrices to achieve this flexibility. By generalizing recent tight wavelet frame construction methods based on the sum of squares representation, we introduce the sum of vanishing products (SVP) condition, which is significantly easier to satisfy. These flexible design methods rely on our main results, which establish the equivalence between the SVP and mixed unitary extension principle conditions. Additionally, we provide illustrative examples to showcase our main findings., Comment: This paper was submitted to wspc/ws-ijwmip

We propose a new framework for creating and easily manipulating 3D models of arbitrary objects using casually captured videos. Our core ingredient is a novel hierarchy deformation model, which captures motions of objects with a tree-structured bones. Our hierarchy system decomposes motions based on the granularity and reveals the correlations between parts without exploiting any prior structural knowledge. We further propose to regularize the bones to be positioned at the basis of motions, centers of parts, sufficiently covering related surfaces of the part. This is achieved by our bone occupancy function, which identifies whether a given 3D point is placed within the bone. Coupling the proposed components, our framework offers several clear advantages: (1) users can obtain animatable 3D models of the arbitrary objects in improved quality from their casual videos, (2) users can manipulate 3D models in an intuitive manner with minimal costs, and (3) users can interactively add or delete control points as necessary. The experimental results demonstrate the efficacy of our framework on diverse instances, in reconstruction quality, interpretability and easier manipulation. Our code is available at https://github.com/subin6/HSNB., Comment: ECCV 2024 accepted

In recent times, the need for effective super-resolution (SR) techniques has surged, especially for large-scale images ranging 2K to 8K resolutions. For DNN-based SISR, decomposing images into overlapping patches is typically necessary due to computational constraints. In such patch-decomposing scheme, one can allocate computational resources differently based on each patch's difficulty to further improve efficiency while maintaining SR performance. However, this approach has a limitation: computational resources is uniformly allocated within a patch, leading to lower efficiency when the patch contain pixels with varying levels of restoration difficulty. To address the issue, we propose the Pixel-level Classifier for Single Image Super-Resolution (PCSR), a novel method designed to distribute computational resources adaptively at the pixel level. A PCSR model comprises a backbone, a pixel-level classifier, and a set of pixel-level upsamplers with varying capacities. The pixel-level classifier assigns each pixel to an appropriate upsampler based on its restoration difficulty, thereby optimizing computational resource usage. Our method allows for performance and computational cost balance during inference without re-training. Our experiments demonstrate PCSR's advantage over existing patch-distributing methods in PSNR-FLOP trade-offs across different backbone models and benchmarks. The code is available at https://github.com/3587jjh/PCSR., Comment: Accepted by ECCV 2024

This paper aims to facilitate more practical NLOS imaging by reducing the number of samplings and scan areas. To this end, we introduce a phasor-based enhancement network that is capable of predicting clean and full measurements from noisy partial observations. We leverage a denoising autoencoder scheme to acquire rich and noise-robust representations in the measurement space. Through this pipeline, our enhancement network is trained to accurately reconstruct complete measurements from their corrupted and partial counterparts. However, we observe that the \naive application of denoising often yields degraded and over-smoothed results, caused by unnecessary and spurious frequency signals present in measurements. To address this issue, we introduce a phasor-based pipeline designed to limit the spectrum of our network to the frequency range of interests, where the majority of informative signals are detected. The phasor wavefronts at the aperture, which are band-limited signals, are employed as inputs and outputs of the network, guiding our network to learn from the frequency range of interests and discard unnecessary information. The experimental results in more practical acquisition scenarios demonstrate that we can look around the corners with $16\times$ or $64\times$ fewer samplings and $4\times$ smaller apertures. Our code is available at https://github.com/join16/LEAP.

Online Temporal Action Localization (On-TAL) is a critical task that aims to instantaneously identify action instances in untrimmed streaming videos as soon as an action concludes -- a major leap from frame-based Online Action Detection (OAD). Yet, the challenge of detecting overlapping actions is often overlooked even though it is a common scenario in streaming videos. Current methods that can address concurrent actions depend heavily on class information, limiting their flexibility. This paper introduces ActionSwitch, the first class-agnostic On-TAL framework capable of detecting overlapping actions. By obviating the reliance on class information, ActionSwitch provides wider applicability to various situations, including overlapping actions of the same class or scenarios where class information is unavailable. This approach is complemented by the proposed "conservativeness loss", which directly embeds a conservative decision-making principle into the loss function for On-TAL. Our ActionSwitch achieves state-of-the-art performance in complex datasets, including Epic-Kitchens 100 targeting the challenging egocentric view and FineAction consisting of fine-grained actions., Comment: ECCV2024

The vocabulary size in temporal action localization (TAL) is limited by the scarcity of large-scale annotated datasets. To overcome this, recent works integrate vision-language models (VLMs), such as CLIP, for open-vocabulary TAL (OV-TAL). However, despite the success of VLMs trained on extensive datasets, existing OV-TAL methods still rely on human-labeled TAL datasets of limited size to train action localizers, limiting their generalizability. In this paper, we explore the scalability of self-training with unlabeled YouTube videos for OV-TAL. Our approach consists of two stages: (1) a class-agnostic action localizer is trained on a human-labeled TAL dataset to generate pseudo-labels for unlabeled videos, and (2) the large-scale pseudo-labeled dataset is then used to train the localizer. Extensive experiments demonstrate that leveraging web-scale videos in self-training significantly enhances the generalizability of an action localizer. Additionally, we identify limitations in existing OV-TAL evaluation schemes and propose a new benchmark for thorough assessment. Finally, we showcase the TAL performance of the large multimodal model Gemini-1.5 on our new benchmark. Code is released at https://github.com/HYUNJS/STOV-TAL.

Voxel hierarchy on dynamic brain graphs is produced by k core percolation on functional dynamic amplitude correlation of resting-state fMRI. Directed graphs and their afferent/efferent capacities are produced by Markov modeling of the universal cover of undirected graphs simultaneously with the calculation of volume entropy. Positive and unsigned negative brain graphs were analyzed separately on sliding-window representation to underpin the visualization and quantitation of mental dynamic states with their transitions. Voxel hierarchy animation maps of positive graphs revealed abrupt changes in coreness k and kmaxcore, which we called mental state transitions. Afferent voxel capacities of the positive graphs also revealed transient modules composed of dominating voxels/independent components and their exchanges representing mental state transitions. Animation and quantification plots of voxel hierarchy and afferent capacity corroborated each other in underpinning mental state transitions and afferent module exchange on the positive directed functional connectivity graphs. We propose the use of spatiotemporal trajectories of voxels on positive dynamic graphs to construct hierarchical structures by k core percolation and quantified in- and out-flows of information of voxels by volume entropy/directed graphs to subserve diverse resting mental state transitions on resting-state fMRI graphs in normal human individuals.

Advancements in egocentric video datasets like Ego4D, EPIC-Kitchens, and Ego-Exo4D have enriched the study of first-person human interactions, which is crucial for applications in augmented reality and assisted living. Despite these advancements, current Online Action Detection methods, which efficiently detect actions in streaming videos, are predominantly designed for exocentric views and thus fail to capitalize on the unique perspectives inherent to egocentric videos. To address this gap, we introduce an Object-Aware Module that integrates egocentric-specific priors into existing OAD frameworks, enhancing first-person footage interpretation. Utilizing object-specific details and temporal dynamics, our module improves scene understanding in detecting actions. Validated extensively on the Epic-Kitchens 100 dataset, our work can be seamlessly integrated into existing models with minimal overhead and bring consistent performance enhancements, marking an important step forward in adapting action detection systems to egocentric video analysis., Comment: CVPR First Joint Egocentric Vision Workshop 2024

In no-reference image quality assessment (NR-IQA), the challenge of limited dataset sizes hampers the development of robust and generalizable models. Conventional methods address this issue by utilizing large datasets to extract rich representations for IQA. Also, some approaches propose vision language models (VLM) based IQA, but the domain gap between generic VLM and IQA constrains their scalability. In this work, we propose a novel pretraining framework that constructs a generalizable representation for IQA by selectively extracting quality-related knowledge from VLM and leveraging the scalability of large datasets. Specifically, we select optimal text prompts for five representative image quality attributes and use VLM to generate pseudo-labels. Numerous attribute-aware pseudo-labels can be generated with large image datasets, allowing our IQA model to learn rich representations about image quality. Our approach achieves state-of-the-art performance on multiple IQA datasets and exhibits remarkable generalization capabilities. Leveraging these strengths, we propose several applications, such as evaluating image generation models and training image enhancement models, demonstrating our model's real-world applicability.

We give for the first time, theoretical estimates of ground-state-to-ground-state (GS-to-GS) electron-capture (EC) branch decay rates of $^{44}$Ti, $^{57}$Co, and $^{139}$Ce. The nuclear-structure calculations have been done exploiting the nuclear shell model (NSM) with well-established Hamiltonians and an advanced theory of $\beta$ decay. In the absence of experimental measurements of these GS-to-GS branches, these estimates are of utmost importance for terrestrial searches of axion-like particles (ALPs). Predictions are made for EC-decay rates of 2$^{nd}$-forbidden unique (FU) and 2$^{nd}$-forbidden non-unique (FNU) EC transitions that can potentially mimic nuclear axion production in experiments designed to detect ALPs in nuclear environments.

The primary purpose of studying quarkonium production in relativistic heavy-ion collisions is to understand the properties of the quark-gluon plasma. At various collision systems, measurements of quarkonium states of different binding energies, such as $\Upsilon(nS)$, can provide comprehensive information. A model study has been performed to investigate the modification of $\Upsilon(nS)$ production in Pb-Pb collisions at $\sqrt{s_{\mathrm{NN}}}=$ 5.02 TeV and Au-Au collisions at $\sqrt{s_{\mathrm{NN}}}=$ 200 GeV. The Monte-Carlo simulation study is performed with a publicly available hydrodynamic simulation package for the quark-gluon plasma medium and a theoretical calculation of temperature-dependent thermal width of $\Upsilon(nS)$ considering the gluo-dissociation and inelastic parton scattering for dissociation inside the medium. In addition, we perform a systematic study with different descriptions of initial collision geometry and formation time of $\Upsilon(nS)$ to investigate their impacts on yield modification. The model calculation with a varied parameter set can describe the experimental data of $\Upsilon(nS)$ in Pb-Pb collisions at 5.02 TeV and $\Upsilon(2S)$ in Au-Au collisions at 200 GeV but underestimates the modification of $\Upsilon(1S)$ at the lower collision energy. The nuclear absorption mechanism is explored to understand the discrepancy between the data and simulation., Comment: 9 pages, 11 figures

The classification of sleep stages is a pivotal aspect of diagnosing sleep disorders and evaluating sleep quality. However, the conventional manual scoring process, conducted by clinicians, is time-consuming and prone to human bias. Recent advancements in deep learning have substantially propelled the automation of sleep stage classification. Nevertheless, challenges persist, including the need for large datasets with labels and the inherent biases in human-generated annotations. This paper introduces NeuroNet, a self-supervised learning (SSL) framework designed to effectively harness unlabeled single-channel sleep electroencephalogram (EEG) signals by integrating contrastive learning tasks and masked prediction tasks. NeuroNet demonstrates superior performance over existing SSL methodologies through extensive experimentation conducted across three polysomnography (PSG) datasets. Additionally, this study proposes a Mamba-based temporal context module to capture the relationships among diverse EEG epochs. Combining NeuroNet with the Mamba-based temporal context module has demonstrated the capability to achieve, or even surpass, the performance of the latest supervised learning methodologies, even with a limited amount of labeled data. This study is expected to establish a new benchmark in sleep stage classification, promising to guide future research and applications in the field of sleep analysis., Comment: 14 pages, 4 figures

Requiring extensive human supervision is often impractical for continual learning due to its cost, leading to the emergence of 'name-only continual learning' that only provides the name of new concepts (e.g., classes) without providing supervised samples. To address the task, recent approach uses web-scraped data but results in issues such as data imbalance, copyright, and privacy concerns. To overcome the limitations of both human supervision and webly supervision, we propose Generative name only Continual Learning (GenCL) using generative models for the name only continual learning. But na\"ive application of generative models results in limited diversity of generated data. So, we specifically propose a diverse prompt generation method, HIerarchical Recurrent Prompt Generation (HIRPG) as well as COmplexity-NAvigating eNsembler (CONAN) that selects samples with minimal overlap from multiple generative models. We empirically validate that the proposed GenCL outperforms prior arts, even a model trained with fully supervised data, in various tasks including image recognition and multi-modal visual reasoning. Data generated by GenCL is available at https://anonymous.4open.science/r/name-only-continual-E079.

Nonlinear quantum photonics serves as a cornerstone in photonic quantum technologies, such as universal quantum computing and quantum communications. The emergence of integrated photonics platform not only offers the advantage of large-scale manufacturing but also provides a variety of engineering methods. Given the complexity of integrated photonics engineering, a comprehensive simulation framework is essential to fully harness the potential of the platform. In this context, we introduce a nonlinear quantum photonics simulation framework which can accurately model a variety of features such as adiabatic waveguide, material anisotropy, linear optics components, photon losses, and detectors. Furthermore, utilizing the framework, we have developed a device scheme, chip-scale temporal walk-off compensation, that is useful for various quantum information processing tasks. Applying the simulation framework, we show that the proposed device scheme can enhance the squeezing parameter of photon-pair sources and the conversion efficiency of quantum frequency converters without relying on higher pump power., Comment: 35 pages, 33 figures, 4 tables

White balance (WB) algorithms in many commercial cameras assume single and uniform illumination, leading to undesirable results when multiple lighting sources with different chromaticities exist in the scene. Prior research on multi-illuminant WB typically predicts illumination at the pixel level without fully grasping the scene's actual lighting conditions, including the number and color of light sources. This often results in unnatural outcomes lacking in overall consistency. To handle this problem, we present a deep white balancing model that leverages the slot attention, where each slot is in charge of representing individual illuminants. This design enables the model to generate chromaticities and weight maps for individual illuminants, which are then fused to compose the final illumination map. Furthermore, we propose the centroid-matching loss, which regulates the activation of each slot based on the color range, thereby enhancing the model to separate illumination more effectively. Our method achieves the state-of-the-art performance on both single- and multi-illuminant WB benchmarks, and also offers additional information such as the number of illuminants in the scene and their chromaticity. This capability allows for illumination editing, an application not feasible with prior methods., Comment: CVPR 2024

This article initiates the study of isotrivial Lagrangian fibrations of compact hyper-K\"ahler manifolds. We present four foundational results that extend well-known facts about isotrivial elliptic fibrations of K3 surfaces. First, we prove that smooth fibers of an isotrivial Lagrangian fibration are isogenous to a power of an elliptic curve. Second, we exhibit a dichotomy between two types of isotrivial Lagrangian fibrations, which we call A and B. Third, we give a classification result for type A isotrivial Lagrangian fibrations. Namely, if a type A isotrivial Lagrangian fibration admits a rational section, then it is birational to one of two straightforward examples of isotrivial fibrations of hyper-K\"ahler manifolds of $\text{K3}^{[n]}$-type and $\text{Kum}_n$-type. Finally, we prove that a genericity assumption on the smooth fiber of an isotrivial Lagrangian fibration ensures that the fibration is of type A., Comment: 44 pages. Major revision: the paper no longer uses the conjecture on the base

In recent years, online Video Instance Segmentation (VIS) methods have shown remarkable advancement with their powerful query-based detectors. Utilizing the output queries of the detector at the frame-level, these methods achieve high accuracy on challenging benchmarks. However, our observations demonstrate that these methods heavily rely on location information, which often causes incorrect associations between objects. This paper presents that a key axis of object matching in trackers is appearance information, which becomes greatly instructive under conditions where positional cues are insufficient for distinguishing their identities. Therefore, we suggest a simple yet powerful extension to object decoders that explicitly extract embeddings from backbone features and drive queries to capture the appearances of objects, which greatly enhances instance association accuracy. Furthermore, recognizing the limitations of existing benchmarks in fully evaluating appearance awareness, we have constructed a synthetic dataset to rigorously validate our method. By effectively resolving the over-reliance on location information, we achieve state-of-the-art results on YouTube-VIS 2019/2021 and Occluded VIS (OVIS). Code is available at https://github.com/KimHanjung/VISAGE., Comment: Technical report

The binding problem in artificial neural networks is actively explored with the goal of achieving human-level recognition skills through the comprehension of the world in terms of symbol-like entities. Especially in the field of computer vision, object-centric learning (OCL) is extensively researched to better understand complex scenes by acquiring object representations or slots. While recent studies in OCL have made strides with complex images or videos, the interpretability and interactivity over object representation remain largely uncharted, still holding promise in the field of OCL. In this paper, we introduce a novel method, Slot Attention with Image Augmentation (SlotAug), to explore the possibility of learning interpretable controllability over slots in a self-supervised manner by utilizing an image augmentation strategy. We also devise the concept of sustainability in controllable slots by introducing iterative and reversible controls over slots with two proposed submethods: Auxiliary Identity Manipulation and Slot Consistency Loss. Extensive empirical studies and theoretical validation confirm the effectiveness of our approach, offering a novel capability for interpretable and sustainable control of object representations.

This paper presents a novel optimization-based method for non-line-of-sight (NLOS) imaging that aims to reconstruct hidden scenes under general setups with significantly reduced reconstruction time. In NLOS imaging, the visible surfaces of the target objects are notably sparse. To mitigate unnecessary computations arising from empty regions, we design our method to render the transients through partial propagations from a continuously sampled set of points from the hidden space. Our method is capable of accurately and efficiently modeling the view-dependent reflectance using surface normals, which enables us to obtain surface geometry as well as albedo. In this pipeline, we propose a novel domain reduction strategy to eliminate superfluous computations in empty regions. During the optimization process, our domain reduction procedure periodically prunes the empty regions from our sampling domain in a coarse-to-fine manner, leading to substantial improvement in efficiency. We demonstrate the effectiveness of our method in various NLOS scenarios with sparse scanning patterns. Experiments conducted on both synthetic and real-world data support the efficacy in general NLOS scenarios, and the improved efficiency of our method compared to the previous optimization-based solutions. Our code is available at https://github.com/hyunbo9/domain-reduction-strategy., Comment: 27 pages, 15 figures