35 datasets found

22 videos of dynamic textures with time-varying visual statistics are collected. The raw data in their original resolutions and formats (MP4 videos). The data includes many...

A dataset of 21 flash-lit videos of time-varying materials is acquired, by a simple-to-construct setup. The data is pre-processed by the following protocol, and ready to use:...

22 videos of dynamic textures with time-varying visual statistics are collected. The data is pre-processed by the following protocol, and ready to use: each video is 5-second...

A dataset of 21 flash-lit videos of time-varying materials is acquired, by a simple-to-construct setup. The raw data in their original resolutions and formats (DNG photographs...

This dataset contains error annotations used in our IEEE RA-L paper titled 'SEDMamba: Enhancing Selective State Space Modelling with Bottleneck Mechanism and Fine-to-Coarse...

The first public dataset containing action annotations of the endoscopic TransSphenoidal Approach (eTSA), consisting of 4 action annotations. The action annotations are given in...

Preprocessed EndoVis 2017 [1], EndoVis 2018 [2], and SAR-RARP [3] datasets for federated instrument segmentation. [1] M. Allan, “2017 robotic instrument segmentation...

This repository contains trained weights for object detection and ellipse prediction for visual localization. These weights were trained on the Chess scene of the 7-Scenes...

Test sequences of two indoor scenes used to evaluate semantic visual SLAM (Simultaneous Localization And Mapping). This repository also contains Yolo v5 weights for object...

The Eiffel Tower active hydrothermal chimney is a major edifice investigated in deep-sea vent ecology at the Lucky Strike hydrothermal field (~ -1700 m), along the northern...

The Eiffel Tower active hydrothermal chimney is a major edifice investigated in deep-sea vent ecology at the Lucky Strike hydrothermal field (~ -1700 m), along the northern...

The LoTuS research project has developed a pilot cleaning system as a research and demonstration facility. Accompanying this, the LoTuS Expert System ("LoTuS Expertensystem")...

The dataset contains UAV footage of wild antelopes (blackbucks) in grassland habitats. It can be mainly used for two tasks: Multi-object tracking (MOT) and Re-Identification...

This repo contains the I3D data used for the paper "Sign Language Translation from Instructional Videos". Together with the data, and weights of models, we also provide the .tsv...

How2Sign consists of a parallel corpus of 80 hours of sign language videos (collected with multi-view RGB and depth sensor data) with corresponding speech transcriptions and...