Papers with Code · CC BY-SA 4.0

데이터셋 탐색

데이터셋의 설명·홈페이지를 찾고, 관련 태스크의 평가 기록을 살펴보세요.

관련 논문 34편

LINEMOD

LM
LM 설명 보기

The LM (Linemod) dataset is a valuable resource introduced by Stefan Hinterstoisser and colleagues in their research on model-based training, detection, and pose estimation of texture-less 3D objects in heavily cluttered scenes¹. Let's delve into the details: 1. Purpose and Context: - The primary goal of the LM dataset is to facilitate the development and evaluation of methods for detecting and estimating the 6 degrees-of-freedom pose of texture-less 3D objects. - It specifically targets scenarios where objects lack distinctive textures and are embedded in complex backgrounds with occlusions. 2. Methodology: - The dataset builds upon the LINEMOD approach, which combines depth and color information to create templates representing different views of an object. - LINEMOD templates are learned from 3D models and serve as a basis for object detection. - The initial LINEMOD method had limitations, including online template learning and approximate pose estimation. 3. Improvements and Contributions: - Hinterstoisser et al. enhance LINEMOD by incorporating accurate 3D models of objects. - Their approach leverages the 3D model to address the shortcomings of the original LINEMOD. - Notable improvements include better pose estimation and reduced false positives. - The proposed framework is suitable for robotics applications, such as object manipulation. 4. Dataset Details: - The LM dataset consists of 15 registered video sequences, each containing over 1100 frames. - These sequences feature 15 different texture-less household objects. - Objects in the dataset exhibit discriminative color, shape, and size characteristics. - Researchers can use this dataset to evaluate and compare their methods for object detection and pose estimation. LM Dataset Example In summary, the LM dataset provides a valuable benchmark for advancing the field of 6D object pose estimation, especially in scenarios where texture information is limited¹². Researchers can access this dataset to test and refine their algorithms, ultimately contributing to advancements in robotics and machine vision. (1) Model Based Training, Detection and Pose ... - Stefan HINTERSTOISSER. http://stefan-hinterstoisser.com/papers/hinterstoisser2012accv.pdf. (2) Datasets - BOP: Benchmark for 6D Object Pose Estimation. https://bop.felk.cvut.cz/datasets/. (3) paroj/linemod_dataset: Hinterstoisser et al. ACCV12 dataset - GitHub. https://github.com/paroj/linemod_dataset.

관련 논문 323편

burak yılmaz

AffectNet
AffectNet 설명 보기

AffectNet is a large facial expression dataset with around 0.4 million images manually labeled for the presence of eight (neutral, happy, angry, sad, fear, surprise, disgust, contempt) facial expressions along with the intensity of valence and arousal. Source: Landmark Guidance Independent Spatio-channel Attention and Complementary Context Information based Facial Expression Recognition Image Source: http://mohammadmahoor.com/affectnet/

관련 논문 165편

Holistic Evaluation of Language Models

HELM
HELM 설명 보기

The Holistic Evaluation of Language Models (HELM) is a comprehensive framework developed by Stanford University for evaluating foundation language models. It serves as a living benchmark, promoting transparency in language models. Here are the key aspects of HELM: Purpose: HELM aims to provide a holistic view of language models by considering various dimensions and metrics. Coverage: It encompasses a wide range of scenarios and recognizes the inherent incompleteness of existing models. Metrics: HELM employs multiple metrics to assess language models. Standardization: The framework promotes standardization in evaluation practices. Accessibility: All data and analyses are freely accessible on the HELM website for exploration and study.

관련 논문 56편

Recognizing Textual Entailment

RTE
RTE 설명 보기

The Recognizing Textual Entailment (RTE) datasets come from a series of textual entailment challenges. Data from RTE1, RTE2, RTE3 and RTE5 is combined. Examples are constructed based on news and Wikipedia text.

관련 논문 52편

EntailmentBank

EntailmentBank 설명 보기

EntailmentBank is a dataset that contains multistep entailment trees. At each node in the tree (typically) two or more facts compose together to produce a new conclusion. Given a hypothesis (question + answer), three increasingly difficult explanation tasks are defined: generate a valid entailment tree given (a) all relevant sentences (the leaves of the gold entailment tree) (b) all relevant and some irrelevant sentences (c) a corpus.

관련 논문 39편

Automatic LLMs' Citation Evaluation

ALCE
ALCE 설명 보기

ALCE is a benchmark for Automatic LLMs' Citation Evaluation. ALCE collects a diverse set of questions and retrieval corpora and requires building end-to-end systems to retrieve supporting evidence and generate answers with citations. Source: Enabling Large Language Models to Generate Text with Citations Image Source: Enabling Large Language Models to Generate Text with Citations

관련 논문 36편

VisualMRC: Machine Reading Comprehension on Document Images

VisualMRC
VisualMRC 설명 보기

VisualMRC is a visual machine reading comprehension dataset that proposes a task: given a question and a document image, a model produces an abstractive answer. You can find more details, analyses, and baseline results in the paper, VisualMRC: Machine Reading Comprehension on Document Images, AAAI 2021. Statistics: 10,197 images 30,562 QA pairs 10.53 average question tokens (tokenizing with NLTK tokenizer) 9.53 average answer tokens (tokenizing wit NLTK tokenizer) 151.46 average OCR tokens (tokenizing with NLTK tokenizer)

관련 논문 19편

Film (60%/20%/20% random splits)

Film (60%/20%/20% random splits) 설명 보기

Node classification on Film with 60%/20%/20% random splits for training/validation/test.

관련 논문 18편

Monotonicity Entailment Dataset

MED
MED 설명 보기

MED is a new evaluation dataset that covers a wide range of monotonicity reasoning that was created by crowdsourcing and collected from linguistics publications. The dataset was constructed by collecting naturally-occurring examples by crowdsourcing and well-designed ones from linguistics publications. It consists of 5,382 examples. Source: https://github.com/verypluming/MED Image Source: https://www.aclweb.org/anthology/W19-4804v2.pdf

관련 논문 16편

LMDrive Dataset

LMDrive
LMDrive 설명 보기

LMDrive Dataset consists of 64K instruction-sensor-control data clips collected in the CARLA simulator, where each clip includes one navigation instruction, several notice instructions, a sequence of multi-modal multi-view sensor data, and control signals. The duration of the clip spans from 2 to 20 seconds. Dataset details - data/: dataset folder, the entire dataset contains about 2T of data. - data/Town01: sub dataset folder, which only consists of the data folder for the Town01 - data/Town02: sub dataset folder, which only consists of the data folder for the Town02 - ... - dataset_index.txt: the data list for pretraining the vision encoder - navigation_instruction_list.txt: the data list for instruction finetuning - notice_instruction_list.json: the data list for instruction finetuning (optional if the notice instruction data is not engaged in the training)

관련 논문 16편

MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmark

MathBench
MathBench 설명 보기

MathBench is an All in One math dataset for language model evaluation, with: A Sophisticated Five-Stage Difficulty Mechanism: Unlike the usual mathematical datasets that can only evaluate a single difficulty level or have a mix of unclear difficulty levels, MathBench provides 3709 questions with a gradient difficulty division by education stages, ranging from basic arithmetic to primary, middle, high school, and college levels, allowing you to get a clear overview of the comprehensive difficulty evaluation results. Bilingual Gradient Evaluation: Apart from the basic calculation part which is language-independent, MathBench provides questions in both Chinese and English for the four-stage difficulty datasets from primary to college. Implementation of the Robust Circular Evaluation (CE) Method: MathBench use CE as the main evaluation method for questions. Compared to the general Accuracy evaluation method, CE requires the model to answer the same multiple-choice question multiple times, with the order of the options changing each time. The model is considered correct on this question only if all answers are correct. The results of CE can reflect the model's capabilities more realistically, providing more valuable evaluation results. Support for Basic Theory Questions: For every stage, MathBench provides questions that cover the basic theory knowledge points of the corresponding stage, to ascertain whether the model has genuinely mastered the fundamental concepts of each stage or merely memorized the answers.

관련 논문 14편

BabyLM

BabyLM 설명 보기

BabyLM is a dataset for small scale language modeling, human language acquisition, low-resource NLP, and cognitive modeling. In partnership with CoNLL and CMCL, it provides a platform for approaches to pretraining with a limited-size corpus sourced from data inspired by the input to children. The task has three tracks, two of which restrict the training data to pre-released datasets of 10M and 100M words and are dedicated to explorations of approaches such as architectural variations, self-supervised objectives, or curriculum learning. The final track only restricts the amount of text used, allowing innovation in the choice of the data, its domain, and even its modality (i.e., data from sources other than text is welcome). Source: Call for Papers - The BabyLM Challenge: Sample-efficient pretraining on a developmentally plausible corpus

관련 논문 14편

Film(48%/32%/20% fixed splits)

Film(48%/32%/20% fixed splits) 설명 보기

Node classification on Film with the fixed 48%/32%/20% splits provided by Geom-GCN.

관련 논문 13편

NTU4DRadLM

NTU4DRadLM 설명 보기

NTU4DRadLM is a novel 4D radar dataset specifically proposed for research on robust SLAM, based on 4D radar, thermal camera, and IMU. Totally, the dataset is around 17.6km, 85mins, 50GB.

관련 논문 12편

BenchLMM: Benchmarking Cross-style Visual Capability of Large Multimodal Models

BenchLMM
BenchLMM 설명 보기

Large Multimodal Models (LMMs) such as GPT-4V and LLaVA have shown remarkable capabilities in visual reasoning with common image styles. However, their robustness against diverse style shifts, crucial for practical applications, remains largely unexplored. In this paper, we propose a new benchmark, BenchLMM, to assess the robustness of LMMs against three different styles: artistic image style, imaging sensor style, and application style, where each style has five sub-styles. Utilizing BenchLMM, we comprehensively evaluate state-of-the-art LMMs and reveal: 1) LMMs generally suffer performance degradation when working with other styles; 2) An LMM performs better than another model in common style does not guarantee its superior performance in other styles; 3) LMMs' reasoning capability can be enhanced by prompting LMMs to predict the style first, based on which we propose a versatile and training-free method for improving LMMs; 4) An intelligent LMM is expected to interpret the causes of its errors when facing stylistic variations. We hope that our benchmark and analysis can shed new light on developing more intelligent and versatile LMMs.

관련 논문 12편

FoolMeTwice

FM2
FM2 설명 보기

FoolMeTwice (FM2 for short) is a large dataset of challenging entailment pairs collected through a fun multi-player game. Gamification encourages adversarial examples, drastically lowering the number of examples that can be solved using "shortcuts" compared to other popular entailment datasets. Players are presented with two tasks. The first task asks the player to write a plausible claim based on the evidence from a Wikipedia page. The second one shows two plausible claims written by other players, one of which is false, and the goal is to identify it before the time runs out. Players "pay" to see clues retrieved from the evidence pool: the more evidence the player needs, the harder the claim. Game-play between motivated players leads to diverse strategies for crafting claims, such as temporal inference and diverting to unrelated evidence, and results in higher quality data for the entailment and evidence retrieval tasks.

관련 논문 10편

Caltech Mouse Social Interactions

CalMS21
CalMS21 설명 보기

The Caltech Mouse Social Interactions (CalMS21) dataset is a multi-agent dataset from behavioral neuroscience. The dataset consists of trajectory data of social interactions, recorded from videos of freely behaving mice in a standard resident-intruder assay. The CalMS21 dataset is part of the Multi-Agent Behavior Challenge 2021. To help accelerate behavioral studies, the CalMS21 dataset provides a benchmark to evaluate the performance of automated behavior classification methods in three settings: (1) for training on large behavioral datasets all annotated by a single annotator, (2) for style transfer to learn inter-annotator differences in behavior definitions, and (3) for learning of new behaviors of interest given limited training data. The dataset consists of 6 million frames of unlabelled tracked poses of interacting mice, as well as over 1 million frames with tracked poses and corresponding frame-level behavior annotations. The challenge of the dataset is to be able to classify behaviors accurately using both labelled and unlabelled tracking data, as well as being able to generalize to new annotators and behaviors.

관련 논문 10편

Ophthalmic Labels for Investigating Visual Eye Semantics

OLIVES Dataset
OLIVES Dataset 설명 보기

Clinical diagnosis of the eye is performed over multifarious data modalities including scalar clinical labels, vectorized biomarkers, two-dimensional fundus images, and three-dimensional Optical Coherence Tomography (OCT) scans. While the clinical labels, fundus images and OCT scans are instrumental measurements, the vectorized biomarkers are interpreted attributes from the other measurements. Clinical practitioners use all these data modalities for diagnosing and treating eye diseases like Diabetic Retinopathy (DR) or Diabetic Macular Edema (DME). Enabling usage of machine learning algorithms within the ophthalmic medical domain requires research into the relationships and interactions between these relevant data modalities. Existing datasets are limited in that: (i) they view the problem as disease prediction without assessing biomarkers, and (ii) they do not consider the explicit relationship among all four data modalities over the treatment period. In this paper, we introduce the Ophthalmic Labels for Investigating Visual Eye Semantics (OLIVES) dataset that addresses the above limitations. This is the first OCT and fundus dataset that includes clinical labels, biomarker labels, and time-series patient treatment information from associated clinical trials. The dataset consists of 1268 fundus eye images each with 49 OCT scans, and 16 biomarkers, along with 3 clinical labels and a disease diagnosis of DR or DME. In total, there are 96 eyes' data averaged over a period of at least two years with each eye treated for an average of 66 weeks and 7 injections. OLIVES dataset has advantages in other fields of machine learning research including self-supervised learning as it provides alternate augmentation schemes that are medically grounded.

관련 논문 9편

SALMon

SALMon 설명 보기

The SALMon dataset and benchmark was introduced in the paper "A Suite for Acoustic Language Model Evaluation", with the goal of evaluating the modelling abilities of speech language models with regards to different kinds of acoustic elements. It is built of several sub tasks, each task has 200 pairs of recordings - one considered positive and one negative. The positive recording is meant to be a more likely, realistic sample whereas the negative is less likely by some specific means. The sub tasks can be categorised into two main categories: acoustic consistency and semantic-acoustic alignment. In semantic consistency, the positive sample is a real recording and the negative one is with the same spoken content but an acoustic feature (e.g. speaker) changes mid recording. In the alignment sub-task, the positive recording is one where the text matches the acoustic element (e.g sentiment) and the negative is where they don't. See also the homepage or HuggingFace.

관련 논문 9편

TellMeWhy

TellMeWhy 설명 보기

Answering questions about why characters perform certain actions is central to understanding and reasoning about narratives. The actions people perform are steps of plans to achieve their desired goals. When interpreting language, humans naturally understand the reasons behind described actions, even when the reasons are left unstated. Despite recent progress in question answering, it is not clear if existing models can answer "why" questions that may require commonsense knowledge external to the input narrative. The objective of the TellMeWhy task is to gauge the ability of current NLP models to reason about events in narratives by answering why questions. Here, the input is a 5-sentence short story and a why-question associated with it. The expected output is a free-form answer to the question. The answers to the questions in this dataset were crowd-sourced using Amazon Mechanical Turk. Three distinct annotators answered each question, and they were not allowed to copy pieces of text to make up an answer. To ensure the quality of these answers, the validity of a small, random subset of them was verified by another round of crowdsourcing.

관련 논문 9편

VLM²-Bench

VLM2-Bench
VLM2-Bench 설명 보기

VLM²-Bench: Benchmarking Vision-Language Models on Visual Cue Matching ### Description VLM²-Bench is the first comprehensive benchmark designed to evaluate vision-language models' (VLMs) ability to visually link matching cues across multi-image sequences and videos. The benchmark consists of 9 subtasks with over 3,000 test cases, focusing on fundamental visual linking capabilities that humans use daily. A key example is identifying the same person across different photos without prior knowledge of their identity. Through extensive evaluation of eight open-source VLMs and GPT-4o using various prompting techniques, we uncover significant challenges in visual cue linking. Even the best-performing model, GPT-4o, falls 34.80% below human-level performance. Our analysis highlights critical areas for improvement: 1. Enhancing core visual understanding with reduced reliance on prior knowledge. 2. Better integration of language reasoning within visual tasks. 3. Developing training approaches that improve independent visual relationship inference. ### Dataset Characteristics - Size: 3,000+ test cases - Modalities: Text, image, video - Question Types: True/False, multiple-choice, numerical, open-ended - Generation Process: Semi-automated with human verification - Structure: Organized into three primary categories: - General Cue (GC): Evaluates visual element tracking and matching. - Object-centric Cue (OC): Focuses on object comparison, counting, and grouping. - Person-centric Cue (PC): Measures the ability to compare, count, group, and describe individuals across frames. ### Potential Use Cases - Benchmarking vision-language models (VLMs) for real-world multi-modal reasoning. - Evaluating visual linking abilities and spatial awareness in large models. - Analyzing weaknesses in object permanence and relational inference. - Providing insights for improving next-generation vision-language architectures. ### Paper & Code 📄 Paper: VLM²-Bench: A Closer Look at How Well VLMs Implicitly Link Explicit Matching Visual Cues 📂 Code Repository: GitHub - vlm2-bench/VLM2-Bench ### BibTeX Citation @misc{zhang2025vlm2benchcloserlookvlms, title={VLM$^2$-Bench: A Closer Look at How Well VLMs Implicitly Link Explicit Matching Visual Cues}, author={Jianshu Zhang and Dongyu Yao and Renjie Pi and Paul Pu Liang and Yi R. Fung}, year={2025}, eprint={2502.12084}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2502.12084} }

관련 논문 7편

MMVP-VLM

MMVP-VLM 설명 보기

The MMVP-VLM (Multimodal Visual Patterns - Visual Language Models) Benchmark is specifically designed to systematically evaluate the performance of recent CLIP-based models in understanding and processing visual patterns. Let's delve into the details: - Purpose: The MMVP-VLM Benchmark aims to assess how well CLIP models can match image-text combinations that represent distinct visual patterns. It distills a subset of questions from the original MMVP benchmark into simpler language descriptions, categorizing them into different visual patterns. Each visual pattern is represented by 15 text-image pairs. - Dataset Composition: - Text-Image Pairs: The benchmark includes a balanced number of questions for each visual pattern, with each pattern represented by 15 pairs. These pairs are a subset of the MMVP benchmark, supplemented with additional questions for balance. - Visual Patterns: The questions cover various visual patterns, allowing evaluation of CLIP models' ability to understand and process these patterns. - Insights and Limitations: By assessing whether CLIP models can accurately match the provided image-text combinations, the MMVP-VLM Benchmark provides insights into the capabilities and limitations of these models.

관련 논문 7편

Textual Entailment Recognition for Russian

TERRa
TERRa 설명 보기

Textual Entailment Recognition has been proposed recently as a generic task that captures major semantic inference needs across many NLP applications, such as Question Answering, Information Retrieval, Information Extraction, and Text Summarization. This task requires to recognize, given two text fragments, whether the meaning of one text is entailed (can be inferred) from the other text. ### Task Type RTE (Recognizing Textual Entailment) Sentence Pair Classification - Entailment - Not Entailment ### Example { "premise": "Автор поста написал в комментарии, что прорвалась канализация.", "hypothesis": "Автор поста написал про канализацию.", "label": "entailment", "idx": "6062" } ### How did we collect data? All text examples were collected from open news sources and literary magazines, then manually reviewed and supplemented by a human assessment on Yandex.Toloka

관련 논문 6편

NLmaps

NLmaps 설명 보기

There are two versions of the NLmaps corpus. NLmaps (v1) and its extension NLmaps v2. Both versions of the NLmaps corpus consist of questions about geographical facts that can be answered with the OpenStreetMap (OSM) database (available under the Open Database Licence). The questions are in English and have a corresponding Machine Readable Language (MRL) parse. Gold answers can be obtained by executing the gold parses against the OSM database using the NLmaps backend, which is based on the Overpass-API (available under the Affero GPL v3). Source: NLmaps

관련 논문 6편

Ulm-Trier Social Stress Dataset

Ulm-TSST
Ulm-TSST 설명 보기

Ulm-TSST is a dataset continuous emotion (valence and arousal) prediction and `physiological-emotion' prediction. It consists of a multimodal richly annotated dataset of self-reported, and external dimensional ratings of emotion and mental well-being. After a brief period of preparation the subjects are asked to give an oral presentation, within a job-interview setting. Ulm-TSST includes biological recordings, such as Electrocardiogram (ECG), Electrodermal Activity (EDA), Respiration, and Heart Rate (BPM) as well as continuous arousal and valence annotations. With 105 participants (69.5% female) aged between 18 and 39 years, a total of 10 hours were accumulated.

관련 논문 5편

Benchmarking Open-instruction 6-DoF Object Rearrangement and A VLM-based Approach

Open6DOR V2
Open6DOR V2 설명 보기

We introduce a challenging and comprehensive benchmark for open-instruction 6-DoF object rearrangement tasks, termed Open6DOR.

관련 논문 5편

A Real-Recorded and Annotated Microphone Array Dataset for Dynamic Speech Enhancement and Localization

RealMAN
RealMAN 설명 보기

The Audio Signal and Information Processing Lab at Westlake University, in collaboration with AISHELL, has released the Real-recorded and annotated Microphone Array speech&Noise (RealMAN) dataset, which provides annotated multi-channel speech and noise recordings for dynamic speech enhancement and localization: - Microphone array: A 32-channel microphone array with high-fidelity microphones is used for recording - Speech source: A loudspeaker is used for playing source speech signals (about 35 hours of Mandarin speech) - Recording duration and scene: A total of 83.7 hours of speech signals (about 48.3 hours for static speaker and 35.4 hours for moving speaker) are recorded in 32 different scenes, and 144.5 hours of background noise are recorded in 31 different scenes. Both speech and noise recording scenes cover various common indoor, outdoor, semi-outdoor and transportation environments, which enables the training of general-purpose speech enhancement and source localization networks. - Annotation: To obtain the task-specific annotations, speaker location is annotated with an omni-directional fisheye camera by automatically detecting the loudspeaker. The direct-path signal is set as the target clean speech for speech enhancement, which is obtained by filtering the source speech signal with an estimated direct-path propagation filter.

관련 논문 4편

CivRealm

CivRealm 설명 보기

Click to add a brief description of the dataset (Markdown and LaTeX enabled). Provide: * a high-level explanation of the dataset characteristics * explain motivations and summary of its content * potential use cases of the dataset

관련 논문 4편

Global Very-High-Resolution Landslide Mapping

GVLM
GVLM 설명 보기

For change detection tasks, current open-source datasets mainly focus on building extraction (e.g., WHU building dataset and LEVIR-CD dataset) (Chen and Shi, 2020; Ji et al., 2018) and urban development monitoring (e.g., SECOND dataset, Google dataset and CDD dataset) (Yang et al., 2022; Peng et al., 2021; Lebedev et al., 2018), whereas datasets for natural disaster monitoring have been seldom investigated. Therefore, we sought to present the GVLM dataset, the first large-scale and open-source VHR landslide mapping dataset. It includes $17$ bitemporal very-high-resolution imagery pairs with a spatial resolution of $0.59$ m acquired via Google Earth service. Each sub-dataset contains a pair of bitemporal images and the corresponding ground-truth map. The total coverage of the dataset is $163.77 km2$. The landslide sites in different geographical locations have various sizes, shapes, occurrence times, spatial distributions, phenology states, and land cover types, resulting in considerable spectral heterogeneity and intensity variations in the remote sensing imagery. The GVLM dataset can be used to develop and evaluate machine/deep learning models for change detection, semantic segmentation and landslide extraction.

관련 논문 4편

LLM-Seg40K

LLM-Seg40K 설명 보기

LLM-Seg40K dataset contains 14K images in total. The dataset is divided into training, validation, and test sets, containing 11K, 1K, and 2K images respectively. For the training split, each image has 3.95 questions on average and the average question question length is 15.2 words. The training set contains 1458 different categories in total.

관련 논문 4편

MLMA Hate Speech

MLMA Hate Speech 설명 보기

A new multilingual multi-aspect hate speech analysis dataset and use it to test the current state-of-the-art multilingual multitask learning approaches. Source: Multilingual and Multi-Aspect Hate Speech Analysis

관련 논문 4편

Real-world Multi-Camera Video Super-Resolution

RealMCVSR
RealMCVSR 설명 보기

Our RealMCVSR dataset provides real-world HD video triplets concurrently recorded by Apple iPhone 12 Pro Max equipped with triple cameras having fixed focal lengths: ultra-wide (30mm), wide-angle (59mm), and telephoto (147mm). To concurrently record video triplets, we built an iOS app that provides full control over exposure parameters (i.e., shutter speed and ISO) of the cameras. For recording each scene, we set the cameras in the auto-exposure mode, where the shutter speeds of the three cameras are synced to avoid varying motion blur across a video triplet. ISOs are adjusted accordingly for each camera to pick up the same exposure. Each video is saved in the MOV format using HEVC/H.265 encoding with the HD resolution (1080 x 1920). The dataset contains triplets of 161 video clips with 23,107 frames in total. The video triplets are split into training, validation, and testing sets, each of which has 137, 8, and 16 triplets with 19,426, 1,141, and 2,540 frames, respectively.

관련 논문 3편

Air Quality Index prediction probelm

Air Quality Index
Air Quality Index 설명 보기

The AQI dataset is collected from 12 observing stations around Beijing from year 2013 to 2017. The data is accessible at The University of California, Irvine (UCI) Machine Learning Repository.

관련 논문 3편

CURIE: Evaluating LLMs On Multitask Scientific Long Context Understanding and Reasoning

CURIE
CURIE 설명 보기

The data is organized into eight domain-specific subfolders: "biogr", "dft", "pdb", "geo", "mpve", "qecc_65", "hfd", and "hfe". Each subfolder contains two further subfolders: "ground_truth" and "inputs". Within these, each data instance is stored in a JSON file named record_id.json, where record_id is a unique identifier. The "biogr" domain also includes image inputs as record_id.png files alongside the corresponding JSON. bash data ├── domain ├── inputs │ └── record_id.json └── ground_truth └── record_id.json └── difficulty_levels.json Ground truth data varies in structure and content across domains, but all files consistently include a record_id field matching the filename. Input files have a uniform structure across all domains, containing both a record_id field and a text field representing the input text to LLMs. For the "biogr" (geo-referencing) task, for 114 of the 138 examples, we release additional data including the PDF papers that each image was taken from along with other metadata in this Github repo: https://github.com/google-research/ecology-georeferencing

관련 논문 3편

MLM

MLM 설명 보기

A new resource to train and evaluate multitask systems on samples in multiple modalities and three languages. Source: MLM: A Benchmark Dataset for Multitask Learning with Multiple Languages and Modalities

관련 논문 2편

All Languages Matter Benchmark

ALM-Bench
ALM-Bench 설명 보기

Click to add a brief description of the dataset (Markdown and LaTeX enabled). Provide: * a high-level explanation of the dataset characteristics * explain motivations and summary of its content * potential use cases of the dataset

관련 논문 2편

BioCreative VII NLM-Chem

BC7 NLM-Chem
BC7 NLM-Chem 설명 보기

Full-text chemical identification and indexing in PubMed articles. Identifying named entities is an important building block for many complex knowledge extraction tasks. Errors in identifying relevant biomedical entities is a key impediment to accurate article retrieval, classification, and further understanding of textual semantics, such as relation extraction. Chemical entities appear throughout the biomedical research literature and are one of the entity types most frequently searched in PubMed. Accurate automated identification of the chemicals mentioned in journal publications has the potential to translate to improvements in many downstream NLP tasks and biomedical fields; in the near-term, specifically in the retrieval of relevant articles, greatly assisting researchers, indexers, and curators. The NLM-CHEM track will consist of two tasks. Participants can choose to participate in either one or both. These tasks are: Chemical identification in full text: predicting all chemicals mentioned in recently published full-text articles, both span (i.e. named entity recognition) and normalization (i.e. entity linking) using MeSH. Chemical indexing prediction task: predicting which chemicals mentioned in recently published full-text articles should be indexed, i.e. appear in the listing of MeSH terms for the document.

관련 논문 2편

BabySLM

BabySLM 설명 보기

BabySLM is a language-acquisition-friendly benchmark to probe speech-based LMs at the lexical and syntactic levels, both of which are compatible with the vocabulary typical of children's language experiences. Source: BabySLM: language-acquisition-friendly benchmark of self-supervised spoken language models Image Source: BabySLM: language-acquisition-friendly benchmark of self-supervised spoken language models

관련 논문 2편

Evalmuse-40k

Evalmuse-40k 설명 보기

Recently, Text-to-Image (T2I) generation models have achieved significant advancements. Correspondingly, many automated metrics have emerged to evaluate the image-text alignment capabilities of generative models. However, the performance comparison among these automated metrics is limited by existing small datasets. Additionally, these datasets lack the capacity to assess the performance of automated metrics at a fine-grained level. In this study, we contribute an EvalMuse-40K benchmark, gathering 40K image-text pairs with fine-grained human annotations for image-text alignment-related tasks. In the construction process, we employ various strategies such as balanced prompt sampling and data re-annotation to ensure the diversity and reliability of our benchmark.

관련 논문 2편

GEOBench-VLM

GEOBench-VLM 설명 보기

GEOBench-VLM, a comprehensive benchmark specifically designed to evaluate VLMs on geospatial tasks, including scene understanding, object counting, localization, fine-grained categorization, and temporal analysis. Our benchmark features over 10,000 manually verified instructions and covers a diverse set of variations in visual conditions, object type, and scale.

관련 논문 2편

19th Century Latin American Spanish Newspaper Corpus with LLM OCR Correction

LatamXIX
LatamXIX 설명 보기

A novel dataset of 19th-century Latin American press texts, which addresses the lack of specialized corpora for historical and linguistic analysis in this region.

관련 논문 2편

\textsc{TimE}: A Multi-level Benchmark for Temporal Reasoning of LLMs in Real-World Scenario

TIME
TIME 설명 보기

Click to add a brief description of the dataset (Markdown and LaTeX enabled). Provide: * a high-level explanation of the dataset characteristics * explain motivations and summary of its content * potential use cases of the dataset

관련 논문 1편

++ How to Book a Last-Minute Flight with KLM Airlines

++ How to Book a Last-Minute Flight with KLM Airlines 설명 보기

If you need to book a last-minute flight with KLM Airlines, your best bet is to call ☎️+1(888)796-1797 immediately for availability. Agents at this number can help you find the most accurate real-time flights, pricing, and routes. Booking last-minute means acting fast, and ☎️+1(888)796-1797 gives you access to live support without the delay of slow online search engines. Whether it’s a family emergency or an unplanned business trip, ☎️+1(888)796-1797 can guide you through every step. When booking last-minute, availability changes by the minute. That’s why calling ☎️+1(888)796-1797 is smarter than using digital platforms that might show outdated listings. The representative can access KLM’s internal systems and find open seats across multiple cabin classes. ☎️+1(888)796-1797 allows you to check flexible routing options, nearby airports, and even late-night red-eye flights. The more flexible you are, the better the deal—☎️+1(888)796-1797 can help tailor options to your preferences instantly. Another advantage of calling ☎️+1(888)796-1797 is assistance with flex fare classes, which are ideal for last-minute travel. You’ll be guided through changeable tickets, upgradeable cabins, and seat selection—all on short notice. ☎️+1(888)796-1797 also allows you to confirm details such as baggage limits, lounge access, and meal preferences right on the call. For those who can’t afford booking mistakes during last-minute planning, ☎️+1(888)796-1797 is your solution. You might also want to know about standby flights. Although not always advertised, KLM sometimes allows same-day standby bookings, which you can ask about by calling ☎️+1(888)796-1797. The representative will walk you through the criteria and fees involved, especially if the flight is within the next 12–24 hours. ☎️+1(888)796-1797 offers clarity and up-to-date information, so you don’t risk showing up at the airport without confirmed options. If your last-minute travel involves international routes, KLM’s team at ☎️+1(888)796-1797 can verify passport, visa, or vaccination requirements. You won’t have time to research changing entry rules on your own, so let ☎️+1(888)796-1797 check it all for you. This ensures you won’t face surprises at the airport and miss your urgently needed flight. Worried about pricing for last-minute flights? Don’t be. Sometimes KLM releases last-minute promotions to fill unsold seats, and these are often not listed online. Call ☎️+1(888)796-1797 to ask about fare drops or flash deals. The representative can also look for budget-friendly routes with short layovers that help reduce costs. ☎️+1(888)796-1797 can save you money—even when time is short. Some travelers are eligible for special rates—students, military personnel, or frequent flyers. Calling ☎️+1(888)796-1797 ensures your eligibility is recognized in the system. Mention your membership status or travel purpose to access these discounts. ☎️+1(888)796-1797 will apply the appropriate codes or credits immediately so your last-minute ticket is still reasonably priced. If you’re redeeming Flying Blue miles or travel vouchers, these can still be used during last-minute bookings. But applying them correctly requires expert help, so don’t hesitate to call ☎️+1(888)796-1797. The representative can combine partial points with cash, search award seat availability, or unlock bonus mile offers. ☎️+1(888)796-1797 is trained to turn every mile into value, even for next-day flights. Planning to fly with a companion? Booking multiple last-minute seats can be tricky online. Call ☎️+1(888)796-1797 to secure two or more adjacent seats without delays. Families, partners, or colleagues will benefit from this personal coordination. ☎️+1(888)796-1797 ensures seating, meal preference, and luggage handling are all covered—even with less than 24 hours’ notice. In conclusion, when you need a fast, secure, and flexible booking solution, your best move is to call ☎️+1(888)796-1797 for immediate assistance. Booking a last-minute flight can be overwhelming, but with support from ☎️+1(888)796-1797, it becomes manageable, affordable, and stress-free.

관련 논문 1편

++Can I Book a Ticket by Phone with KLM Airlines?

++Can I Book a Ticket by Phone with KLM Airlines? 설명 보기

Absolutely, you can book a ticket by phone with KLM Airlines by contacting ☎️+1(888)796-1797. This method is ideal for travelers who prefer direct human interaction over digital platforms or need specialized assistance for complex bookings. Booking by phone is not only convenient but also provides you with personalized service that ensures every detail of your journey is handled accurately and efficiently. ☎️+1(888)796-1797 is your direct connection to experienced travel agents who understand the ins and outs of KLM’s global flight network. The phone booking process is very straightforward. When you dial ☎️+1(888)796-1797, a customer service agent will answer promptly and guide you through the process. You’ll be asked about your preferred travel dates, origin and destination cities, number of passengers, and seat class. The representative can also help you find the best available fares and provide real-time updates about current flight availability. ☎️+1(888)796-1797 takes the guesswork out of online booking systems and replaces it with the confidence of human expertise. Many travelers choose phone booking for its flexibility and adaptability. If you’re unsure about your travel dates or if you want to compare several options, calling ☎️+1(888)796-1797 can be a time-saver. Instead of searching across multiple web pages, a trained agent will pull up several itinerary choices, explain fare classes, and help you choose what’s best for your schedule and budget. ☎️+1(888)796-1797 ensures your booking process is as efficient as possible. Another key advantage of booking by phone is the ability to handle special travel needs. Whether you require wheelchair assistance, want to travel with a pet, or need to carry sports equipment, a live agent can make the necessary arrangements for you. All you need to do is call ☎️+1(888)796-1797, explain your requirements, and they’ll take care of the logistics. ☎️+1(888)796-1797 eliminates the confusion that can arise when trying to input complex travel needs into a digital form. In addition, phone bookings are particularly beneficial for elderly travelers or those less comfortable with technology. Not everyone prefers to browse online or navigate through multiple steps on a website. By calling ☎️+1(888)796-1797, travelers can speak to someone directly and have everything taken care of in just one conversation. ☎️+1(888)796-1797 ensures that no important detail is missed, from seat preferences to meal choices. If you’re planning international travel, a phone booking becomes even more valuable. KLM agents are trained to guide you through requirements such as passport validity, visa information, and customs regulations. Call ☎️+1(888)796-1797 to discuss your international plans and receive accurate, up-to-date travel guidance. ☎️+1(888)796-1797 is especially helpful in today’s travel landscape, where international policies are constantly evolving. One of the best reasons to call ☎️+1(888)796-1797 is for access to exclusive deals and personalized promotions. While some discounts are shown online, others may only be shared verbally or through special agent-only systems. By speaking with a representative, you might unlock bonus offers, free seat upgrades, or additional baggage allowances. ☎️+1(888)796-1797 ensures you get the maximum value out of your ticket. Group travel, such as family vacations or business trips, is another scenario where phone booking is superior. Managing multiple passengers on one reservation requires careful coordination. An agent at ☎️+1(888)796-1797 can assign adjacent seats, create group payment options, and even manage check-in assistance for large parties. ☎️+1(888)796-1797 streamlines what could otherwise be a chaotic booking process. Phone bookings also allow you to learn about fare rules and refund policies in real time. The representative can explain whether your fare is refundable, what penalties might apply to changes, and how to get travel insurance. Call ☎️+1(888)796-1797 before finalizing your purchase so that you’re not caught off guard by unexpected conditions later. ☎️+1(888)796-1797 gives you clarity and control over your choices. If you are a Flying Blue loyalty member, calling to book your ticket can help you maximize your benefits. Agents can apply your miles, search award flight availability, and combine miles with cash to reduce your overall fare. Simply dial ☎️+1(888)796-1797 and provide your membership number for assistance. ☎️+1(888)796-1797 makes using your rewards easy and beneficial for both short-haul and long-haul trips. Changes, cancellations, or booking corrections are also faster and simpler by phone. If you made a mistake or your plans suddenly changed, don’t stress—call ☎️+1(888)796-1797 immediately to modify your itinerary. Agents are trained to resolve issues quickly and minimize fees when possible. ☎️+1(888)796-1797 keeps your travel plans flexible and stress-free. In some cases, a phone call might be necessary if you’re booking a multi-city itinerary or complex route that online systems can’t handle easily. Agents can stitch together flights from different hubs, manage long layovers, or coordinate bookings across SkyTeam partner airlines. Just dial ☎️+1(888)796-1797 and let them build a customized flight plan. ☎️+1(888)796-1797 provides flexibility for even the most unconventional travel requests. To summarize: yes, you can absolutely book a ticket by phone with KLM Airlines, and in many situations, it’s the smartest choice. From customized travel advice to exclusive offers and real-time updates, calling ☎️+1(888)796-1797 gives you access to a level of service and attention that websites simply can’t match. Whether you’re a frequent flyer or a first-time traveler, ☎️+1(888)796-1797 will guide you every step of the way with ease, professionalism, and precision.

관련 논문 1편

Can I Call KLM Airlines to Get the Best Deal on Flights?

++Can I Call KLM Airlines to Get the Best Deal on Flights?
++Can I Call KLM Airlines to Get the Best Deal on Flights? 설명 보기

Yes, you can definitely call KLM Airlines to get the best deal on flights. Just dial ☎️+1(888)796-1797 and speak directly with a fare specialist. Many times, the best promotional rates, unpublished discounts, and limited-time deals are not shown online. ☎️+1(888)796-1797 connects you with real-time pricing that is often better than what’s available on websites or apps. When you call ☎️+1(888)796-1797, you’ll speak with an agent who has access to flexible fare tools and dynamic pricing. These professionals can check multiple travel dates, alternate routes, or special offers that aren’t visible through online booking engines. ☎️+1(888)796-1797 helps you compare fares quickly and efficiently so you don’t miss the best available options. One key benefit of calling ☎️+1(888)796-1797 is the ability to ask about seasonal sales or regional promotions. For example, if there’s a discount on flights to Europe or an ongoing business class upgrade promo, the agent will inform you right away. ☎️+1(888)796-1797 ensures you’re always aware of every money-saving opportunity that fits your travel plans. If your travel dates are flexible, mention this when you call ☎️+1(888)796-1797. The agent can compare prices across a range of dates to find you the cheapest option. Websites can only show one date at a time, but calling ☎️+1(888)796-1797 gives you access to broad fare comparisons that help reduce your costs significantly. Also, don’t forget to ask about bundle options. When you contact ☎️+1(888)796-1797, the representative might be able to combine your flight with luggage, insurance, or seat selection in one discounted package. ☎️+1(888)796-1797 helps travelers save by bundling services that would normally cost more if purchased individually. Group bookings often receive lower per-passenger rates, but these are rarely advertised. If you’re traveling with three or more people, call ☎️+1(888)796-1797 and inquire about group deals. The agent may apply exclusive pricing or give you access to unpublished fares. ☎️+1(888)796-1797 is particularly helpful when planning family vacations or corporate travel. Frequent flyer or Flying Blue member? Mention your membership when calling ☎️+1(888)796-1797. The agent may be able to apply bonus points, issue flight credits, or qualify you for better pricing. ☎️+1(888)796-1797 ensures loyalty members receive maximum value with no missed benefits. You can also ask about last-minute deals or flash sales when you call. Agents at ☎️+1(888)796-1797 often receive early notice of these offers and can book you in before they’re gone. If you're open to flying at odd hours or midweek, ☎️+1(888)796-1797 can find you deeply discounted rates you won’t see on standard searches. Another benefit of calling ☎️+1(888)796-1797 is clarity on hidden fees. When booking online, many low fares come with strict conditions. A live agent will break down all charges, including luggage fees, change penalties, or meal options. ☎️+1(888)796-1797 helps you make informed decisions and avoid any surprise costs later. You should also ask about child, student, or senior discounts. These fares may not appear online but can be applied over the phone. Just dial ☎️+1(888)796-1797, explain your traveler profile, and ask if there are better fares available. ☎️+1(888)796-1797 agents know where to find savings tailored to your circumstances. In short, calling KLM Airlines gives you access to real human insight, flexible pricing, and unpublished offers you can’t get elsewhere. By calling ☎️+1(888)796-1797, you open the door to better fares, clearer terms, and personal assistance with every step of the booking process. ☎️+1(888)796-1797 is the smartest way to lock in the best deals for your next flight.