Papers with Code · CC BY-SA 4.0

데이터셋 탐색

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

관련 논문 45편

BEDLAM

BEDLAM 설명 보기

BEDLAM is a large-scale synthetic video dataset designed to train and test algorithms on the task of 3D human pose and shape estimation (HPS). It contains diverse body shapes, skin tones, and motions. The clothing is realistically simulated on the moving bodies using commercial clothing physics simulation.

관련 논문 45편

Brain-Score

Brain-Score 설명 보기

The Brain-Score platform aims to yield strong computational models of the ventral stream. We enable researchers to quickly get a sense of how their model scores against standardized brain benchmarks on multiple dimensions and facilitate comparisons to other state-of-the-art models. At the same time, new brain data can quickly be tested against a wide range of models to determine how well existing models explain the data. Brain-Score is organized by the Brain-Score team in collaboration with researchers and labs worldwide. We are working towards an easy-to-use platform where a model can easily be submitted to yield its scores on a range of brain benchmarks and new benchmarks can be incorporated to challenge the models. This quantified approach lets us keep track of how close our models are to the brain on a range of experiments (data) using different evaluation techniques (metrics). For more details, please refer to the technical paper and the perspective paper.

관련 논문 45편

Conversational Text-to-SQL Challenge

CoSQL
CoSQL 설명 보기

CoSQL is a corpus for building cross-domain, general-purpose database (DB) querying dialogue systems. It consists of 30k+ turns plus 10k+ annotated SQL queries, obtained from a Wizard-of-Oz (WOZ) collection of 3k dialogues querying 200 complex DBs spanning 138 domains. Each dialogue simulates a real-world DB query scenario with a crowd worker as a user exploring the DB and a SQL expert retrieving answers with SQL, clarifying ambiguous questions, or otherwise informing of unanswerable questions. Source: CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases

관련 논문 45편

DART

DART 설명 보기

DART is a large dataset for open-domain structured data record to text generation. DART consists of 82,191 examples across different domains with each input being a semantic RDF triple set derived from data records in tables and the tree ontology of the schema, annotated with sentence descriptions that cover all facts in the triple set. Source: DART: Open-Domain Structured Data Record to Text Generation

관련 논문 45편

Dynamic Facial Expression in the Wild

DFEW
DFEW 설명 보기

Recently, facial expression recognition (FER) in the wild has gained a lot of researchers’ attention because it is a valuable topic to enable the FER techniques to move from the laboratory to the real applications. In this paper, we focus on this challenging but interesting topic and make contributions from three aspects. First, we present a new large-scale ’in-the-wild’ dynamic facial expression database, DFEW (Dynamic Facial Expression in the Wild), consisting of over 16,000 video clips from thousands of movies. These video clips contain various challenging interferences in practical scenarios such as extreme illumination, occlusions, and capricious pose changes. Second, we propose a novel method called ExpressionClustered Spatiotemporal Feature Learning (EC-STFL) framework to deal with dynamic FER in the wild. Third, we conduct extensive benchmark experiments on DFEW using a lot of spatiotemporal deep feature learning methods as well as our proposed EC-STFL. Experimental results show that DFEW is a well-designed and challenging database, and the proposed EC-STFL can promisingly improve the performance of existing spatiotemporal deep neural networks in coping with the problem of dynamic FER in the wild. Our DFEW database is publicly available and can be freely downloaded from https://dfew-dataset.github.io/.

관련 논문 45편

Generation, Evaluation, and Metrics

GEM
GEM 설명 보기

Generation, Evaluation, and Metrics (GEM) is a benchmark environment for Natural Language Generation with a focus on its Evaluation, both through human annotations and automated Metrics. GEM aims to: - measure NLG progress across 13 datasets spanning many NLG tasks and languages. - provide an in-depth analysis of data and models presented via data statements and challenge sets. - develop standards for evaluation of generated text using both automated and human metrics. It is our goal to regularly update GEM and to encourage toward more inclusive practices in dataset development by extending existing data or developing datasets for additional languages. Source: https://gem-benchmark.com/ Image Source: Gehrmann et al

관련 논문 45편

Geometry3K

Geometry3K 설명 보기

A new large-scale geometry problem-solving dataset - 3,002 multi-choice geometry problems - dense annotations in formal language for the diagrams and text - 27,213 annotated diagram logic forms (literals) - 6,293 annotated text logic forms (literals)

관련 논문 45편

Humans Interacting with Common Objects

HICO
HICO 설명 보기

HICO is a benchmark for recognizing human-object interactions (HOI). Key features: - A diverse set of interactions with common object categories - A list of well-defined, sense-based HOI categories - An exhaustive labeling of co-occurring interactions with an object category in each image - The annotation of each HOI instance (i.e. a human and an object bounding box with an interaction class label) in all images Source: HICO: A Benchmark for Recognizing Human-Object Interactions in Images

관련 논문 45편

LasHeR

LasHeR 설명 보기

LasHeR consists of 1224 visible and thermal infrared video pairs with more than 730K frame pairs in total. Each frame pair is spatially aligned and manually annotated with a bounding box, making the dataset well and densely annotated. LasHeR is highly diverse capturing from a broad range of object categories, camera viewpoints, scene complexities and environmental factors across seasons, weathers, day and night.

관련 논문 45편

MultiLingual SUMmarization

MLSUM
MLSUM 설명 보기

A large-scale MultiLingual SUMmarization dataset. Obtained from online newspapers, it contains 1.5M+ article/summary pairs in five different languages -- namely, French, German, Spanish, Russian, Turkish. Together with English newspapers from the popular CNN/Daily mail dataset, the collected data form a large scale multilingual dataset which can enable new research directions for the text summarization community. Source: MLSUM: The Multilingual Summarization Corpus

관련 논문 45편

MSRDailyActivity3D

MSRDailyActivity3D 설명 보기

DailyActivity3D dataset is a daily activity dataset captured by a Kinect device. There are 16 activity types: drink, eat, read book, call cellphone, write on a paper, use laptop, use vacuum cleaner, cheer up, sit still, toss paper, play game, lay down on sofa, walk, play guitar, stand up, sit down. If possible, each subject performs an activity in two different poses: “sitting on sofa” and “standing”. The total number of the activity samples is 320. This dataset is designed to cover human’s daily activities in the living room. When the performer stands close to the sofa or sits on the sofa, the 3D joint positions extracted by the skeleton tracker are very noisy. Moreover, most of the activities involve the humans-object interactions. Thus this dataset is more challenging. Source: https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/06247813.pdf Image Source: https://www.researchgate.net/publication/308001852_Automatic_Learning_of_Articulated_Skeletons_Based_on_Mean_of_3D_Joints_for_Efficient_Action_Recognition

관련 논문 45편

THE MVTEC 3D ANOMALY DETECTION DATASET

MVTEC 3D-AD
MVTEC 3D-AD 설명 보기

MVTec 3D Anomaly Detection Dataset (MVTec 3D-AD) is a comprehensive 3D dataset for the task of unsupervised anomaly detection and localization. It contains over 4000 high-resolution scans acquired by an industrial 3D sensor. Each of the 10 different object categories comprises a set of defect-free training and validation samples and a test set of samples with various kinds of defects. Precise ground-truth annotations are provided for each anomalous test sample.

관련 논문 45편

Real Scenario Text-based Person Re-identification

RSTPReid
RSTPReid 설명 보기

RSTPReid contains 20505 images of 4,101 persons from 15 cameras. Each person has 5 corresponding images taken by different cameras with complex both indoor and outdoor scene transformations and backgrounds in various periods of time, which makes RSTPReid much more challenging and more adaptable to real scenarios. Each image is annotated with 2 textual descriptions. For data division, 3701 (index < 18505), 200 (18505 <= index < 19505) and 200 (index >= 19505) identities are utilized for training, validation and testing, respectively (Marked by item 'split' in the JSON file). Each sentence is no shorter than 23 words.

관련 논문 45편

Semantic Textual Similarity

STS Benchmark
STS Benchmark 설명 보기

STS Benchmark comprises a selection of the English datasets used in the STS tasks organized in the context of SemEval between 2012 and 2017. The selection of datasets include text from image captions, news headlines and user forums. Source: STS Benchmark

관련 논문 45편

ScanNet200

ScanNet200 설명 보기

The ScanNet200 benchmark studies 200-class 3D semantic segmentation - an order of magnitude more class categories than previous 3D scene understanding benchmarks. The source of scene data is identical to ScanNet, but parses a larger vocabulary for semantic and instance segmentation

관련 논문 45편

TACoS Multi-Level Corpus

TACoS Multi-Level Corpus 설명 보기

Augments the video-description dataset TACoS with short and single sentence descriptions. Source: Coherent Multi-Sentence Video Description with Variable Level of Detail

관련 논문 45편

Talk2Car

Talk2Car 설명 보기

The Talk2Car dataset finds itself at the intersection of various research domains, promoting the development of cross-disciplinary solutions for improving the state-of-the-art in grounding natural language into visual space. The annotations were gathered with the following aspects in mind: Free-form high quality natural language commands, that stimulate the development of solutions that can operate in the wild. A realistic task setting. Specifically, the authors consider an autonomous driving setting, where a passenger can control the actions of an Autonomous Vehicle by giving commands in natural language. The Talk2Car dataset was build on top of the nuScenes dataset to include an extensive suite of sensor modalities, i.e. semantic maps, GPS, LIDAR, RADAR and 360-degree RGB images annotated with 3D bounding boxes. Such variety of input modalities sets the object referral task on the Talk2Car dataset apart from related challenges, where additional sensor modalities are generally missing. Source: https://talk2car.github.io/ Image Source: https://github.com/talk2car/Talk2Car

관련 논문 45편

YouCook

YouCook 설명 보기

This data set was prepared from 88 open-source YouTube cooking videos. The YouCook dataset contains videos of people cooking various recipes. The videos were downloaded from YouTube and are all in the third-person viewpoint; they represent a significantly more challenging visual problem than existing cooking and kitchen datasets (the background kitchen/scene is different for many and most videos have dynamic camera changes). In addition, frame-by-frame object and action annotations are provided for training data (as well as a number of precomputed low-level features). Finally, each video has a number of human provided natural language descriptions (on average, there are eight different descriptions per video). This dataset has been created to serve as a benchmark in describing complex real-world videos with natural language descriptions. Source: A Thousand Frames in Just a Few Words: Lingual Description of Videos through Latent Topics and Sparse Object Stitching

관련 논문 44편

3RScan

3RScan 설명 보기

A novel dataset and benchmark, which features 1482 RGB-D scans of 478 environments across multiple time steps. Each scene includes several objects whose positions change over time, together with ground truth annotations of object instances and their respective 6DoF mappings among re-scans. Source: RIO: 3D Object Instance Re-Localization in Changing Indoor Environments

관련 논문 44편

BIWI

BIWI 설명 보기

The dataset contains over 15K images of 20 people (6 females and 14 males - 4 people were recorded twice). For each frame, a depth image, the corresponding rgb image (both 640x480 pixels), and the annotation is provided. The head pose range covers about +-75 degrees yaw and +-60 degrees pitch. Ground truth is provided in the form of the 3D location of the head and its rotation. Source: https://www.kaggle.com/kmader/biwi-kinect-head-pose-database Image Source: https://icu.ee.ethz.ch/research/datsets.html

관련 논문 44편

COCO-O

COCO-O 설명 보기

COCO-O(ut-of-distribution) contains 6 domains (sketch, cartoon, painting, weather, handmake, tattoo) of COCO objects which are hard to be detected by most existing detectors. The dataset has a total of 6,782 images and 26,624 labelled bounding boxes.

관련 논문 44편

EmotionLines

EmotionLines 설명 보기

EmotionLines contains a total of 29245 labeled utterances from 2000 dialogues. Each utterance in dialogues is labeled with one of seven emotions, six Ekman’s basic emotions plus the neutral emotion. Each labeling was accomplished by 5 workers, and for each utterance in a label, the emotion category with the highest votes was set as the label of the utterance. Those utterances voted as more than two different emotions were put into the non-neutral category. Therefore the dataset has a total of 8 types of emotion labels, anger, disgust, fear, happiness, sadness, surprise, neutral, and non-neutral. Source: Bridging Dialogue Generation and Facial Expression Synthesis Image Source: https://arxiv.org/pdf/1802.08379.pdf

관련 논문 44편

GPTFuzzer

GPTFuzzer 설명 보기

GPTFuzzer is a fascinating project that explores red teaming of large language models (LLMs) using auto-generated jailbreak prompts. Let's dive into the details: 1. Project Overview: - GPTFuzzer aims to assess the security and robustness of LLMs by crafting prompts that can potentially lead to harmful or unintended behavior. - The project focuses on GPT-3 and similar models. 2. Datasets: - The datasets used in GPTFuzzer include: - Harmful Questions: Sampled from public datasets like llm-jailbreak-study and hh-rlhf. - Human-Written Templates: Collected from llm-jailbreak-study. - Responses: Gathered by querying models like Vicuna-7B, ChatGPT, and Llama-2-7B-chat. 3. Models: - The judgment model is a finetuned RoBERTa-large model. - The training code and data are available in the repository. - During fuzzing experiments, the model is automatically downloaded and cached. 4. Updates: - The project has received recognition and awards at conferences like Geekcon 2023. - The team continues to improve the codebase and aims to build a general black-box fuzzing framework for LLMs. Source: Conversation with Bing, 3/17/2024 (1) sherdencooper/GPTFuzz: Official repo for GPTFUZZER - GitHub. https://github.com/sherdencooper/GPTFuzz. (2) GPTFUZZER : Red Teaming Large Language Models with Auto ... - GitHub. https://github.com/sherdencooper/GPTFuzz/blob/master/README.md. (3) GPTFUZZER : Red Teaming Large Language Models with Auto ... - GitHub. https://github.com/CriticalPulsar/GPTFuzz/blob/master/README.md. (4) undefined. https://avatars.githubusercontent.com/u/37368657?v=4. (5) undefined. https://github.com/sherdencooper/GPTFuzz/blob/master/README.md?raw=true. (6) undefined. https://desktop.github.com. (7) undefined. https://github.com/sherdencooper/GPTFuzz/raw/master/README.md. (8) undefined. https://opensource.org/licenses/MIT. (9) undefined. https://camo.githubusercontent.com/a4426cbe5c21edb002526331c7a8fbfa089e84a550567b02a0d829a98b136ad0/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f4c6963656e73652d4d49542d79656c6c6f772e737667. (10) undefined. https://img.shields.io/badge/License-MIT-yellow.svg. (11) undefined. https://arxiv.org/pdf/2309.10253.pdf. (12) undefined. https://sherdencooper.github.io/. (13) undefined. https://scholar.google.com/citations?user=Zv_rC0AAAAAJ&amp. (14) undefined. http://www.dataisland.org/. (15) undefined. http://xinyuxing.org/. (16) undefined. https://geekcon.darknavy.com/2023/china/en/index.html. (17) undefined. https://avatars.githubusercontent.com/u/35443979?v=4. (18) undefined. https://github.com/CriticalPulsar/GPTFuzz/blob/master/README.md?raw=true. (19) undefined. https://docs.github.com/articles/about-issue-and-pull-request-templates. (20) undefined. https://github.com/CriticalPulsar/GPTFuzz/raw/master/README.md. (21) undefined. https://scholar.google.com/citations?user=Zv_rC0AAAAAJ&hl=en.

관련 논문 44편

A Large-scale Multimodal Dataset for Continuous American Sign Language

How2Sign
How2Sign 설명 보기

The How2Sign is a multimodal and multiview continuous American Sign Language (ASL) dataset consisting of a parallel corpus of more than 80 hours of sign language videos and a set of corresponding modalities including speech, English transcripts, and depth. A three-hour subset was further recorded in the Panoptic studio enabling detailed 3D pose estimation.

관련 논문 44편

MC-TACO

MC-TACO 설명 보기

MC-TACO is a dataset of 13k question-answer pairs that require temporal commonsense comprehension. The dataset contains five temporal properties, (1) duration (how long an event takes), (2) temporal ordering (typical order of events), (3) typical time (when an event occurs), (4) frequency (how often an event occurs), and (5) stationarity (whether a state is maintained for a very long time or indefinitely). Source: MC-TACO

관련 논문 44편

Metal Parts Defect Detection Dataset

MPDD
MPDD 설명 보기

MPDD is a dataset aimed at benchmarking visual defect detection methods in industrial metal parts manufacturing. It consists of more than 1000 images with pixel-precise defect annotation masks. The dataset is divided into the training subset with anomaly-free samples and the validation subset that contains both normal and anomalous samples. The dataset can be downloaded at the following link.

관련 논문 44편

Original Chinese Natural Language Inference

OCNLI
OCNLI 설명 보기

OCNLI stands for Original Chinese Natural Language Inference. It is corpus for Chinese Natural Language Inference, collected following closely the procedures of MNLI, but with enhanced strategies aiming for more challenging inference pairs. No human/machine translation is used in creating the dataset, and thus the Chinese texts are original and not translated. OCNLI has roughly 50k pairs for training, 3k for development and 3k for test. Only the test data is released but not its labels. OCNLI is part of the CLUE benchmark. Source: OCNLI

관련 논문 44편

Occ3D

Occ3D 설명 보기

Occ3D is a dataset for 3D occupancy prediction, which aims to estimate the detailed occupancy and semantics of objects from multi-view images. To facilitate this task, a label generation pipeline that produces dense, visibility-aware labels for a given scene. This pipeline includes point cloud aggregation, point labeling, and occlusion handling. Source: Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving Image Source: Occ3D - Github Repo

관련 논문 44편

PeMSD8

PeMSD8 설명 보기

This dataset contains the traffic data in San Bernardino from July to August in 2016, with 170 detectors on 8 roads with a time interval of 5 minutes. This dataset is popular as a benchmark traffic forecasting dataset.

관련 논문 44편

SCUT-CTW1500

SCUT-CTW1500 설명 보기

The SCUT-CTW1500 dataset contains 1,500 images: 1,000 for training and 500 for testing. In particular, it provides 10,751 cropped text instance images, including 3,530 with curved text. The images are manually harvested from the Internet, image libraries such as Google Open-Image, or phone cameras. The dataset contains a lot of horizontal and multi-oriented text. Source: Text Recognition in the Wild: A Survey Image Source: https://github.com/Yuliang-Liu/Curve-Text-Detector

관련 논문 44편

TurkCorpus

TurkCorpus 설명 보기

TurkCorpus, a dataset with 2,359 original sentences from English Wikipedia, each with 8 manual reference simplifications. The dataset is divided into two subsets: 2,000 sentences for validation and 359 for testing of sentence simplification models.

관련 논문 43편

ChEBI-20

ChEBI-20 설명 보기

Dataset contains 33,010 molecule-description pairs split into 80%/10%/10% train/val/test splits. The goal of the task is to retrieve the relevant molecule for a natural language description. It is defined as follows: To push the boundaries of multimodal models, we present a new IR task: \textbf{Text2Mol}. Given a text query and list of molecules without any reference textual information (represented, for example, as SMILES strings, graphs, or other equivalent representations) retrieve the molecule corresponding to the query. From a text description of a molecule, the model must incorporate the information in the description into a semantic representation which can be used to directly retrieve the molecule. This requires the integration of two very different types of information: the structured knowledge represented by text and the chemical properties present in molecular graphs. We assume there is only one correct (relevant) molecule for each description, so we consider two measures for this task: Hits@1 and mean reciprocal rank (MRR). 80% of the data is used for training. Retrieval is done against the entire corpus of molecules (train, val, test).

관련 논문 43편

DensePASS

DensePASS 설명 보기

DensePASS - a novel densely annotated dataset for panoramic segmentation under cross-domain conditions, specifically built to study the Pinhole-to-Panoramic transfer and accompanied with pinhole camera training examples obtained from Cityscapes. DensePASS covers both, labelled- and unlabelled 360-degree images, with the labelled data comprising 19 classes which explicitly fit the categories available in the source domain (i.e. pinhole) data.

관련 논문 43편

EdNet

EdNet 설명 보기

A large-scale hierarchical dataset of diverse student activities collected by Santa, a multi-platform self-study solution equipped with artificial intelligence tutoring system. EdNet contains 131,441,538 interactions from 784,309 students collected over more than 2 years, which is the largest among the ITS datasets released to the public so far. Source: EdNet: A Large-Scale Hierarchical Dataset in Education

관련 논문 43편

ImageNet Semantic Segmentation

ImageNet-S
ImageNet-S 설명 보기

Powered by the ImageNet dataset, unsupervised learning on large-scale data has made significant advances for classification tasks. There are two major challenges to allowing such an attractive learning modality for segmentation tasks: i) a large-scale benchmark for assessing algorithms is missing; ii) unsupervised shape representation learning is difficult. We propose a new problem of large-scale unsupervised semantic segmentation (LUSS) with a newly created benchmark dataset to track the research progress. Based on the ImageNet dataset, we propose the ImageNet-S dataset with 1.2 million training images and 50k high-quality semantic segmentation annotations for evaluation. Our benchmark has a high data diversity and a clear task objective. We also present a simple yet effective baseline method that works surprisingly well for LUSS. In addition, we benchmark related un/weakly/fully supervised methods accordingly, identifying the challenges and possible directions of LUSS.

관련 논문 43편

L-Eval

L-Eval 설명 보기

Although large language models (LLMs) demonstrate impressive performance for many language tasks, most of them can only handle texts a few thousand tokens long, limiting their applications on longer sequence inputs, such as books, reports, and codebases. Recent works have proposed methods to improve LLMs' long context capabilities by extending context windows and more sophisticated memory mechanisms. However, comprehensive benchmarks tailored for evaluating long context understanding are lacking. In this paper, we introduce LongBench, the first bilingual, multi-task benchmark for long context understanding, enabling a more rigorous evaluation of long context understanding. LongBench comprises 21 datasets across 6 task categories in both English and Chinese, with an average length of 6,711 words (English) and 13,386 characters (Chinese). These tasks cover key long-text application areas including single-doc QA, multi-doc QA, summarization, few-shot learning, synthetic tasks, and code completion. All datasets in LongBench are standardized into a unified format, allowing for effortless automatic evaluation of LLMs. Upon comprehensive evaluation of 8 LLMs on LongBench, we find that: (1) Commercial model (GPT-3.5-Turbo-16k) outperforms other open-sourced models, but still struggles on longer contexts. (2) Scaled position embedding and fine-tuning on longer sequences lead to substantial improvement on long context understanding. (3) Context compression technique such as retrieval brings improvement for model with weak ability on long contexts, but the performance still lags behind models that have strong long context understanding capability. The code and datasets are available at https://github.com/THUDM/LongBench.

관련 논문 43편

MURA

MURA 설명 보기

A large dataset of musculoskeletal radiographs containing 40,561 images from 14,863 studies, where each study is manually labeled by radiologists as either normal or abnormal. Source: MURA: Large Dataset for Abnormality Detection in Musculoskeletal Radiographs

관련 논문 43편

MusicNet

MusicNet 설명 보기

MusicNet is a collection of 330 freely-licensed classical music recordings, together with over 1 million annotated labels indicating the precise time of each note in every recording, the instrument that plays each note, and the note's position in the metrical structure of the composition. The labels are acquired from musical scores aligned to recordings by dynamic time warping. The labels are verified by trained musicians; we estimate a labeling error rate of 4%. We offer the MusicNet labels to the machine learning and music communities as a resource for training models and a common benchmark for comparing results. Source: MusicNet

관련 논문 43편

NATS-Bench

NATS-Bench 설명 보기

A unified benchmark on searching for both topology and size, for (almost) any up-to-date NAS algorithm. NATS-Bench includes the search space of 15,625 neural cell candidates for architecture topology and 32,768 for architecture size on three datasets. Source: NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Size

관련 논문 43편

Occluded-DukeMTMC

Occluded-DukeMTMC 설명 보기

Occluded-DukeMTMC contains 15,618 training images, 17,661 gallery images, and 2,210 occluded query images. The experiment results on Occluded-DukeMTMC will demonstrate the superiority of our method in Occluded Person Re-ID problems, let alone that our method does not need any manually cropping procedure as pre-process.

관련 논문 43편

POP909

POP909 설명 보기

POP909 is a dataset which contains multiple versions of the piano arrangements of 909 popular songs created by professional musicians. The main body of the dataset contains the vocal melody, the lead instrument melody, and the piano accompaniment for each song in MIDI format, which are aligned to the original audio files. Furthermore, annotations are provided of tempo, beat, key, and chords, where the tempo curves are hand-labelled and others are done by MIR algorithms. Source: https://arxiv.org/pdf/2008.07142.pdf Image Source: https://arxiv.org/pdf/2008.07142.pdf

관련 논문 43편

PosePrior

PosePrior 설명 보기

Accurate modeling of priors over 3D human pose is fundamental to many problems in computer vision. Most previous priors are either not general enough for the diverse nature of human poses or not restrictive enough to avoid invalid 3D poses. We propose a physically-motivated prior that only allows anthropometrically valid poses and restricts the ones that are invalid. One can use joint-angle limits to evaluate whether two connected bones are valid or not. However, it is established in biomechanics that there are dependencies in joint-angle limits between certain pair of bones. For example how much one can flex one’s arm depends on whether it is in front of, or behind, the back. Medical textbooks only provide joint-angle limits in a few positions and the complete configuration of pose-dependent joint-angle limits for the full body is unknown.