Papers with Code 아카이브

1 Image, 2*2 Stitching

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

하위 태스크
2
평가표
0
보존된 평가 기록
0

데이터셋

출처에 같은 태스크 이름으로 연결된 데이터셋입니다. 동명 태스크가 포함될 수 있으므로, 비교할 때는 평가 결과의 조건도 확인하세요.

NIR2RGB VCIP Challange Dataset

#This dataset provides the VCIP 2020 Grand Challenge on the NIR Image Colorization dataset. ##You can refer to https://jchenhkg.github.io/projects/NIR2RGB_VCIP_Challenge/ for a detailed description of this dataset. ## If you think this dataset is helpful, please feel free to cite our paper: @inproceedings{yang2023cooperative, title={Cooperative Colorization: Exploring Latent Cross-Domain Priors for NIR Image Spectrum Translation}, author={Yang, Xingxing and Chen, Jie and Yang, Zaifeng}, booktitle={Proceedings of the 31st ACM International Conference on Multimedia}, pages={2409--2417}, year={2023} }

Cam2BEV

The dataset contains two subsets of synthetic, semantically segmented road-scene images, which have been created for developing and applying the methodology described in the paper "A Sim2Real Deep Learning Approach for the Transformation of Images from Multiple Vehicle-Mounted Cameras to a Semantically Segmented Image in Bird’s Eye View" (IEEE Xplore, arXiv, YouTube) The dataset can be used through the official code implementation of the Cam2BEV methodology described on Github. | Dataset | # Training Samples | # Validation Samples | # Vehicle Cameras | # Semantic Classes | Contained Images (examples) | | --- | --- | --- | --- | --- | --- | | Dataset 1: 360° Surround | 33199 | 3731 | 4 (front, rear, left, right) | 30 (CityScapes) | front camera, rear camera, left camera, right camera, bird's eye view, [bird's eye view incl. occlusion](https://gitlab.ika.rwth-aachen.de/cam2bev/cam2bev-data/-/raw/master/1_FRLR/examples bev+occlusion.png), homography view | | Dataset 2: Front Camera only | 32246 | 3172 | 1 (front) | 30 (CityScapes) | front camera, bird's eye view, bird's eye view incl. occlusion, homography view |

Mila Simulated Floods

Mila Simulated Floods Dataset is a 1.5 square km virtual world using the Unity3D game engine including urban, suburban and rural areas. The urban environment contains skyscrapers, large buildings, and roads, as well as objects such as traffic items and vehicles. The rural environment consists of a landscape of grassy hills, forests, and mountains, with sparse houses and other buildings such as a church, and no roads. The rural and urban areas make up for 1 square km of our virtual world. The suburban environment is a residential area of 0.5 square km with many individual houses with front yards. To gather the simulated dataset, we captured before and after flood pairs from 2000 viewpoints with the following modalities: - non-flooded RGB image, depth map, segmentation map - flooded RGB image, binary mask of the flooded area, segmentation map The camera was placed about 1.5 above ground, and has a field of view of 120 degree, and the resolution of the images is 1200 x 900. At each viewpoint, we took 10 pictures, by varying slightly the position of the camera in order to augment the dataset.

OADAT

An experimental and synthetic (simulated) OA raw signals and reconstructed image domain datasets rendered with different experimental parameters and tomographic acquisition geometries. For detailed information, see github.com/berkanlafci/oadat.

####How do i ask a question at Expedia?

How Do I Ask a Question at Expedia? [Complete Guide + Support Numbers] When planning a trip, booking a hotel, or managing travel changes, it’s natural to have questions—especially when things don’t go as expected. Expedia, one of the world’s leading online travel agencies, provides multiple customer support options to help you ask questions and resolve travel-related issues effectively. Whether you’re wondering about a reservation, refund, or policy, this comprehensive guide will walk you through how to ask a question at Expedia, using various communication methods including phone, chat, email, and more. Need Quick Support? Call Expedia Helpline: 📞 +1-888-829-0881 OR 📞 +1-805-330-4056 Available 24/7 for personalized travel assistance. Why You Might Need to Ask a Question at Expedia There are dozens of situations where travelers seek clarification or support from Expedia. Some common scenarios include: Questions about flight/hotel bookings Modifying or canceling reservations Confirming check-in/check-out times Refund eligibility and delays Technical glitches on the Expedia website or app Issues with Expedia Rewards points Changing passenger details Payment errors or billing concerns Regardless of your concern, Expedia offers multiple channels to connect with their support team, get answers, and resolve your issues smoothly. 1. Ask a Question via Expedia Customer Service Helpline ✅ The Fastest Way to Get Help: Call a Live Representative Calling Expedia’s customer service hotline is the most direct and fastest way to ask a question and receive a real-time answer. 📞 Toll-Free Numbers: +1-888-829-0881 (General Inquiries) +1-805-330-4056 (Priority Support) These numbers are available 24/7 to assist with: Booking issues Account access Emergency changes Last-minute cancellations Refund processing Policy clarification When you call, make sure to have your itinerary number, registered email, and full name handy. This allows the agent to access your reservation quickly and provide faster assistance. 👨‍💼 Tip: If you are calling from outside the U.S., check if international call rates apply or consider using Skype or VoIP services to save on charges. 2. Use the Expedia Help Center If your question isn't urgent, you might find a quick answer in the Expedia Help Center. Here's how to use it: 🔍 Step-by-Step: Go to www.expedia.com Scroll to the bottom and click “Support” or “Help” Enter your question in the search bar Browse relevant articles, FAQs, and guides Topics covered include: “How to change a flight” “What is Expedia’s refund policy?” “How to manage travel credits” “How to apply a coupon” This section is perfect for general questions that don’t require live assistance. 3. Ask a Question Using Live Chat Expedia offers a Live Chat service for real-time support with less wait time compared to calling. It's great for asking simple to moderately complex questions. 💬 How to Access Live Chat: Visit www.expedia.com Log in to your Expedia account Click on “My Trips” to access your bookings Select a booking, scroll down to “Need Help?” Click “Chat Now” or “Contact Us” You’ll be connected to a virtual assistant first. If needed, you can request a human agent during the chat. 🌟 Pros of Using Chat: Available 24/7 Multilingual support, including Spanish Can attach screenshots or booking IDs Easy to copy the conversation for your records 4. Ask a Question via the Expedia App The Expedia Mobile App is another convenient platform to ask questions or get help on the go. Available on both iOS and Android, the app offers direct chat support and account management tools. 📱 Features: Access trips and bookings instantly Send messages to customer support Receive notifications about flight changes or cancellations Easily reschedule or cancel bookings To ask a question: Open the app Tap on “Trips” Select your reservation Tap “Help” or “Support” Choose to chat or call 5. Ask a Question by Email (For Non-Urgent Matters) If you have a non-urgent question or need documentation, you can send an email to Expedia. While email is slower than other methods, it’s helpful for situations that require written proof or escalations. 📧 Suggested Email Format: Subject: Issue with Booking #123456789 Body: Briefly explain your concern, include booking ID, and attach any relevant documents. Where to Send: Expedia does not prominently list a direct email, so it’s best to submit your query via their “Contact Us” page which will route your message to the appropriate department. Alternatively, after chatting with a virtual agent, you can request an email follow-up. 6. Contact Expedia via Social Media For general questions, updates, or public-facing concerns, you can message or tag Expedia on social platforms: Twitter: @Expedia Facebook: Expedia Facebook Page Instagram: @Expedia While these channels may not handle complex issues, the social media team can direct you to the right department quickly. 7. Ask a Question Through the Virtual Agent Expedia’s AI-powered Virtual Agent is available 24/7 to handle common questions and requests. 🚀 What the Virtual Agent Can Help With: Rebooking canceled flights Answering policy-related questions Finding travel documents Tracking refund status Providing check-in instructions To access the Virtual Agent: Visit Expedia Help Center Click “Chat Now” Start typing your question If the bot can’t resolve your issue, type “Talk to a person” or “Speak to a live agent.” What to Include When Asking a Question To ensure your question is answered quickly and correctly, always include: Full name on booking Itinerary or confirmation number Email address linked to the Expedia account Phone number (optional) A clear and concise explanation of the issue This prevents delays and allows agents to locate your account immediately. Common Questions Customers Ask Expedia Here are examples of the most frequently asked questions that Expedia agents receive: “How can I cancel my flight or hotel booking?” “When will I get my refund?” “Can I change the dates of my reservation?” “My credit card was charged twice—what do I do?” “How do I apply Expedia points to my booking?” “The hotel didn’t honor my booking—what now?” “Where can I find my itinerary?” “How do I contact the airline directly through Expedia?” Expedia’s support staff is trained to handle these and more, so don’t hesitate to ask. When Should You Escalate Your Question? If your issue isn’t being resolved, or if you've waited several days without a response, it’s time to escalate. 🚨 Escalation Steps: Call customer support again and request to speak with a supervisor Ask for a callback or escalation through chat or virtual assistant If the issue is unresolved after 5–7 business days, consider writing to Expedia’s corporate office or tagging them on Twitter for visibility. You can also call the Expedia priority helpline at +1-805-330-4056 for faster action. Expedia Customer Support Hours Phone Support: 24/7 (including weekends & holidays) Live Chat: 24/7 Help Center: Available anytime Social Media: Responsive between 9 AM to 8 PM (local time) Important Travel Tips When Asking a Question Always keep a copy of your booking confirmation Contact support as early as possible before your travel date If using chat, save a transcript for reference Be polite and concise—support agents are more likely to go above and beyond Final Thoughts Asking a question at Expedia is straightforward thanks to their multi-channel support system. Whether it’s a quick FAQ, a booking problem, or an urgent travel change, Expedia offers several ways to get the help you need. For immediate answers, call their toll-free numbers: 📞 +1-888-829-0881 or 📞 +1-805-330-4056 And if you prefer digital communication, their Live Chat, App, and Help Center have got you covered. FAQs 🔹 Is Expedia customer service available 24/7? Yes, both phone and chat support are available 24/7. 🔹 How long does it take to get a refund? Typically 7–14 business days, depending on your payment method and travel partner policy. 🔹 Can I talk to an agent in Spanish or another language? Yes, multilingual support is available via phone and chat. If you found this guide helpful, consider saving it for future reference or sharing it with fellow travelers. Safe travels!

2007 BP Anisotropic Velocity Benchmark

The 2007 BP TTI Velocity-Analysis Benchmark dataset was created by Hemang Shah and provided courtesy of BP Exploration Operation Company Limited ("BP"). It was originally used at the velocity-analysis workshop at the 2010 EAGE meeting in Barcelona, Spain.

[[FAQs~Communication]]How Do I Communicate to Expedia?

To Communicate with Expedia customer service, you can call 1-800-Expedia (1-888-829-0881). You can also contact Expedia customer service via their customer support page and virtual agent.1-888-829-0881 If you need to cancel a flight, you can do so on Expedia up to 24 hours before the scheduled departure time 1-888-829-0881. If you cancel within this time frame, you will receive a full refund of your flight booking, including any fees for seats or bags. You can call Expedia at 1-888-829-0881 to cancel your flight. For more information on Expedia Corporate Travel, you can call 1-888-829-0881. On Expedia, the "refundable option" refers to their 24-hour cancellation policy 1-888-829-0881, which allows you to cancel most bookings within 24 hours of purchase and receive a full refund, as long as your travel date is at least a week away; essentially, you can get a full refund if you cancel within 24 hours of booking. Key points about Expedia's refundable option:1-888-829-0881 24-hour window: You have 24 hours from the time of booking to cancel for a full refund.1-888-829-0881 Travel date requirement: The flight departure date must usually be at least a week away to be eligible for a full refund.1-888-829-0881 Contact customer service: To initiate a refund, you need to contact Expedia's customer service. 1-888-829-0881 Expedia offers a "24-hour risk-free cancellation"1-888-829-0881 policy, which means you can cancel most bookings within 24 hours of making them for a full refund, as long as the travel date is at least 7 days away from departure; you can contact their customer service to initiate a cancellation. 1-888-829-0881 Key points about Expedia's cancellation policy:1-888-829-0881 24-hour window: You have 24 hours from the time of booking to cancel for a full refund. 1-888-829-0881 Applies to most bookings: This policy generally applies to flights, hotels, and car rentals. Check-in date requirement: The travel date must be at least 7 days away for the full refund to apply. 1-888-829-0881 Contact customer service: To cancel within the 24-hour window, you need to contact Expedia's customer service.1-888-829-0881

CARLA2Real

This dataset contains synthetic images extracted from the CARLA simulator along with rich information extracted from the deferred rendering pipeline of Unreal Engine 4. The main purpose of this dataset is the training of the state-of-the-art image-to-image translation model proposed by Intel Labs "Enhancing Photorealism Enhancement" (EPE). Translation results derived from the model targeting the characteristics of Cityscapes, KITTI, and Mapillary Vistas are also provided. Computer vision-based models trained on these data are expected to perform better when deployed in the real world.

CPM-Synt-1

CPM-Synt-1 is a dataset consisting of 5555 images with synthesis - makeup images with pattern segmentation mask

CPM-Synt-2

CPM-Synt-2 is a dataset consisting of 1625 images with synthesis - triplets: makeup, non-makeup, ground-truth.

GANGen-Detection

This dataset was created to test whether it's possible to build a general-purpose detector that can tell real images apart from fake ones generated by convolutional neural networks (CNNs), no matter which model or dataset was used to create the fake images. To do this, the authors collected fake images generated by 11 different CNN-based image generation models. These models represent a wide range of current image synthesis techniques and include: ProGAN StyleGAN BigGAN CycleGAN StarGAN GauGAN DeepFakes Cascaded Refinement Networks (CRN) Implicit Maximum Likelihood Estimation (IMLE) Second-order Attention Super-Resolution (SOAT-SR) Seeing-in-the-Dark (SID) The dataset includes fake images from each of these models and a set of real images, allowing for binary classification (real vs. fake). The study found that a standard image classifier (like a convolutional neural network) trained on fake images from just one generator (ProGAN) was able to detect fake images from other, completely different generators with surprising accuracy. This suggests that many CNN-generated images, even from different architectures, share common flaws that can be learned and detected. The dataset is useful for research in detecting synthetic media, improving image forensics, and understanding the weaknesses in current generative models. Code and pre-trained models were made available by the authors (https://github.com/chuangchuangtan/GANGen-Detection).

LISA Gaze Dataset

LISA Gaze is a dataset for driver gaze estimation comprising of 11 long drives, driven by 10 subjects in two different cars. Source: Driver Gaze Zone Estimation using Convolutional Neural Networks: A General Framework and Ablative Analysis

PEnG

This dataset builds upon the SpaGBOL dataset - a graph-based dataset covering numerous cities across the globe for the purpose of structured city-scale Cross-View Geo-Localisation (CVGL). We introduce the idea of Multi-View Geo-Localisation (MVGL) - localising in two steps within a graph. First using CVGL to retrieve the most likely primary nodes (road junctions), before performing relative pose estimation also candidate edges to increase precision. The corresponding initial network proposed reduced median error from hundreds of metres down to approximately 22m error across the entire dataset.

RASMD

Current autonomous driving algorithms heavily rely on the visible spectrum, which is prone to performance degradation in adverse conditions like fog, rain, snow, glare, and high contrast. Although other spectral bands like near-infrared (NIR) and long-wave infrared (LWIR) can enhance vision perception in such situations, they have limitations and lack large-scale datasets and benchmarks. Short-wave infrared (SWIR) imaging offers several advantages over NIR and LWIR. However, no publicly available large-scale datasets currently incorporate SWIR data for autonomous driving. To address this gap, we introduce the RGB and SWIR Multispectral Driving (RASMD) dataset, which comprises 100,000 synchronized and spatially aligned RGB-SWIR image pairs collected across diverse locations, lighting, and weather conditions. In addition, we provide a subset for RGB-SWIR translation and object detection annotations for a subset of challenging traffic scenarios to demonstrate the utility of SWIR imaging through experiments on both object detection and RGB-to-SWIR image translation. Our experiments show that combining RGB and SWIR data in an ensemble framework significantly improves detection accuracy compared to RGB-only approaches, particularly in conditions where visible-spectrum sensors struggle. We anticipate that the RASMD dataset will advance research in multispectral imaging for autonomous driving and robust perception systems.

TwinSynths

The TwinSynths dataset is a novel benchmark designed to overcome common limitations found in earlier synthetic image datasets, such as low image quality, inadequate content preservation, and limited class diversity. TwinSynths generates pairs of images where each synthetic image is visually identical to its real counterpart, ensuring that the essential content remains intact while showcasing the unique architectural features of the generative models used. TwinSynths comprises two subsets: TwinSynths-GAN This subset uses a GAN generator architecture which trained from scratch on individual real images using a mean-squared error loss to ensure pixel-level fidelity. By fixing the latent vector input, the method produces synthetic images that closely mirror the original content. The GAN subset consists of 8,000 generated images spanning 80 classes selected from ImageNet. TwinSynths-DM For the diffusion model-based subset, DDIM inversion is used to maintain the content integrity of the original images. By applying a noise-adding forward process followed by a text-conditioned denoising procedure (using class name prompts), this generates synthetic images that are highly similar to their real counterparts. The same set of ImageNet classes is used as in the GAN subset, allowing for a consistent evaluation across different generative methods.

WinSyn

75k photos of windows + 21k synthetic renders of building windows.

Corn Seeds Dataset

This dataset is the images of corn seeds considering the top and bottom view independently (two images for one corn seed: top and bottom). There are four classes of the corn seed (Broken-B, Discolored-D, Silkcut-S, and Pure-P) 17802 images are labeled by the experts at the AdTech Corp. and 26K images were unlabeled out of which 9k images were labeled using the Active Learning (BatchBALD) We have created three different dataset: (1). Primary dataset: contains the 17802 images labeled by the experts. Top-view(8901) and Bottom-view(8901). (2). Dataset with fake images: We generated fake images using Conditional GAN (BigGAN) as follows: broken-2937, discolored-5823, pure-2937, silkcut-5823 instances and added them into the train set to balance the data set. (3). Balanced dataset: In this case of adding newly captured images labeled using the Batch Active Learning method, new 9000 labeled images are added into the primary dataset. This new dataset contains 26,802 images split into train and validation set 80: 20, respectively. Contains the 17802 images and the 9K images labeled by the Active Learning (BatchBALD).

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.