Search

The discrepancies between theoretical and observed spectra, and the systematic differences between various spectroscopic parameter estimates, complicate the determination of atmospheric parameters of M-type stars. In this work, we present an empirical sample of 5105 M-type star spectra with homogeneous atmospheric parameter labels through stellar-label transfer and sample cleaning. We addressed systematic discrepancies in spectroscopic parameter estimates by adopting recent results for Gaia EDR3 stars as a reference standard. Then, we used a density-based spatial clustering of applications with noise to remove unreliable samples in each subgrid of parameters. To confirm the reliability of the stellar labels, a 5-layer neural network was utilized, randomly partitioning the samples into training and testing sets. The standard deviations between the predicted and actual values in the testing set are 14 K for Teff , 0.06 dex for log g, and 0.05 dex for [M/H], respectively. In addition, we conducted an internal cross-validation to enhance validation and obtained precisions of 11 K, 0.05 dex, and 0.05 dex for Teff , log g, and [M/H], respectively. A grid of 1365 high Signal-to-Noise ratio (S/N) spectra and their labels, selected from the empirical sample, was utilized in the stellar parameter pipeline for M-Type stars (LASPM) of the Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST), producing an almost seamless Kiel distribution diagram for LAMOST DR10 and DR11 data. The atmospheric parameters for M-type stars from LAMOST DR11 show improved precision compared to the data from DR9, with improvements (for spectra with S/N higher than 10) from 118 to 67 K in Teff , 0.2 to 0.07 dex in log g, and 0.29 to 0.14 dex in [M/H]., Comment: 28 pages, 23 figures, Journal

In this work, we consider the target detection problem in a multistatic integrated sensing and communication (ISAC) scenario characterized by the cell-free MIMO communication network deployment, where multiple radio units (RUs) in the network cooperate with each other for the sensing task. By exploiting the angle resolution from multiple arrays deployed in the network and the delay resolution from the communication signals, i.e., orthogonal frequency division multiplexing (OFDM) signals, we formulate a cooperative sensing problem with coherent data fusion of multiple RUs' observations and propose a sparse Bayesian learning (SBL)-based method, where the global coordinates of target locations are directly detected. Intensive numerical results indicate promising target detection performance of the proposed SBL-based method. Additionally, a theoretical analysis of the considered cooperative multistatic sensing task is provided using the pairwise error probability (PEP) analysis, which can be used to provide design insights, e.g., illumination and beam patterns, for the considered problem., Comment: submitted to WCNC 2025

Large Language Models (LLMs) often suffer from catastrophic forgetting when learning multiple tasks sequentially, making continual learning (CL) essential for their dynamic deployment. Existing state-of-the-art (SOTA) methods, such as O-LoRA, typically focus on constructing orthogonality tasks to decouple parameter interdependence from various domains.In this paper, we reveal that building non-collision parameters is a more critical factor in addressing CL challenges. Our theoretical and experimental analyses demonstrate that non-collision parameters can provide better task orthogonality, which is a sufficient but unnecessary condition. Furthermore, knowledge from multiple domains will be preserved in non-collision parameter subspaces, making it more difficult to forget previously seen data. Leveraging this insight, we propose Non-collision Low-Rank Adaptation (N-LoRA), a simple yet effective approach leveraging low collision rates to enhance CL in LLMs. Experimental results on multiple CL benchmarks indicate that N-LoRA achieves superior performance (+2.9), higher task orthogonality (*4.1 times), and lower parameter collision (*58.1 times) than SOTA methods.

Floquet prethermalization is observed in periodically driven quantum many-body systems where the system avoids heating and maintains a stable, non-equilibrium state, for extended periods. Here we introduce a novel quantum control method using off-resonance and short-angle excitation to significantly extend Floquet prethermal lifetimes. This is demonstrated on randomly positioned, dipolar-coupled, 13C nuclear spins in diamond, but the methodology is broadly applicable. We achieve a lifetime $T_2'~800 s at 100 K while tracking the transition to the prethermal state quasi-continuously. This corresponds to a >533,000-fold extension over the bare spin lifetime without prethermalization, and constitutes a new record both in terms of absolute lifetime as well as the total number of Floquet pulses applied (here exceeding 7 million). Using Laplace inversion, we develop a new form of noise spectroscopy that provides insights into the origin of the lifetime extension. Finally, we demonstrate applications of these extended lifetimes in long-time, reinitialization-free quantum sensing of time-varying magnetic fields continuously for ~10 minutes at room temperature. Our work facilitates new opportunities for stabilizing driven quantum systems through Floquet control, and opens novel applications for continuously interrogated, long-time responsive quantum sensors., Comment: 6 pages, 4 figures

Continuous phase modulation (CPM) has extensive applications in wireless communications due to its high spectral and power efficiency. However, its nonlinear characteristics pose significant challenges for detection in frequency selective fading channels. This paper proposes an iterative receiver tailored for the detection of CPM signals over frequency selective fading channels. This design leverages the factor graph framework to integrate equalization, demodulation, and decoding functions. The equalizer employs the unitary approximate message passing (UAMP) algorithm, while the unitary transformation is implemented using the fast Fourier transform (FFT) with the aid of a cyclic prefix (CP), thereby achieving low computational complexity while with high performance. For CPM demodulation and channel decoding, with belief propagation (BP), we design a message passing-based maximum a posteriori (MAP) algorithm, and the message exchange between the demodulator, decoder and equalizer is elaborated. With proper message passing schedules, the receiver can achieve fast convergence. Simulation results show that compared with existing turbo receivers, the proposed receiver delivers significant performance enhancement with low computational complexity.

Let $K$ be a simplicial complex, and let $\Delta_i^{up}(K)$ be the $i$-th up normalized Laplacian of $K$. Horak and Jost showed that the largest eigenvalue of $\Delta_i^{up}(K)$ is at most $i+2$, and characterized the equality case by the orientable or non-orientable circuits. In this paper, by using the balancedness of signed graphs, we show that $\Delta_i^{up}(K)$ has an eigenvalue $i+2$ if and only if $K$ has an $(i+1)$-path connected component $K'$ such that the $i$-th signed incidence graph $B_i(K')$ is balanced, which implies Horak and Jost's characterization. We also characterize the multiplicity of $i+2$ as an eigenvalue of $\Delta_i^{up}(K)$, which generalizes the corresponding result in graph case. Finally we gave some classes of infinitely many simplicial complexes $K$ with $\Delta_i^{up}(K)$ having an eigenvalue $i+2$ by using wedge, Cartesian product and duplication of motifs., Comment: arXiv admin note: substantial text overlap with arXiv:2405.19078

This paper propels creative control in generative visual AI by allowing users to "select". Departing from traditional text or sketch-based methods, we for the first time allow users to choose visual concepts by parts for their creative endeavors. The outcome is fine-grained generation that precisely captures selected visual concepts, ensuring a holistically faithful and plausible result. To achieve this, we first parse objects into parts through unsupervised feature clustering. Then, we encode parts into text tokens and introduce an entropy-based normalized attention loss that operates on them. This loss design enables our model to learn generic prior topology knowledge about object's part composition, and further generalize to novel part compositions to ensure the generation looks holistically faithful. Lastly, we employ a bottleneck encoder to project the part tokens. This not only enhances fidelity but also accelerates learning, by leveraging shared knowledge and facilitating information exchange among instances. Visual results in the paper and supplementary material showcase the compelling power of PartCraft in crafting highly customized, innovative creations, exemplified by the "charming" and creative birds. Code is released at https://github.com/kamwoh/partcraft., Comment: ECCV 2024. arXiv admin note: substantial text overlap with arXiv:2311.15477

This paper, for the first time, marries large foundation models with human sketch understanding. We demonstrate what this brings -- a paradigm shift in terms of generalised sketch representation learning (e.g., classification). This generalisation happens on two fronts: (i) generalisation across unknown categories (i.e., open-set), and (ii) generalisation traversing abstraction levels (i.e., good and bad sketches), both being timely challenges that remain unsolved in the sketch literature. Our design is intuitive and centred around transferring the already stellar generalisation ability of CLIP to benefit generalised learning for sketches. We first "condition" the vanilla CLIP model by learning sketch-specific prompts using a novel auxiliary head of raster to vector sketch conversion. This importantly makes CLIP "sketch-aware". We then make CLIP acute to the inherently different sketch abstraction levels. This is achieved by learning a codebook of abstraction-specific prompt biases, a weighted combination of which facilitates the representation of sketches across abstraction levels -- low abstract edge-maps, medium abstract sketches in TU-Berlin, and highly abstract doodles in QuickDraw. Our framework surpasses popular sketch representation learning algorithms in both zero-shot and few-shot setups and in novel settings across different abstraction boundaries., Comment: ECCV 2024

This paper investigates radar-assisted user acquisition for downlink multi-user multiple-input multiple-output (MIMO) transmission using Orthogonal Frequency Division Multiplexing (OFDM) signals. Specifically, we formulate a concise mathematical model for the user acquisition problem, where each user is characterized by its delay and beamspace response. Therefore, we propose a two-stage method for user acquisition, where the Multiple Signal Classification (MUSIC) algorithm is adopted for delay estimation, and then a least absolute shrinkage and selection operator (LASSO) is applied for estimating the user response in the beamspace. Furthermore, we also provide a comprehensive performance analysis of the considered problem based on the pair-wise error probability (PEP). Particularly, we show that the rank and the geometric mean of non-zero eigenvalues of the squared beamspace difference matrix determines the user acquisition performance. More importantly, we reveal that simultaneously probing multiple beams outperforms concentrating power on a specific beam direction in each time slot under the power constraint, when only limited OFDM symbols are transmitted. Our numerical results confirm our conclusions and also demonstrate a promising acquisition performance of the proposed two-stage method.

In this paper, we delve into the intricate dynamics of Fine-Grained Sketch-Based Image Retrieval (FG-SBIR) by addressing a critical yet overlooked aspect -- the choice of viewpoint during sketch creation. Unlike photo systems that seamlessly handle diverse views through extensive datasets, sketch systems, with limited data collected from fixed perspectives, face challenges. Our pilot study, employing a pre-trained FG-SBIR model, highlights the system's struggle when query-sketches differ in viewpoint from target instances. Interestingly, a questionnaire however shows users desire autonomy, with a significant percentage favouring view-specific retrieval. To reconcile this, we advocate for a view-aware system, seamlessly accommodating both view-agnostic and view-specific tasks. Overcoming dataset limitations, our first contribution leverages multi-view 2D projections of 3D objects, instilling cross-modal view awareness. The second contribution introduces a customisable cross-modal feature through disentanglement, allowing effortless mode switching. Extensive experiments on standard datasets validate the effectiveness of our method., Comment: Accepted in European Conference on Computer Vision (ECCV) 2024

Existing fine-grained hashing methods typically lack code interpretability as they compute hash code bits holistically using both global and local features. To address this limitation, we propose ConceptHash, a novel method that achieves sub-code level interpretability. In ConceptHash, each sub-code corresponds to a human-understandable concept, such as an object part, and these concepts are automatically discovered without human annotations. Specifically, we leverage a Vision Transformer architecture and introduce concept tokens as visual prompts, along with image patch tokens as model inputs. Each concept is then mapped to a specific sub-code at the model output, providing natural sub-code interpretability. To capture subtle visual differences among highly similar sub-categories (e.g., bird species), we incorporate language guidance to ensure that the learned hash codes are distinguishable within fine-grained object classes while maintaining semantic alignment. This approach allows us to develop hash codes that exhibit similarity within families of species while remaining distinct from species in other families. Extensive experiments on four fine-grained image retrieval benchmarks demonstrate that ConceptHash outperforms previous methods by a significant margin, offering unique sub-code interpretability as an additional benefit. Code at: https://github.com/kamwoh/concepthash., Comment: CVPRW 2024 - FGVC11 best paper award

This paper introduces a novel approach to sketch colourisation, inspired by the universal childhood activity of colouring and its professional applications in design and story-boarding. Striking a balance between precision and convenience, our method utilises region masks and colour palettes to allow intuitive user control, steering clear of the meticulousness of manual colour assignments or the limitations of textual prompts. By strategically combining ControlNet and staged generation, incorporating Stable Diffusion v1.5, and leveraging BLIP-2 text prompts, our methodology facilitates faithful image generation and user-directed colourisation. Addressing challenges of local and global consistency, we employ inventive solutions such as an inversion scheme, guided sampling, and a self-attention mechanism with a scaling factor. The resulting tool is not only fast and training-free but also compatible with consumer-grade Nvidia RTX 4090 Super GPUs, making it a valuable asset for both creative professionals and enthusiasts in various fields. Project Page: \url{https://chaitron.github.io/SketchDeco/}

We propose SketchINR, to advance the representation of vector sketches with implicit neural models. A variable length vector sketch is compressed into a latent space of fixed dimension that implicitly encodes the underlying shape as a function of time and strokes. The learned function predicts the $xy$ point coordinates in a sketch at each time and stroke. Despite its simplicity, SketchINR outperforms existing representations at multiple tasks: (i) Encoding an entire sketch dataset into a fixed size latent vector, SketchINR gives $60\times$ and $10\times$ data compression over raster and vector sketches, respectively. (ii) SketchINR's auto-decoder provides a much higher-fidelity representation than other learned vector sketch representations, and is uniquely able to scale to complex vector sketches such as FS-COCO. (iii) SketchINR supports parallelisation that can decode/render $\sim$$100\times$ faster than other learned vector representations such as SketchRNN. (iv) SketchINR, for the first time, emulates the human ability to reproduce a sketch with varying abstraction in terms of number and complexity of strokes. As a first look at implicit sketches, SketchINR's compact high-fidelity representation will support future work in modelling long and complex sketches., Comment: CVPR 2024

In this paper, we explore the unique modality of sketch for explainability, emphasising the profound impact of human strokes compared to conventional pixel-oriented studies. Beyond explanations of network behavior, we discern the genuine implications of explainability across diverse downstream sketch-related tasks. We propose a lightweight and portable explainability solution -- a seamless plugin that integrates effortlessly with any pre-trained model, eliminating the need for re-training. Demonstrating its adaptability, we present four applications: highly studied retrieval and generation, and completely novel assisted drawing and sketch adversarial attacks. The centrepiece to our solution is a stroke-level attribution map that takes different forms when linked with downstream tasks. By addressing the inherent non-differentiability of rasterisation, we enable explanations at both coarse stroke level (SLA) and partial stroke level (P-SLA), each with its advantages for specific downstream tasks., Comment: CVPR 2024

This paper unravels the potential of sketches for diffusion models, addressing the deceptive promise of direct sketch control in generative AI. We importantly democratise the process, enabling amateur sketches to generate precise images, living up to the commitment of "what you sketch is what you get". A pilot study underscores the necessity, revealing that deformities in existing models stem from spatial-conditioning. To rectify this, we propose an abstraction-aware framework, utilising a sketch adapter, adaptive time-step sampling, and discriminative guidance from a pre-trained fine-grained sketch-based image retrieval model, working synergistically to reinforce fine-grained sketch-photo association. Our approach operates seamlessly during inference without the need for textual prompts; a simple, rough sketch akin to what you and I can create suffices! We welcome everyone to examine results presented in the paper and its supplementary. Contributions include democratising sketch control, introducing an abstraction-aware framework, and leveraging discriminative guidance, validated through extensive experiments., Comment: Accepted in CVPR 2024. Project page available at https://subhadeepkoley.github.io/StableSketching

Two primary input modalities prevail in image retrieval: sketch and text. While text is widely used for inter-category retrieval tasks, sketches have been established as the sole preferred modality for fine-grained image retrieval due to their ability to capture intricate visual details. In this paper, we question the reliance on sketches alone for fine-grained image retrieval by simultaneously exploring the fine-grained representation capabilities of both sketch and text, orchestrating a duet between the two. The end result enables precise retrievals previously unattainable, allowing users to pose ever-finer queries and incorporate attributes like colour and contextual cues from text. For this purpose, we introduce a novel compositionality framework, effectively combining sketches and text using pre-trained CLIP models, while eliminating the need for extensive fine-grained textual descriptions. Last but not least, our system extends to novel applications in composed image retrieval, domain attribute transfer, and fine-grained generation, providing solutions for various real-world scenarios., Comment: Accepted in CVPR 2024. Project page available at https://subhadeepkoley.github.io/Sketch2Word

In this paper, we propose a novel abstraction-aware sketch-based image retrieval framework capable of handling sketch abstraction at varied levels. Prior works had mainly focused on tackling sub-factors such as drawing style and order, we instead attempt to model abstraction as a whole, and propose feature-level and retrieval granularity-level designs so that the system builds into its DNA the necessary means to interpret abstraction. On learning abstraction-aware features, we for the first-time harness the rich semantic embedding of pre-trained StyleGAN model, together with a novel abstraction-level mapper that deciphers the level of abstraction and dynamically selects appropriate dimensions in the feature matrix correspondingly, to construct a feature matrix embedding that can be freely traversed to accommodate different levels of abstraction. For granularity-level abstraction understanding, we dictate that the retrieval model should not treat all abstraction-levels equally and introduce a differentiable surrogate Acc.@q loss to inject that understanding into the system. Different to the gold-standard triplet loss, our Acc.@q loss uniquely allows a sketch to narrow/broaden its focus in terms of how stringent the evaluation should be - the more abstract a sketch, the less stringent (higher q). Extensive experiments depict our method to outperform existing state-of-the-arts in standard SBIR tasks along with challenging scenarios like early retrieval, forensic sketch-photo matching, and style-invariant retrieval., Comment: Accepted in CVPR 2024. Project page available at https://subhadeepkoley.github.io/AbstractAway

This paper, for the first time, explores text-to-image diffusion models for Zero-Shot Sketch-based Image Retrieval (ZS-SBIR). We highlight a pivotal discovery: the capacity of text-to-image diffusion models to seamlessly bridge the gap between sketches and photos. This proficiency is underpinned by their robust cross-modal capabilities and shape bias, findings that are substantiated through our pilot studies. In order to harness pre-trained diffusion models effectively, we introduce a straightforward yet powerful strategy focused on two key aspects: selecting optimal feature layers and utilising visual and textual prompts. For the former, we identify which layers are most enriched with information and are best suited for the specific retrieval requirements (category-level or fine-grained). Then we employ visual and textual prompts to guide the model's feature extraction process, enabling it to generate more discriminative and contextually relevant cross-modal representations. Extensive experiments on several benchmark datasets validate significant performance improvements., Comment: Accepted in CVPR 2024. Project page available at https://subhadeepkoley.github.io/DiffusionZSSBIR

This paper studies improving the detector performance which considers the activity state (AS) temporal correlation of the user equipments (UEs) in the time domain under the uplink grant-free non-orthogonal multiple access (GF-NOMA) system. The Bernoulli Gaussian-Markov chain (BG-MC) probability model is used for exploiting both the sparsity and slow change characteristic of the AS of the UE. The GAMP Bernoulli Gaussian-Markov chain (GAMP-BG-MC) algorithm is proposed to improve the detector performance, which can utilize the bidirectional message passing between the neighboring time slots to fully exploit the temporally-correlated AS of the UE. Furthermore, the parameters of the BG-MC model can be updated adaptively during the estimation procedure with unknown system statistics. Simulation results show that the proposed algorithm can improve the detection accuracy compared with the existing methods while keeping the same order complexity.

Neural Radiance Field (NeRF) models have gained significant attention in the computer vision community in the recent past with state-of-the-art visual quality and produced impressive demonstrations. Since then, technopreneurs have sought to leverage NeRF models into a profitable business. Therefore, NeRF models make it worth the risk of plagiarizers illegally copying, re-distributing, or misusing those models. This paper proposes a comprehensive intellectual property (IP) protection framework for the NeRF model in both black-box and white-box settings, namely IPR-NeRF. In the black-box setting, a diffusion-based solution is introduced to embed and extract the watermark via a two-stage optimization process. In the white-box setting, a designated digital signature is embedded into the weights of the NeRF model by adopting the sign loss objective. Our extensive experiments demonstrate that not only does our approach maintain the fidelity (\ie, the rendering quality) of IPR-NeRF models, but it is also robust against both ambiguity and removal attacks compared to prior arts., Comment: Error on result tabulation of state of the art method which might cause misleading to readers

In Data Release 9 of LAMOST, we present measurements of v sin i for a total of 121,698 stars measured using the Medium Resolution Spectrograph (MRS) and 80,108 stars using the Low Resolution Spectrograph (LRS). These values were obtained through a chi^2 minimisation process, comparing LAMOST spectra with corresponding grids of synthetically broadened spectra. Due to the resolution and the spectral range of LAMOST, v sin i measurements are limited to stars with effective temperature (Teff) ranging from 5000 K to 8500 K for MRS and 7000 K to 9000 K for LRS. The detectable v sin i for MRS is set between 27 km/s and 350 km/s , and for LRS between 110 km/s and 350 km/s, This limitation is because the convolved reference spectra become less informative beyond 350 km/s. The intrinsic precisions of v sin i , determined from multi-epoch observations, is approximately 4.0 km/s for MRS and 10.0 km/s for LRS at signal-to-noise ratio (S/N) greater than 50. Our v sin i values show consistence with those from APOGEE17, displaying a scatter of 8.79 km/s. They are also in agreement with measurements from the Gaia DR3 and SUN catalogs. An observed trend in LAMOST MRS data is the decrease in v sin i with dropping Teff, particularly transiting around 7000 K for dwarfs and 6500 K for giants, primarily observed in stars with near-solar abundances., Comment: 13 pages, 16 figures

In this paper, by the representation theory of symmetric group, we give a decomposition of the Laplace operator (in matrix form) of a covering simplicial complex into the direct sum of some matrices, including the Laplace operator of the underlying simplicial complex. So, the spectrum of a covering simplicial complex can be expressed into a union of the spectrum of the underlying simplicial complex and the spectra of some other matrices, which implies a result of Horak and Jost. In particular, we show that the spectrum of a $2$-fold covering simplicial complex is the union the that of the underlying simplicial complex and that of an incidence-signed simplicial complex, which is an analog of Bilu and Linial's result on graphs. Finally we show that the dimension of the cohomology group of a covering simplicial complex is greater than or equal to that of the underlying simplicial complex.

In this paper, we democratise 3D content creation, enabling precise generation of 3D shapes from abstract sketches while overcoming limitations tied to drawing skills. We introduce a novel part-level modelling and alignment framework that facilitates abstraction modelling and cross-modal correspondence. Leveraging the same part-level decoder, our approach seamlessly extends to sketch modelling by establishing correspondence between CLIPasso edgemaps and projected 3D part regions, eliminating the need for a dataset pairing human sketches and 3D shapes. Additionally, our method introduces a seamless in-position editing process as a byproduct of cross-modal part-aligned modelling. Operating in a low-dimensional implicit space, our approach significantly reduces computational demands and processing time., Comment: CVPR 2024, Project Page: https://hmrishavbandy.github.io/doodle23d/

In this paper, we democratise caricature generation, empowering individuals to effortlessly craft personalised caricatures with just a photo and a conceptual sketch. Our objective is to strike a delicate balance between abstraction and identity, while preserving the creativity and subjectivity inherent in a sketch. To achieve this, we present Explicit Rank-1 Model Editing alongside single-image personalisation, selectively applying nuanced edits to cross-attention layers for a seamless merge of identity and style. Additionally, we propose Random Mask Reconstruction to enhance robustness, directing the model to focus on distinctive identity and style features. Crucially, our aim is not to replace artists but to eliminate accessibility barriers, allowing enthusiasts to engage in the artistry.

Creating multi-view wire art (MVWA), a static 3D sculpture with diverse interpretations from different viewpoints, is a complex task even for skilled artists. In response, we present DreamWire, an AI system enabling everyone to craft MVWA easily. Users express their vision through text prompts or scribbles, freeing them from intricate 3D wire organisation. Our approach synergises 3D B\'ezier curves, Prim's algorithm, and knowledge distillation from diffusion models or their variants (e.g., ControlNet). This blend enables the system to represent 3D wire art, ensuring spatial continuity and overcoming data scarcity. Extensive evaluation and analysis are conducted to shed insight on the inner workings of the proposed system, including the trade-off between connectivity and visual aesthetics., Comment: CVPR 2024

High-resolution image generation with Generative Artificial Intelligence (GenAI) has immense potential but, due to the enormous capital investment required for training, it is increasingly centralised to a few large corporations, and hidden behind paywalls. This paper aims to democratise high-resolution GenAI by advancing the frontier of high-resolution generation while remaining accessible to a broad audience. We demonstrate that existing Latent Diffusion Models (LDMs) possess untapped potential for higher-resolution image generation. Our novel DemoFusion framework seamlessly extends open-source GenAI models, employing Progressive Upscaling, Skip Residual, and Dilated Sampling mechanisms to achieve higher-resolution image generation. The progressive nature of DemoFusion requires more passes, but the intermediate results can serve as "previews", facilitating rapid prompt iteration., Comment: Project Page: https://ruoyidu.github.io/demofusion/demofusion.html

Reference-based video object segmentation is an emerging topic which aims to segment the corresponding target object in each video frame referred by a given reference, such as a language expression or a photo mask. However, language expressions can sometimes be vague in conveying an intended concept and ambiguous when similar objects in one frame are hard to distinguish by language. Meanwhile, photo masks are costly to annotate and less practical to provide in a real application. This paper introduces a new task of sketch-based video object segmentation, an associated benchmark, and a strong baseline. Our benchmark includes three datasets, Sketch-DAVIS16, Sketch-DAVIS17 and Sketch-YouTube-VOS, which exploit human-drawn sketches as an informative yet low-cost reference for video object segmentation. We take advantage of STCN, a popular baseline of semi-supervised VOS task, and evaluate what the most effective design for incorporating a sketch reference is. Experimental results show sketch is more effective yet annotation-efficient than other references, such as photo masks, language and scribble., Comment: BMVC 2023

Failure indexing is a longstanding crux in software testing and debugging, the goal of which is to automatically divide failures (e.g., failed test cases) into distinct groups according to the culprit root causes, as such multiple faults in a faulty program can be handled independently and simultaneously. This community has long been plagued by two challenges: 1) The effectiveness of division is still far from promising. Existing techniques only employ a limited source of run-time data (e.g., code coverage) to be failure proximity, which typically delivers unsatisfactory results. 2) The outcome can be hardly comprehensible. A developer who receives the failure indexing result does not know why all failures should be divided the way they are. This leads to difficulties for developers to be convinced by the result, which in turn affects the adoption of the results. To tackle these challenges, in this paper, we propose SURE, a viSUalized failuRe indExing approach using the program memory spectrum. We first collect the run-time memory information at preset breakpoints during the execution of failed test cases, and transform it into human-friendly images (called program memory spectrum, PMS). Then, any pair of PMS images that serve as proxies for two failures is fed to a trained Siamese convolutional neural network, to predict the likelihood of them being triggered by the same fault. Results demonstrate the effectiveness of SURE: It achieves 101.20% and 41.38% improvements in faults number estimation, as well as 105.20% and 35.53% improvements in clustering, compared with the state-of-the-art technique in this field, in simulated and real-world environments, respectively. Moreover, we carry out a human study to quantitatively evaluate the comprehensibility of PMS, revealing that this novel type of representation can help developers better comprehend failure indexing results., Comment: Due to the limitation "The abstract field cannot be longer than 1,920 characters", the abstract here is shorter than that in the PDF file

In this paper we investigate Ramanujan hypergraphs by using hypergraph coverings. We first show that the spectrum of a $k$-fold covering $\bar{H}$ of a connected hypergraph $H$ contains the spectrum of $H$, and that it is the union of the spectrum of $H$ and the spectrum of an incidence-signed hypergraph with $H$ as underlying hypergraph if $k=2$, which generalizes Bilu-Linial result on graph coverings. We give a lower bound for the second largest eigenvalue of a $d$-regular hypergraph by universal cover, which generalizes Alon-Boppana bound on $d$-regular graphs and Feng-Li bound on $(d,r)$-regular hypergraphs. By using interlacing family of polynomials, we prove that every $(d,r)$-regular hypergraph has a right-sided Ramanujan $2$-covering, and has a left-sided Ramanujan $2$-covering if the roots of the matching polynomial of its incident graph satisfy some condition. By Ramanujan $2$-coverings, we prove the existence of some families of infinite many left-sided or right-sided $(d,r)$-regular Ramanujan hypergraphs under certain conditions on $d$ and $r$.

Artificial Intelligence Generated Content (AIGC) has shown remarkable progress in generating realistic images. However, in this paper, we take a step "backward" and address AIGC for the most rudimentary visual modality of human sketches. Our objective is on the creative nature of sketches, and that creative sketching should take the form of an interactive process. We further enable text to drive the sketch ideation process, allowing creativity to be freely defined, while simultaneously tackling the challenge of "I can't sketch". We present a method to generate controlled sketches using a text-conditioned diffusion model trained on pixel representations of images. Our proposed approach, referred to as SketchDreamer, integrates a differentiable rasteriser of Bezier curves that optimises an initial input to distil abstract semantic knowledge from a pretrained diffusion model. We utilise Score Distillation Sampling to learn a sketch that aligns with a given caption, which importantly enable both text and sketch to interact with the ideation process. Our objective is to empower non-professional users to create sketches and, through a series of optimisation processes, transform a narrative into a storyboard by expanding the text prompt while making minor adjustments to the sketch input. Through this work, we hope to aspire the way we create visual content, democratise the creative process, and inspire further research in enhancing human creativity in AIGC. The code is available at \url{https://github.com/WinKawaks/SketchDreamer}., Comment: BMVC 2023

We present the analysis of 16 classical T Taur stars using LAMOST and TESS data, investigating spectral properties, photometric variations, and mass-accretion rates. All 16 stars exhibit emissions in H$\alpha$ lines, from which the average mass-accretion rate of $1.76\times10^{-9}~M_{\odot}yr^{-1}$ is derived. Two of the stars, DL Tau and Haro 6-13, show mass-accretion bursts simultaneously in TESS, ASAS-SN, and/or ZTF survey. Based on these observations, we find that the mass-accretion rates of DL Tau and Haro 6-13 reach their maximums of $2.5 \times 10^{-8}~M_{\odot}yr^{-1}$ and $2 \times 10^{-10}~M_{\odot}yr^{-1}$ during the TESS observation, respectively. We detect thirteen flares among these stars. The flare frequency distribution shows that the CTTSs' flare activity is not only dominated by strong flares with high energy but much more active than those of solar-type and young low-mass stars. By comparing the variability classes reported in the literature, we find that the transition timescale between different classes of variability in CTTSs, such as from Stochastic (S) to Bursting (B) or from quasi-periodic symmetric (QPS) to quasi-periodic dipping (QPD), may range from 1.6 to 4 years. We observe no significant correlation between inclination and mass-accretion rates derived from the emission indicators. This suggests that inner disk properties may be more important than that of outer disk. Finally, we find a relatively significant positive correlation between the asymmetric metric "M" and the cold disk inclination compared to the literature. A weak negative correlation between the periodicity metric "Q" value and inclination has been also found., Comment: 39 pages, 22 figures, 8 tables

3D shape modeling is labor-intensive, time-consuming, and requires years of expertise. To facilitate 3D shape modeling, we propose a 3D shape generation network that takes a 3D VR sketch as a condition. We assume that sketches are created by novices without art training and aim to reconstruct geometrically realistic 3D shapes of a given category. To handle potential sketch ambiguity, our method creates multiple 3D shapes that align with the original sketch's structure. We carefully design our method, training the model step-by-step and leveraging multi-modal 3D shape representation to support training with limited training data. To guarantee the realism of generated 3D shapes we leverage the normalizing flow that models the distribution of the latent space of 3D shapes. To encourage the fidelity of the generated 3D shapes to an input sketch, we propose a dedicated loss that we deploy at different stages of the training process. The code is available at https://github.com/Rowl1ng/3Dsketch2shape., Comment: Accepted by ICCV 2023

Recently, text-guided 3D generative methods have made remarkable advancements in producing high-quality textures and geometry, capitalizing on the proliferation of large vision-language and image diffusion models. However, existing methods still struggle to create high-fidelity 3D head avatars in two aspects: (1) They rely mostly on a pre-trained text-to-image diffusion model whilst missing the necessary 3D awareness and head priors. This makes them prone to inconsistency and geometric distortions in the generated avatars. (2) They fall short in fine-grained editing. This is primarily due to the inherited limitations from the pre-trained 2D image diffusion models, which become more pronounced when it comes to 3D head avatars. In this work, we address these challenges by introducing a versatile coarse-to-fine pipeline dubbed HeadSculpt for crafting (i.e., generating and editing) 3D head avatars from textual prompts. Specifically, we first equip the diffusion model with 3D awareness by leveraging landmark-based control and a learned textual embedding representing the back view appearance of heads, enabling 3D-consistent head avatar generations. We further propose a novel identity-aware editing score distillation strategy to optimize a textured mesh with a high-resolution differentiable rendering technique. This enables identity preservation while following the editing instruction. We showcase HeadSculpt's superior fidelity and editing capabilities through comprehensive experiments and comparisons with existing methods., Comment: Webpage: https://brandonhan.uk/HeadSculpt/