Search

In this paper we formulate the almost invariant subspaces theorems of backward shift operators in terms of the ranges or kernels of product of Toeplitz and Hankel operators. This approach simplifies and gives more explicit forms of these almost invariant subspaces which are derived from related nearly backward shift invariant subspaces with finite defect. Furthermore, this approach also leads to the surprising result that the almost invariant subspaces of backward shift operators are the same as the almost invariant subspaces of forward shift operators which were treated only briefly in literature., Comment: 21 pages

Omnidirectional (360-degree) video is rapidly gaining popularity due to advancements in immersive technologies like virtual reality (VR) and extended reality (XR). However, real-time streaming of such videos, especially in live mobile scenarios like unmanned aerial vehicles (UAVs), is challenged by limited bandwidth and strict latency constraints. Traditional methods, such as compression and adaptive resolution, help but often compromise video quality and introduce artifacts that degrade the viewer experience. Additionally, the unique spherical geometry of 360-degree video presents challenges not encountered in traditional 2D video. To address these issues, we initiated the 360-degree Video Super Resolution and Quality Enhancement Challenge. This competition encourages participants to develop efficient machine learning solutions to enhance the quality of low-bitrate compressed 360-degree videos, with two tracks focusing on 2x and 4x super-resolution (SR). In this paper, we outline the challenge framework, detailing the two competition tracks and highlighting the SR solutions proposed by the top-performing models. We assess these models within a unified framework, considering quality enhancement, bitrate gain, and computational efficiency. This challenge aims to drive innovation in real-time 360-degree video streaming, improving the quality and accessibility of immersive visual experiences., Comment: 14 pages, 9 figures

As we enter the era of big data, collecting high-quality data is very important. However, collecting data by humans is not only very time-consuming but also expensive. Therefore, many scientists have devised various methods to collect data using computers. Among them, there is a method called web crawling, but the authors found that the crawling method has a problem in that unintended data is collected along with the user. The authors found that this can be filtered using the object recognition model YOLOv10. However, there are cases where data that is not properly filtered remains. Here, image reclassification was performed by additionally utilizing the distance output from the Siamese network, and higher performance was recorded than other classification models. (average \_f1 score YOLO+MobileNet 0.678->YOLO+SiameseNet 0.772)) The user can specify a distance threshold to adjust the balance between data deficiency and noise-robustness. The authors also found that the Siamese network can achieve higher performance with fewer resources because the cropped images are used for object recognition when processing images in the Siamese network. (Class 20 mean-based f1 score, non-crop+Siamese(MobileNetV3-Small) 80.94 -> crop preprocessing+Siamese(MobileNetV3-Small) 82.31) In this way, the image retrieval system that utilizes two consecutive models to reduce errors can save users' time and effort, and build better quality data faster and with fewer resources than before., Comment: 15 pages, 13 figures, 2 tables

We present a method to create diffusion-based video models from pretrained Text-to-Image (T2I) models. Recently, AnimateDiff proposed freezing the T2I model while only training temporal layers. We advance this method by proposing a unique architecture, incorporating a mapping network and frame-wise tokens, tailored for video generation while maintaining the diversity and creativity of the original T2I model. Key innovations include novel loss functions for temporal smoothness and a mitigating gradient sampling technique, ensuring realistic and temporally consistent video generation despite limited public video data. We have successfully integrated video-specific inductive biases into the architecture and loss functions. Our method, built on the frozen StableDiffusion model, simplifies training processes and allows for seamless integration with off-the-shelf models like ControlNet and DreamBooth. project page: https://kwonminki.github.io/HARIVO, Comment: ECCV2024

Beam shaping in nanophotonic systems remains a challenge due to the reliance on complex heuristic optimization procedures. In this work, we experimentally demonstrate a novel approach to topological beam shaping using Jackiw-Rebbi states in metasurfaces. By fabricating thin-film dielectric structures with engineered Dirac-mass distributions, we create domain walls that allow precise control over beam profiles. We observe the emergence of Jackiw-Rebbi states and confirm their localized characteristics. Notably, we achieve a flat-top beam profile by carefully tailoring the Dirac mass distribution, highlighting the potential of this method for customized beam shaping. This experimental realization establishes our approach as a new mechanism for beam control, rooted in topological physics, and offers an efficient strategy for nanophotonic design.

We present the largest Galactic neutral hydrogen HI absorption survey to date, utilizing the Australian SKA Pathfinder Telescope at an unprecedented spatial resolution of 30''. This survey, GASKAP-HI, unbiasedly targets 2,714 continuum background sources over 250 square degrees in the direction of the Magellanic Clouds, a significant increase compared to a total of 373 sources observed by previous Galactic absorption surveys across the entire Milky Way. We aim to investigate the physical properties of cold (CNM) and warm (WNM) neutral atomic gas in the Milky Way foreground, characterized by two prominent filaments at high Galactic latitudes (between $-45^{\circ}$ and $-25^{\circ}$). We detected strong HI absorption along 462 lines of sight above the 3$\sigma$ threshold, achieving an absorption detection rate of 17%. GASKAP-HI's unprecedented angular resolution allows for simultaneous absorption and emission measurements to sample almost the same gas clouds along a line of sight. A joint Gaussian decomposition is then applied to absorption-emission spectra to provide direct estimates of HI optical depths, temperatures, and column densities for the CNM and WNM components. The thermal properties of CNM components are consistent with those previously observed along a wide range of Solar neighborhood environments, indicating that cold HI properties are widely prevalent throughout the local interstellar medium. Across our region of interest, CNM accounts for ~30% of the total HI gas, with the CNM fraction increasing with column density toward the two filaments. Our analysis reveals an anti-correlation between CNM temperature and its optical depth, which implies that CNM with lower optical depth leads to a higher temperature., Comment: Largest Galactic HI Absorption Survey To Date (GASKAP-HI): Cold Atomic Gas in the Magellanic Cloud foreground using Australian SKA Pathfinder. This paper has 19 pages, 17 figures. This paper has been accepted for publication in Monthly Notices of the Royal Astronomical Society Main Journal

We study the phenomenology of the charged Higgs boson, $H^\pm$,appearing in the fermionic dark matter model mediated by the dark $Z$ boson. This model is in favor of the light dark $Z$ boson, $Z'$, and the light additional neutral Higgs boson, $h$. We find that $H^\pm \to W^\pm h$ and the $H^\pm \to W^\pm Z'$ are dominant decay channels. Thus the promising final states are trilepton signals, $e \mu \mu$ or $\mu \mu \mu$ following $Z' \to \mu^+ \mu^-$ decays and leptonic decays of the $W^\pm$ boson. The charged Higgs boson will be produced from the top quark decays $t \to b H^\pm$ following $t \bar{t}$ production, if $H^\pm$ is light. Whereas $H^\pm$ is heavier than the top quark, the dominant production processes are associated productions with either $Z'$ or $h$, $pp \to W^\star \to H^\pm h$ and $pp \to W^\star \to H^\pm Z'$. We explore the discovery potential of the charged Higgs boson at the LHC. We also discuss the implications of dark matter in relation with the charged Higgs phenomenology., Comment: 12 pages, 4 figures

We present a proof-of-concept simulation-based inference on $\Omega_{\rm m}$ and $\sigma_{8}$ from the SDSS BOSS LOWZ NGC catalog using neural networks and domain generalization techniques without the need of summary statistics. Using rapid lightcone simulations, ${\rm L{\scriptsize -PICOLA}}$, mock galaxy catalogs are produced that fully incorporate the observational effects. The collection of galaxies is fed as input to a point cloud-based network, ${\texttt{Minkowski-PointNet}}$. We also add relatively more accurate ${\rm G{\scriptsize ADGET}}$ mocks to obtain robust and generalizable neural networks. By explicitly learning the representations which reduces the discrepancies between the two different datasets via the semantic alignment loss term, we show that the latent space configuration aligns into a single plane in which the two cosmological parameters form clear axes. Consequently, during inference, the SDSS BOSS LOWZ NGC catalog maps onto the plane, demonstrating effective generalization and improving prediction accuracy compared to non-generalized models. Results from the ensemble of 25 independently trained machines find $\Omega_{\rm m}=0.339 \pm 0.056$ and $\sigma_{8}=0.801 \pm 0.061$, inferred only from the distribution of galaxies in the lightcone slices without relying on any indirect summary statistics. A single machine that best adapts to the ${\rm G{\scriptsize ADGET}}$ mocks yields a tighter prediction of $\Omega_{\rm m}=0.282 \pm 0.014$ and $\sigma_{8}=0.786 \pm 0.036$. We emphasize that adaptation across multiple domains can enhance the robustness of the neural networks in observational data., Comment: 28 pages, 14 figures; Accepted for publication in ApJ

Molecular clouds (MCs) are the birthplaces of new stars in galaxies. A key component of MCs are photodissociation regions (PDRs), where far-ultraviolet radiation plays a crucial role in determining the gas's physical and chemical state. Traditional PDR models assume chemical steady state (CSS), where the rates of H$_2$ formation and photodissociation are balanced. However, real MCs are dynamic and can be out of CSS. In this study, we demonstrate that combining H$_2$ emission lines observed in the far-ultraviolet or infrared with column density observations can be used to derive the rates of H$_2$ formation and photodissociation. We derive analytical formulae that relate these rates to observable quantities, which we validate using synthetic H$_2$ line emission maps derived from the SILCC-Zoom hydrodynamical simulation. Our method estimates integrated H$_2$ formation and dissociation rates to within 29\% accuracy. Our simulations cover a wide dynamic range in H$_2$ formation and photodissociation rates, showing significant deviations from CSS, with 74\% of the MC's mass deviating from CSS by a factor greater than 2. Our analytical formulae can effectively distinguish between regions in and out of CSS. When applied to actual H$_2$ line observations, our method can assess the chemical state of MCs, providing insights into their evolutionary stages and lifetimes., Comment: Submitted to ApJ. **Comments Welcome!** This paper is the first ("Paper-I") in 2-paper series. Paper II, entitled "The Molecular Cloud Lifecycle II: Formation and Destruction of Molecular Clouds Diagnosed via H 2 Fluorescent Emission Emission" by Burkhart et al has been recently accepted for publication in ApJ, and may be found here: arXiv:2402.01587

We introduce LocoTrack, a highly accurate and efficient model designed for the task of tracking any point (TAP) across video sequences. Previous approaches in this task often rely on local 2D correlation maps to establish correspondences from a point in the query image to a local region in the target image, which often struggle with homogeneous regions or repetitive features, leading to matching ambiguities. LocoTrack overcomes this challenge with a novel approach that utilizes all-pair correspondences across regions, i.e., local 4D correlation, to establish precise correspondences, with bidirectional correspondence and matching smoothness significantly enhancing robustness against ambiguities. We also incorporate a lightweight correlation encoder to enhance computational efficiency, and a compact Transformer architecture to integrate long-term temporal information. LocoTrack achieves unmatched accuracy on all TAP-Vid benchmarks and operates at a speed almost 6 times faster than the current state-of-the-art., Comment: ECCV 2024. Project page: https://ku-cvlab.github.io/locotrack Code: https://github.com/KU-CVLAB/locotrack

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.

We introduce HyperCLOVA X, a family of large language models (LLMs) tailored to the Korean language and culture, along with competitive capabilities in English, math, and coding. HyperCLOVA X was trained on a balanced mix of Korean, English, and code data, followed by instruction-tuning with high-quality human-annotated datasets while abiding by strict safety guidelines reflecting our commitment to responsible AI. The model is evaluated across various benchmarks, including comprehensive reasoning, knowledge, commonsense, factuality, coding, math, chatting, instruction-following, and harmlessness, in both Korean and English. HyperCLOVA X exhibits strong reasoning capabilities in Korean backed by a deep understanding of the language and cultural nuances. Further analysis of the inherent bilingual nature and its extension to multilingualism highlights the model's cross-lingual proficiency and strong generalization ability to untargeted languages, including machine translation between several language pairs and cross-lingual inference tasks. We believe that HyperCLOVA X can provide helpful guidance for regions or countries in developing their sovereign LLMs., Comment: 44 pages; updated authors list and fixed author names

Recent advances in generative models trained on large-scale datasets have made it possible to synthesize high-quality samples across various domains. Moreover, the emergence of strong inversion networks enables not only a reconstruction of real-world images but also the modification of attributes through various editing methods. However, in certain domains related to privacy issues, e.g., human faces, advanced generative models along with strong inversion methods can lead to potential misuses. In this paper, we propose an essential yet under-explored task called generative identity unlearning, which steers the model not to generate an image of a specific identity. In the generative identity unlearning, we target the following objectives: (i) preventing the generation of images with a certain identity, and (ii) preserving the overall quality of the generative model. To satisfy these goals, we propose a novel framework, Generative Unlearning for Any Identity (GUIDE), which prevents the reconstruction of a specific identity by unlearning the generator with only a single image. GUIDE consists of two parts: (i) finding a target point for optimization that un-identifies the source latent code and (ii) novel loss functions that facilitate the unlearning procedure while less affecting the learned distribution. Our extensive experiments demonstrate that our proposed method achieves state-of-the-art performance in the generative machine unlearning task. The code is available at https://github.com/KHU-AGI/GUIDE., Comment: 15 pages, 17 figures, 10 tables, CVPR 2024 Poster

Human matting is a foundation task in image and video processing, where human foreground pixels are extracted from the input. Prior works either improve the accuracy by additional guidance or improve the temporal consistency of a single instance across frames. We propose a new framework MaGGIe, Masked Guided Gradual Human Instance Matting, which predicts alpha mattes progressively for each human instances while maintaining the computational cost, precision, and consistency. Our method leverages modern architectures, including transformer attention and sparse convolution, to output all instance mattes simultaneously without exploding memory and latency. Although keeping constant inference costs in the multiple-instance scenario, our framework achieves robust and versatile performance on our proposed synthesized benchmarks. With the higher quality image and video matting benchmarks, the novel multi-instance synthesis approach from publicly available sources is introduced to increase the generalization of models in real-world scenarios., Comment: CVPR 2024. Project link: https://maggie-matt.github.io

Data augmentations are widely used in training medical image deep learning models to increase the diversity and size of sparse datasets. However, commonly used augmentation techniques can result in loss of clinically relevant information from medical images, leading to incorrect predictions at inference time. We propose the Interactive Medical Image Learning (IMIL) framework, a novel approach for improving the training of medical image analysis algorithms that enables clinician-guided intermediate training data augmentations on misprediction outliers, focusing the algorithm on relevant visual information. To prevent the model from using irrelevant features during training, IMIL will 'blackout' clinician-designated irrelevant regions and replace the original images with the augmented samples. This ensures that for originally mispredicted samples, the algorithm subsequently attends only to relevant regions and correctly correlates them with the respective diagnosis. We validate the efficacy of IMIL using radiology residents and compare its performance to state-of-the-art data augmentations. A 4.2% improvement in accuracy over ResNet-50 was observed when using IMIL on only 4% of the training set. Our study demonstrates the utility of clinician-guided interactive training to achieve meaningful data augmentations for medical image analysis algorithms., Comment: CVPR 2024 Workshop on Domain adaptation, Explainability and Fairness in AI for Medical Image Analysis (DEF-AI-MIA)

While there has been significant progress in customizing text-to-image generation models, generating images that combine multiple personalized concepts remains challenging. In this work, we introduce Concept Weaver, a method for composing customized text-to-image diffusion models at inference time. Specifically, the method breaks the process into two steps: creating a template image aligned with the semantics of input prompts, and then personalizing the template using a concept fusion strategy. The fusion strategy incorporates the appearance of the target concepts into the template image while retaining its structural details. The results indicate that our method can generate multiple custom concepts with higher identity fidelity compared to alternative approaches. Furthermore, the method is shown to seamlessly handle more than two concepts and closely follow the semantic meaning of the input prompt without blending appearances across different subjects., Comment: CVPR 2024