Search

Natural Language Inference (NLI) is a task within Natural Language Processing (NLP) that holds value for various AI applications. However, there have been limited studies on Natural Language Inference in Vietnamese that explore the concept of joint models. Therefore, we conducted experiments using various combinations of contextualized language models (CLM) and neural networks. We use CLM to create contextualized work presentations and use Neural Networks for classification. Furthermore, we have evaluated the strengths and weaknesses of each joint model and identified the model failure points in the Vietnamese context. The highest F1 score in this experiment, up to 82.78% in the benchmark dataset (ViNLI). By conducting experiments with various models, the most considerable size of the CLM is XLM-R (355M). That combination has consistently demonstrated superior performance compared to fine-tuning strong pre-trained language models like PhoBERT (+6.58%), mBERT (+19.08%), and XLM-R (+0.94%) in terms of F1-score. This article aims to introduce a novel approach or model that attains improved performance for Vietnamese NLI. Overall, we find that the joint approach of CLM and neural networks is simple yet capable of achieving high-quality performance, which makes it suitable for applications that require efficient resource utilization.

Medical eye-tracking data is an important information source for understanding how radiologists visually interpret medical images. This information not only improves the accuracy of deep learning models for X-ray analysis but also their interpretability, enhancing transparency in decision-making. However, the current eye-tracking data is dispersed, unprocessed, and ambiguous, making it difficult to derive meaningful insights. Therefore, there is a need to create a new dataset with more focus and purposeful eyetracking data, improving its utility for diagnostic applications. In this work, we propose a refinement method inspired by the target-present visual search challenge: there is a specific finding and fixations are guided to locate it. After refining the existing eye-tracking datasets, we transform them into a curated visual search dataset, called GazeSearch, specifically for radiology findings, where each fixation sequence is purposefully aligned to the task of locating a particular finding. Subsequently, we introduce a scan path prediction baseline, called ChestSearch, specifically tailored to GazeSearch. Finally, we employ the newly introduced GazeSearch as a benchmark to evaluate the performance of current state-of-the-art methods, offering a comprehensive assessment for visual search in the medical imaging domain., Comment: Aceepted WACV 2025

Endovascular surgical tool reconstruction represents an important factor in advancing endovascular tool navigation, which is an important step in endovascular surgery. However, the lack of publicly available datasets significantly restricts the development and validation of novel machine learning approaches. Moreover, due to the need for specialized equipment such as biplanar scanners, most of the previous research employs monoplanar fluoroscopic technologies, hence only capturing the data from a single view and significantly limiting the reconstruction accuracy. To bridge this gap, we introduce Guide3D, a bi-planar X-ray dataset for 3D reconstruction. The dataset represents a collection of high resolution bi-planar, manually annotated fluoroscopic videos, captured in real-world settings. Validating our dataset within a simulated environment reflective of clinical settings confirms its applicability for real-world applications. Furthermore, we propose a new benchmark for guidewrite shape prediction, serving as a strong baseline for future work. Guide3D not only addresses an essential need by offering a platform for advancing segmentation and 3D reconstruction techniques but also aids the development of more accurate and efficient endovascular surgery interventions. Our project is available at https://airvlab.github.io/guide3d/., Comment: Accepted to ACCV 2024

Object tracking, especially animal tracking, is one of the key topics that attract a lot of attention due to its benefits of animal behavior understanding and monitoring. Recent state-of-the-art tracking methods are founded on deep learning architectures for object detection, appearance feature extraction and track association. Despite the good tracking performance, these methods are trained and evaluated on common objects such as human and cars. To perform on the animal, there is a need to create large datasets of different types in multiple conditions. The dataset construction comprises of data collection and data annotation. In this work, we put more focus on the latter task. Particularly, we renovate the well-known tool, LabelMe, so as to assist common user with or without in-depth knowledge about computer science to annotate the data with less effort. The new tool named as TrackMe inherits the simplicity, high compatibility with varied systems, minimal hardware requirement and convenient feature utilization from the predecessor. TrackMe is an upgraded version with essential features for multiple object tracking annotation.

Text-based VQA is a challenging task that requires machines to use scene texts in given images to yield the most appropriate answer for the given question. The main challenge of text-based VQA is exploiting the meaning and information from scene texts. Recent studies tackled this challenge by considering the spatial information of scene texts in images via embedding 2D coordinates of their bounding boxes. In this study, we follow the definition of meaning from linguistics to introduce a novel method that effectively exploits the information from scene texts written in Vietnamese. Experimental results show that our proposed method obtains state-of-the-art results on two large-scale Vietnamese Text-based VQA datasets. The implementation can be found at this link., Comment: PACLIC 2024

Object tracking is a fundamental task in computer vision, requiring the localization of objects of interest across video frames. Diffusion models have shown remarkable capabilities in visual generation, making them well-suited for addressing several requirements of the tracking problem. This work proposes a novel diffusion-based methodology to formulate the tracking task. Firstly, their conditional process allows for injecting indications of the target object into the generation process. Secondly, diffusion mechanics can be developed to inherently model temporal correspondences, enabling the reconstruction of actual frames in video. However, existing diffusion models rely on extensive and unnecessary mapping to a Gaussian noise domain, which can be replaced by a more efficient and stable interpolation process. Our proposed interpolation mechanism draws inspiration from classic image-processing techniques, offering a more interpretable, stable, and faster approach tailored specifically for the object tracking task. By leveraging the strengths of diffusion models while circumventing their limitations, our Diffusion-based INterpolation TrackeR (DINTR) presents a promising new paradigm and achieves a superior multiplicity on seven benchmarks across five indicator representations., Comment: Accepted at NeurIPS 2024

Despite recent progress, Multi-Object Tracking (MOT) continues to face significant challenges, particularly its dependence on prior knowledge and predefined categories, complicating the tracking of unfamiliar objects. Generic Multiple Object Tracking (GMOT) emerges as a promising solution, requiring less prior information. Nevertheless, existing GMOT methods, primarily designed as OneShot-GMOT, rely heavily on initial bounding boxes and often struggle with variations in viewpoint, lighting, occlusion, and scale. To overcome the limitations inherent in both MOT and GMOT when it comes to tracking objects with specific generic attributes, we introduce Grounded-GMOT, an innovative tracking paradigm that enables users to track multiple generic objects in videos through natural language descriptors. Our contributions begin with the introduction of the G2MOT dataset, which includes a collection of videos featuring a wide variety of generic objects, each accompanied by detailed textual descriptions of their attributes. Following this, we propose a novel tracking method, KAM-SORT, which not only effectively integrates visual appearance with motion cues but also enhances the Kalman filter. KAM-SORT proves particularly advantageous when dealing with objects of high visual similarity from the same generic category in GMOT scenarios. Through comprehensive experiments, we demonstrate that Grounded-GMOT outperforms existing OneShot-GMOT approaches. Additionally, our extensive comparisons between various trackers highlight KAM-SORT's efficacy in GMOT, further establishing its significance in the field. Project page: https://UARK-AICV.github.io/G2MOT. The source code and dataset will be made publicly available., Comment: ACCV 2024, main track, oral presentation

Chick sexing, the process of determining the gender of day-old chicks, is a critical task in the poultry industry due to the distinct roles that each gender plays in production. While effective traditional methods achieve high accuracy, color, and wing feather sexing is exclusive to specific breeds, and vent sexing is invasive and requires trained experts. To address these challenges, we propose a novel approach inspired by facial gender classification techniques in humans: facial chick sexing. This new method does not require expert knowledge and aims to reduce training time while enhancing animal welfare by minimizing chick manipulation. We develop a comprehensive system for training and inference that includes data collection, facial and keypoint detection, facial alignment, and classification. We evaluate our model on two sets of images: Cropped Full Face and Cropped Middle Face, both of which maintain essential facial features of the chick for further analysis. Our experiment demonstrates the promising viability, with a final accuracy of 81.89%, of this approach for future practices in chick sexing by making them more universally applicable.

Amodal Instance Segmentation (AIS) presents an intriguing challenge, including the segmentation prediction of both visible and occluded parts of objects within images. Previous methods have often relied on shape prior information gleaned from training data to enhance amodal segmentation. However, these approaches are susceptible to overfitting and disregard object category details. Recent advancements highlight the potential of conditioned diffusion models, pretrained on extensive datasets, to generate images from latent space. Drawing inspiration from this, we propose AISDiff with a Diffusion Shape Prior Estimation (DiffSP) module. AISDiff begins with the prediction of the visible segmentation mask and object category, alongside occlusion-aware processing through the prediction of occluding masks. Subsequently, these elements are inputted into our DiffSP module to infer the shape prior of the object. DiffSP utilizes conditioned diffusion models pretrained on extensive datasets to extract rich visual features for shape prior estimation. Additionally, we introduce the Shape Prior Amodal Predictor, which utilizes attention-based feature maps from the shape prior to refine amodal segmentation. Experiments across various AIS benchmarks demonstrate the effectiveness of our AISDiff., Comment: ACCV2024; Project page: https://uark-aicv.github.io/AISDiff

Vision language models have played a key role in extracting meaningful features for various robotic applications. Among these, Contrastive Language-Image Pretraining (CLIP) is widely used in robotic tasks that require both vision and natural language understanding. However, CLIP was trained solely on static images paired with text prompts and has not yet been fully adapted for robotic tasks involving dynamic actions. In this paper, we introduce Robotic-CLIP to enhance robotic perception capabilities. We first gather and label large-scale action data, and then build our Robotic-CLIP by fine-tuning CLIP on 309,433 videos (~7.4 million frames) of action data using contrastive learning. By leveraging action data, Robotic-CLIP inherits CLIP's strong image performance while gaining the ability to understand actions in robotic contexts. Intensive experiments show that our Robotic-CLIP outperforms other CLIP-based models across various language-driven robotic tasks. Additionally, we demonstrate the practical effectiveness of Robotic-CLIP in real-world grasping applications., Comment: 7 pages

While Multi-Object Tracking (MOT) has made substantial advancements, it is limited by heavy reliance on prior knowledge and limited to predefined categories. In contrast, Generic Multiple Object Tracking (GMOT), tracking multiple objects with similar appearance, requires less prior information about the targets but faces challenges with variants like viewpoint, lighting, occlusion, and resolution. Our contributions commence with the introduction of the \textbf{\text{Refer-GMOT dataset}} a collection of videos, each accompanied by fine-grained textual descriptions of their attributes. Subsequently, we introduce a novel text prompt-based open-vocabulary GMOT framework, called \textbf{\text{TP-GMOT}}, which can track never-seen object categories with zero training examples. Within \text{TP-GMOT} framework, we introduce two novel components: (i) {\textbf{\text{TP-OD}}, an object detection by a textual prompt}, for accurately detecting unseen objects with specific characteristics. (ii) Motion-Appearance Cost SORT \textbf{\text{MAC-SORT}}, a novel object association approach that adeptly integrates motion and appearance-based matching strategies to tackle the complex task of tracking multiple generic objects with high similarity. Our contributions are benchmarked on the \text{Refer-GMOT} dataset for GMOT task. Additionally, to assess the generalizability of the proposed \text{TP-GMOT} framework and the effectiveness of \text{MAC-SORT} tracker, we conduct ablation studies on the DanceTrack and MOT20 datasets for the MOT task. Our dataset, code, and models will be publicly available at: https://fsoft-aic.github.io/TP-GMOT

(abridged) Together with gravity, turbulence, and stellar feedback, magnetic fields (B-fields) are thought to play a critical role in the evolution of molecular clouds and star formation processes. We aim to map the morphology and measure the strength of B-fields of the nearby molecular cloud, rho Ophiuchus-A ($\rho$ Oph-A), and then to understand the role of B-fields in regulating star formation and shaping the cloud. We have analyzed the far-infrared (FIR) polarization of thermal dust emission observed by SOFIA/HAWC$+$ at 89 and 154 $\mu$m toward the densest part of $\rho$ Oph-A, which is irradiated by the nearby B3/4 star, Oph-S1. The cloud exhibits well-ordered B-fields with magnetic orientations mainly perpendicular to the ridge of the cloud toward the densest region and B-field strengths are in the range of 0.2-2.5 mG, using the Davis-Chandrasekhar-Fermi method. The B-fields are strongest at the densest part of the cloud, which is associated with the starless core SM1, and decreases toward the outskirts of the cloud. By calculating the map of the mass-to-flux ratio, Alfv\'en Mach number, and plasma $\beta$ parameter in $\rho$ Oph-A, we find that the cloud is predominantly magnetically sub-critical, sub-Alfv\'enic, which implies that the cloud is supported by strong B-fields that dominate over gravity, turbulence, and thermal gas energy. Measured B-field strengths at two densest subregions using other methods that account for the compressible mode are relatively lower than that measured with the DCF method but do not significantly change our conclusions on the roles of B-fields relative to gravity and turbulence on star formation. A virial analysis suggests that the cloud is gravitationally unbound. We find that B-fields are sufficiently strong to support the cloud against radiative feedback and to regulate the shape of the cloud., Comment: Accepted to A&A

Grasp detection is an essential task in robotics with various industrial applications. However, traditional methods often struggle with occlusions and do not utilize language for grasping. Incorporating natural language into grasp detection remains a challenging task and largely unexplored. To address this gap, we propose a new method for language-driven grasp detection with mask-guided attention by utilizing the transformer attention mechanism with semantic segmentation features. Our approach integrates visual data, segmentation mask features, and natural language instructions, significantly improving grasp detection accuracy. Our work introduces a new framework for language-driven grasp detection, paving the way for language-driven robotic applications. Intensive experiments show that our method outperforms other recent baselines by a clear margin, with a 10.0% success score improvement. We further validate our method in real-world robotic experiments, confirming the effectiveness of our approach., Comment: Accepted at IROS 2024

Language-driven grasp detection is a fundamental yet challenging task in robotics with various industrial applications. In this work, we present a new approach for language-driven grasp detection that leverages the concept of lightweight diffusion models to achieve fast inference time. By integrating diffusion processes with grasping prompts in natural language, our method can effectively encode visual and textual information, enabling more accurate and versatile grasp positioning that aligns well with the text query. To overcome the long inference time problem in diffusion models, we leverage the image and text features as the condition in the consistency model to reduce the number of denoising timesteps during inference. The intensive experimental results show that our method outperforms other recent grasp detection methods and lightweight diffusion models by a clear margin. We further validate our method in real-world robotic experiments to demonstrate its fast inference time capability., Comment: Accepted at IROS 2024

6-DoF grasp detection has been a fundamental and challenging problem in robotic vision. While previous works have focused on ensuring grasp stability, they often do not consider human intention conveyed through natural language, hindering effective collaboration between robots and users in complex 3D environments. In this paper, we present a new approach for language-driven 6-DoF grasp detection in cluttered point clouds. We first introduce Grasp-Anything-6D, a large-scale dataset for the language-driven 6-DoF grasp detection task with 1M point cloud scenes and more than 200M language-associated 3D grasp poses. We further introduce a novel diffusion model that incorporates a new negative prompt guidance learning strategy. The proposed negative prompt strategy directs the detection process toward the desired object while steering away from unwanted ones given the language input. Our method enables an end-to-end framework where humans can command the robot to grasp desired objects in a cluttered scene using natural language. Intensive experimental results show the effectiveness of our method in both benchmarking experiments and real-world scenarios, surpassing other baselines. In addition, we demonstrate the practicality of our approach in real-world robotic applications. Our project is available at https://airvlab.github.io/grasp-anything., Comment: Accepted at ECCV 2024

Dark matter may exist today in the form of ultraheavy composite bound states. Collisions between such dark matter states can release intense bursts of radiation that includes gamma-rays among the final products. Thus, indirect-detection signals of dark matter may include unconventional gamma-ray bursts. Such bursts may have been missed not necessarily because of their low arriving gamma-ray fluxes, but rather their briefness and rareness. We point out that intense bursts whose non-detection thus far are due to the latter can be detected in the near future with existing and planned facilities. In particular, we propose that, with slight experimental adjustments and suitable data analyses, imaging atmospheric Cherenkov telescopes (IACTs) and Pulsed All-sky Near-infrared and Optical Search for Extra-Terrestrial Intelligence (PANOSETI) are promising tools for detecting such rare, brief, but intense bursts. We also show that if we assume these bursts originate from collisions of dark matter states, IACTs and PANOSETI can probe a large dark matter parameter space beyond existing limits. Additionally, we present a concrete model of dark matter that produces bursts potentially detectable in these instruments.

Predicting human gaze behavior within computer vision is integral for developing interactive systems that can anticipate user attention, address fundamental questions in cognitive science, and hold implications for fields like human-computer interaction (HCI) and augmented/virtual reality (AR/VR) systems. Despite methodologies introduced for modeling human eye gaze behavior, applying these models to medical imaging for scanpath prediction remains unexplored. Our proposed system aims to predict eye gaze sequences from radiology reports and CXR images, potentially streamlining data collection and enhancing AI systems using larger datasets. However, predicting human scanpaths on medical images presents unique challenges due to the diverse nature of abnormal regions. Our model predicts fixation coordinates and durations critical for medical scanpath prediction, outperforming existing models in the computer vision community. Utilizing a two-stage training process and large publicly available datasets, our approach generates static heatmaps and eye gaze videos aligned with radiology reports, facilitating comprehensive analysis. We validate our approach by comparing its performance with state-of-the-art methods and assessing its generalizability among different radiologists, introducing novel strategies to model radiologists' search patterns during CXR image diagnosis. Based on the radiologist's evaluation, MedGaze can generate human-like gaze sequences with a high focus on relevant regions over the CXR images. It sometimes also outperforms humans in terms of redundancy and randomness in the scanpaths., Comment: Submitted to the Journal

Human-AI collaboration to identify and correct perceptual errors in chest radiographs has not been previously explored. This study aimed to develop a collaborative AI system, CoRaX, which integrates eye gaze data and radiology reports to enhance diagnostic accuracy in chest radiology by pinpointing perceptual errors and refining the decision-making process. Using public datasets REFLACX and EGD-CXR, the study retrospectively developed CoRaX, employing a large multimodal model to analyze image embeddings, eye gaze data, and radiology reports. The system's effectiveness was evaluated based on its referral-making process, the quality of referrals, and performance in collaborative diagnostic settings. CoRaX was tested on a simulated error dataset of 271 samples with 28% (93 of 332) missed abnormalities. The system corrected 21% (71 of 332) of these errors, leaving 7% (22 of 312) unresolved. The Referral-Usefulness score, indicating the accuracy of predicted regions for all true referrals, was 0.63 (95% CI 0.59, 0.68). The Total-Usefulness score, reflecting the diagnostic accuracy of CoRaX's interactions with radiologists, showed that 84% (237 of 280) of these interactions had a score above 0.40. In conclusion, CoRaX efficiently collaborates with radiologists to address perceptual errors across various abnormalities, with potential applications in the education and training of novice radiologists., Comment: Under Review in Journal

The development of Natural Language Processing (NLI) datasets and models has been inspired by innovations in annotation design. With the rapid development of machine learning models today, the performance of existing machine learning models has quickly reached state-of-the-art results on a variety of tasks related to natural language processing, including natural language inference tasks. By using a pre-trained model during the annotation process, it is possible to challenge current NLI models by having humans produce premise-hypothesis combinations that the machine model cannot correctly predict. To remain attractive and challenging in the research of natural language inference for Vietnamese, in this paper, we introduce the adversarial NLI dataset to the NLP research community with the name ViANLI. This data set contains more than 10K premise-hypothesis pairs and is built by a continuously adjusting process to obtain the most out of the patterns generated by the annotators. ViANLI dataset has brought many difficulties to many current SOTA models when the accuracy of the most powerful model on the test set only reached 48.4%. Additionally, the experimental results show that the models trained on our dataset have significantly improved the results on other Vietnamese NLI datasets.

Graph Neural Networks (GNNs) have achieved state-of-the-art results in node classification tasks. However, most improvements are in multi-class classification, with less focus on the cases where each node could have multiple labels. The first challenge in studying multi-label node classification is the scarcity of publicly available datasets. To address this, we collected and released three real-world biological datasets and developed a multi-label graph generator with tunable properties. We also argue that traditional notions of homophily and heterophily do not apply well to multi-label scenarios. Therefore, we define homophily and Cross-Class Neighborhood Similarity for multi-label classification and investigate $9$ collected multi-label datasets. Lastly, we conducted a large-scale comparative study with $8$ methods across nine datasets to evaluate current progress in multi-label node classification. We release our code at \url{https://github.com/Tianqi-py/MLGNC}.

This study introduces a first step for constructing a hybrid reduced-order models (ROMs) for segregated fluid-structure interaction in an Arbitrary Lagrangian-Eulerian (ALE) approach at a high Reynolds number using the Finite Volume Method (FVM). The ROM is driven by proper orthogonal decomposition (POD) with hybrid techniques that combines the classical Galerkin projection and two data-driven methods (radial basis networks , and neural networks/ long short term memory). Results demonstrate the ROM ability to accurately capture the physics of fluid-structure interaction phenomena. This approach is validated through a case study focusing on flow-induced vibration (FIV) of a pitch-plunge airfoil at a high Reynolds number 10000000., Comment: arXiv admin note: text overlap with arXiv:2305.13613

The Landau--Lifshitz--Bloch equation (LLBE) describes the evolution of magnetic spin field in a ferromagnet at high temperatures. We consider a viscous (pseudo-parabolic) regularisation of the LLBE for temperatures higher than the Curie temperature, which we call the $\epsilon$-LLBE. Variants of the $\epsilon$-LLBE are applicable to model pattern formation, phase transition, and heat conduction for non-simple materials, among other things. In this paper, we show well-posedness of the $\epsilon$-LLBE and the convergence of the solution $\boldsymbol{u}^\epsilon$ of the regularised equation to the solution $\boldsymbol{u}$ of the LLBE as $\epsilon\to 0^+$. As a by-product of our analysis, we show the existence and uniqueness of regular solution to the LLBE for temperatures higher than the Curie temperature. Furthermore, we propose a linear fully discrete conforming finite element scheme to approximate the solution of the $\epsilon$-LLBE. Error analysis is performed to show unconditional stability and optimal uniform-in-time convergence rate for the schemes. Several numerical simulations corroborate our theoretical results.

The ability of three-dimensional (3D) spheroid modeling to study the invasive behavior of breast cancer cells has drawn increased attention. The deep learning-based image processing framework is very effective at speeding up the cell morphological analysis process. Out-of-focus photos taken while capturing 3D cells under several z-slices, however, could negatively impact the deep learning model. In this work, we created a new algorithm to handle blurry images while preserving the stacked image quality. Furthermore, we proposed a unique training architecture that leverages consistency training to help reduce the bias of the model when dense-slice stacking is applied. Additionally, the model's stability is increased under the sparse-slice stacking effect by utilizing the self-training approach. The new blurring stacking technique and training flow are combined with the suggested architecture and self-training mechanism to provide an innovative yet easy-to-use framework. Our methods produced noteworthy experimental outcomes in terms of both quantitative and qualitative aspects.

To address this challenge, we introduce CattleFace-RGBT, a RGB-T Cattle Facial Landmark dataset consisting of 2,300 RGB-T image pairs, a total of 4,600 images. Creating a landmark dataset is time-consuming, but AI-assisted annotation can help. However, applying AI to thermal images is challenging due to suboptimal results from direct thermal training and infeasible RGB-thermal alignment due to different camera views. Therefore, we opt to transfer models trained on RGB to thermal images and refine them using our AI-assisted annotation tool following a semi-automatic annotation approach. Accurately localizing facial key points on both RGB and thermal images enables us to not only discern the cattle's respiratory signs but also measure temperatures to assess the animal's thermal state. To the best of our knowledge, this is the first dataset for the cattle facial landmark on RGB-T images. We conduct benchmarking of the CattleFace-RGBT dataset across various backbone architectures, with the objective of establishing baselines for future research, analysis, and comparison. The dataset and models are at https://github.com/UARK-AICV/CattleFace-RGBT-benchmark

Current video-language models (VLMs) rely extensively on instance-level alignment between video and language modalities, which presents two major limitations: (1) visual reasoning disobeys the natural perception that humans do in first-person perspective, leading to a lack of reasoning interpretation; and (2) learning is limited in capturing inherent fine-grained relationships between two modalities. In this paper, we take an inspiration from human perception and explore a compositional approach for egocentric video representation. We introduce HENASY (Hierarchical ENtities ASsemblY), which includes a spatiotemporal token grouping mechanism to explicitly assemble dynamically evolving scene entities through time and model their relationship for video representation. By leveraging compositional structure understanding, HENASY possesses strong interpretability via visual grounding with free-form text queries. We further explore a suite of multi-grained contrastive losses to facilitate entity-centric understandings. This comprises three alignment types: video-narration, noun-entity, verb-entities alignments. Our method demonstrates strong interpretability in both quantitative and qualitative experiments; while maintaining competitive performances on five downstream tasks via zero-shot transfer or as video/text representation, including video/text retrieval, action recognition, multi-choice query, natural language query, and moments query., Comment: Accepted to NeurIPS 2024

Increasing the throughput of the Transformer architecture, a foundational component used in numerous state-of-the-art models for vision and language tasks (e.g., GPT, LLaVa), is an important problem in machine learning. One recent and effective strategy is to merge token representations within Transformer models, aiming to reduce computational and memory requirements while maintaining accuracy. Prior works have proposed algorithms based on Bipartite Soft Matching (BSM), which divides tokens into distinct sets and merges the top k similar tokens. However, these methods have significant drawbacks, such as sensitivity to token-splitting strategies and damage to informative tokens in later layers. This paper presents a novel paradigm called PiToMe, which prioritizes the preservation of informative tokens using an additional metric termed the energy score. This score identifies large clusters of similar tokens as high-energy, indicating potential candidates for merging, while smaller (unique and isolated) clusters are considered as low-energy and preserved. Experimental findings demonstrate that PiToMe saved from 40-60\% FLOPs of the base models while exhibiting superior off-the-shelf performance on image classification (0.5\% average performance drop of ViT-MAE-H compared to 2.6\% as baselines), image-text retrieval (0.3\% average performance drop of CLIP on Flickr30k compared to 4.5\% as others), and analogously in visual questions answering with LLaVa-7B. Furthermore, PiToMe is theoretically shown to preserve intrinsic spectral properties of the original token space under mild conditions, Comment: Accepted at NeurIPS 2024

Multiple imputation (MI) models can be improved by including auxiliary covariates (AC), but their performance in high-dimensional data is not well understood. We aimed to develop and compare high-dimensional MI (HDMI) approaches using structured and natural language processing (NLP)-derived AC in studies with partially observed confounders. We conducted a plasmode simulation study using data from opioid vs. non-steroidal anti-inflammatory drug (NSAID) initiators (X) with observed serum creatinine labs (Z2) and time-to-acute kidney injury as outcome. We simulated 100 cohorts with a null treatment effect, including X, Z2, atrial fibrillation (U), and 13 other investigator-derived confounders (Z1) in the outcome generation. We then imposed missingness (MZ2) on 50% of Z2 measurements as a function of Z2 and U and created different HDMI candidate AC using structured and NLP-derived features. We mimicked scenarios where U was unobserved by omitting it from all AC candidate sets. Using LASSO, we data-adaptively selected HDMI covariates associated with Z2 and MZ2 for MI, and with U to include in propensity score models. The treatment effect was estimated following propensity score matching in MI datasets and we benchmarked HDMI approaches against a baseline imputation and complete case analysis with Z1 only. HDMI using claims data showed the lowest bias (0.072). Combining claims and sentence embeddings led to an improvement in the efficiency displaying the lowest root-mean-squared-error (0.173) and coverage (94%). NLP-derived AC alone did not perform better than baseline MI. HDMI approaches may decrease bias in studies with partially observed confounders where missingness depends on unobserved factors.

We introduce our project, AGNSTRONG (Active Galactic Nuclei and STaR fOrmation in Nearby Galaxies). Our research goals encompass investigating the kinematic properties of ionized and molecular gas outflows, understanding the impact of AGN feedback, and exploring the coevolution dynamics between AGN strength activity and star formation activity. We aim to conduct a thorough analysis to determine whether there is an increase or suppression in SFRs among targets with and without powerful relativistic jets. Our sample consists of 35 nearby AGNs with and without powerful relativistic jet detections. Utilizing sub-millimeter (sub-mm) continuum observations at 450 {\mu}m and 850 {\mu}m from SCUBA-2 at the James Clerk Maxwell Telescope, we determine star-formation rates (SFRs) for our sources using spectral energy distribution (SED) fitting models. Additionally, we employ high-quality, spatially resolved spectra from UV-optical to near-infrared bands obtained with the Double Spectrograph and Triple Spectrograph mounted on the 200-inch Hale telescope at Palomar Observatory to study their multiphase gas outflow properties. This paper presents an overview of our sample selection methodology, research strategy, and initial results of our project. We find that the SFRs determined without including the sub-mm data in the SED fitting are overestimated by approximately 0.08 dex compared to those estimated with the inclusion of sub-mm data. Additionally, we compare the estimated SFRs in our work with those traced by the 4000{\AA} break, as provided by the MPA-JHU catalog. We find that our determined SFRs are systematically higher than those traced by the 4000{\AA} break. Finally, we outline our future research plans., Comment: 13 pages, accepted for publication in The Astronomical Journal

Despite demonstrating superior rate-distortion (RD) performance, learning-based image compression (LIC) algorithms have been found to be vulnerable to malicious perturbations in recent studies. However, the adversarial attacks considered in existing literature remain divergent from real-world scenarios, both in terms of the attack direction and bitrate. Additionally, existing methods focus solely on empirical observations of the model vulnerability, neglecting to identify the origin of it. These limitations hinder the comprehensive investigation and in-depth understanding of the adversarial robustness of LIC algorithms. To address the aforementioned issues, this paper considers the arbitrary nature of the attack direction and the uncontrollable compression ratio faced by adversaries, and presents two practical rate-distortion attack paradigms, i.e., Specific-ratio Rate-Distortion Attack (SRDA) and Agnostic-ratio Rate-Distortion Attack (ARDA). Using the performance variations as indicators, we evaluate the adversarial robustness of eight predominant LIC algorithms against diverse attacks. Furthermore, we propose two novel analytical tools for in-depth analysis, i.e., Entropy Causal Intervention and Layer-wise Distance Magnify Ratio, and reveal that hyperprior significantly increases the bitrate and Inverse Generalized Divisive Normalization (IGDN) significantly amplifies input perturbations when under attack. Lastly, we examine the efficacy of adversarial training and introduce the use of online updating for defense. By comparing their advantages and disadvantages, we provide a reference for constructing more robust LIC algorithms against the rate-distortion attacks.

As the impact of climate change escalates, the global necessity to transition to sustainable energy sources becomes increasingly evident. Renewable energies have emerged as a viable solution for users, with Photovoltaic energy being a favored choice for small installations due to its reliability and efficiency. Accurate mapping of PV installations is crucial for understanding the extension of its adoption and informing energy policy. To meet this need, we introduce S3Former, designed to segment solar panels from aerial imagery and provide size and location information critical for analyzing the impact of such installations on the grid. Solar panel identification is challenging due to factors such as varying weather conditions, roof characteristics, Ground Sampling Distance variations and lack of appropriate initialization weights for optimized training. To tackle these complexities, S3Former features a Masked Attention Mask Transformer incorporating a self-supervised learning pretrained backbone. Specifically, our model leverages low-level and high-level features extracted from the backbone and incorporates an instance query mechanism incorporated on the Transformer architecture to enhance the localization of solar PV installations. We introduce a self-supervised learning phase (pretext task) to improve the initialization weights on the backbone of S3Former. We evaluated S3Former using diverse datasets, demonstrate improvement state-of-the-art models., Comment: Preprint

Axion-like particles (ALPs) are good candidates for mediators to the dark sector. We explore scenarios in which an ALP mediates interactions between dark matter and electroweak gauge bosons. These models yield testable electromagnetic signals in astrophysical, cosmological, and terrestrial probes. We find promising prospects for both indirect detection and accelerator tests, with interesting parameter space already constrained by current experiments. Our work provides concrete benchmarks for future tests of the electroweak ALP portal., Comment: 15+5 pages, 10 figures

Optical Character Recognition - Visual Question Answering (OCR-VQA) is the task of answering text information contained in images that have just been significantly developed in the English language in recent years. However, there are limited studies of this task in low-resource languages such as Vietnamese. To this end, we introduce a novel dataset, ViOCRVQA (Vietnamese Optical Character Recognition - Visual Question Answering dataset), consisting of 28,000+ images and 120,000+ question-answer pairs. In this dataset, all the images contain text and questions about the information relevant to the text in the images. We deploy ideas from state-of-the-art methods proposed for English to conduct experiments on our dataset, revealing the challenges and difficulties inherent in a Vietnamese dataset. Furthermore, we introduce a novel approach, called VisionReader, which achieved 0.4116 in EM and 0.6990 in the F1-score on the test set. Through the results, we found that the OCR system plays a very important role in VQA models on the ViOCRVQA dataset. In addition, the objects in the image also play a role in improving model performance. We open access to our dataset at link (https://github.com/qhnhynmm/ViOCRVQA.git) for further research in OCR-VQA task in Vietnamese.

This paper describes our systems for the sub-task I in the Software Mention Detection in Scholarly Publications shared-task. We propose three approaches leveraging different pre-trained language models (BERT, SciBERT, and XLM-R) to tackle this challenge. Our bestperforming system addresses the named entity recognition (NER) problem through a three-stage framework. (1) Entity Sentence Classification - classifies sentences containing potential software mentions; (2) Entity Extraction - detects mentions within classified sentences; (3) Entity Type Classification - categorizes detected mentions into specific software types. Experiments on the official dataset demonstrate that our three-stage framework achieves competitive performance, surpassing both other participating teams and our alternative approaches. As a result, our framework based on the XLM-R-based model achieves a weighted F1-score of 67.80%, delivering our team the 3rd rank in Sub-task I for the Software Mention Recognition task., Comment: Software mention recognition, Named entity recognition, Transformer, Three-stage framework

Generative AI has put many professional writers on the defensive; a major negotiation point of the recent Writers Guild of America's strike concerned use of AI. However, must AI threaten writers, their livelihoods or their creativity? And under what conditions, if any, might AI assistance be invited by different types of writers (from the amateur to the professional, from the screenwriter to the novelist)? To explore these questions, we conducted a qualitative study with 37 writers. We found that most writing occurs across five stages and within one of three modes; we additionally map openness to AI assistance to each intersecting stage-mode. We found that most writers were interested in AI assistance to some degree, but some writers felt drawing firm boundaries with an AI was key to their comfort using such systems. Designers can leverage these insights to build agency-respecting AI products for writers.

In the food industry, assessing the quality of poultry carcasses during processing is a crucial step. This study proposes an effective approach for automating the assessment of carcass quality without requiring skilled labor or inspector involvement. The proposed system is based on machine learning (ML) and computer vision (CV) techniques, enabling automated defect detection and carcass quality assessment. To this end, an end-to-end framework called CarcassFormer is introduced. It is built upon a Transformer-based architecture designed to effectively extract visual representations while simultaneously detecting, segmenting, and classifying poultry carcass defects. Our proposed framework is capable of analyzing imperfections resulting from production and transport welfare issues, as well as processing plant stunner, scalder, picker, and other equipment malfunctions. To benchmark the framework, a dataset of 7,321 images was initially acquired, which contained both single and multiple carcasses per image. In this study, the performance of the CarcassFormer system is compared with other state-of-the-art (SOTA) approaches for both classification, detection, and segmentation tasks. Through extensive quantitative experiments, our framework consistently outperforms existing methods, demonstrating remarkable improvements across various evaluation metrics such as AP, AP@50, and AP@75. Furthermore, the qualitative results highlight the strengths of CarcassFormer in capturing fine details, including feathers, and accurately localizing and segmenting carcasses with high precision. To facilitate further research and collaboration, the pre-trained model and source code of CarcassFormer is available for research purposes at: \url{https://github.com/UARK-AICV/CarcassFormer}., Comment: Accepted to Poultry Science Journal