1,082 datasets found

Street image and satellite image data can capture urban qualities and improve house price estimation.

Channel attention mechanisms endeavor to recalibrate channel weights to enhance representation abilities of networks.

The dataset consists of 80,000 robot trajectories collected via human teleoperation, with 2,800 demonstrations labeled by crowd-sourced language annotators.

Data-driven Instruction Augmentation for Language-conditioned Control (DIAL) is a method that uses pre-trained vision-language models (VLMs) to label offline datasets for...

The dataset used in the paper is the DVGO dataset, which contains 3D scenes and is used for training and testing the proposed neural radiance field model.

The dataset used in the paper is the LF dataset, which contains real-world scenes and is used for training and testing the proposed neural radiance field model.

The KITTI 2012 and 2015 datasets are used for stereo matching experiments.

The dataset used in the paper is the COCO object detection and instance segmentation dataset, and the ADE20K semantic segmentation dataset.

The proposed binary model is built on modeling contextual dependencies. An overview of the BCDNet architecture is illustrate in Fig. 4. We first describe the fundamentals of...

Counterfactual explanations and adversarial attacks have a related goal: flipping output labels with minimal perturbations regardless of their characteristics.

Camouflaged object detection (COD) aims to search and segment camouflaged objects from single image.

The dataset used in the paper is a large-scale dataset for autonomous driving and UAV racing, generated using the Sim4CV simulator.

The dataset used in the paper for object detection, self-driving, and UAV racing tasks.

The dataset used in the paper is the CIFAR-100 and ImageNet datasets.

The Vision-and-Language Navigation (VLN) task gives a global natural sentence I = {w0,..., wl} as an instruction, where wi is a word token while the l is the length of the...

The Waymo Open Dataset and the nuScenes Dataset are used to evaluate the performance of the AFDetV2 model.

Symmetric parallax attention for stereo image super-resolution.

Learning parallax attention for stereo image super-resolution.

Stereo image super-resolution aims at enhancing the quality of super-resolution results by utilizing the complementary information provided by binocular systems.

Stereo image super-resolution aims at enhancing the quality of super-resolution results by utilizing the complementary information provided by binocular systems.