In this paper, we aim to investigate the capabilities of multimodal machine learning models, particularly the OpenFlamingo model, in processing a large-scale dataset of consumer-to-consumer (C2C) online posts related to car parts. We have collected data from two platforms, OfferUp and Craigslist, resulting in a dataset of over 1.2 million posts with their corresponding images. The OpenFlamingo model was used to extract embeddings for the text and image of each post. We used $k$-means clustering on the joint embeddings to identify underlying patterns and commonalities among the posts. We have found that most clusters contain a pattern, but some clusters showed no internal patterns. The results provide insight into the fact that OpenFlamingo can be used for finding patterns in large datasets but needs some modification in the architecture according to the dataset.

Automotive related datasets have previously been used for training autonomous driving systems or vehicle classification tasks. However, there is a lack of datasets in the field of automotive AI for car parts detection, and most available datasets are limited in size and scope, struggling to cover diverse scenarios. To address this gap, this paper presents a large-scale and fine-grained automotive dataset consisting of 84,162 images for detecting 12 different types of car parts. This dataset was collected from natural cameras and online websites which covers various car brands, scenarios, and shooting angles. To alleviate the burden of manual annotation, we propose a novel semi-supervised auto-labeling method that leverages state-of-the-art pre-trained detectors. Moreover, we study the limitations of the Grounding DINO approach for zero-shot labeling. Finally, we evaluate the effectiveness of our proposed dataset through fine-grained car parts detection by training several lightweight YOLO-series detectors.

Elham Mansoori, member of Afghan Dreamers, an all-girls robotics team in Afghanistan, works on their prototype of a ventilator. In Afghanistan, a group of teenage girls are trying to build a mechanized, hand-operated ventilator for coronavirus patients, using a design from M.I.T. and parts from old Toyota Corollas. It sounds like an impossible dream, but then again, the all-girls robotics team in question is called the "Afghan Dreamers." Living a country where two-thirds of adolescent girls cannot read or write, they're used to overcoming challenges. The team of some dozen girls aged 15 to 17 was formed three years ago by Roya Mahboob, an Afghan tech entrepreneur who heads the Digital Citizen Fund, a group that runs classes for girls in STEM and robotics and oversees and funds the Afghan Dreamers.

Imagine picking out the perfect engine, wheels and steering system and then assembling the pieces together to make your dream car. That's how cars could be made in the future, according to Ford, who has built a giant 3D printer that can produce almost any part of a full-sized vehicle. The company said its invention could be used to produce cheap and light-weight 3D-printed cars, with personalised vehicle parts. To produce a 3D car part, the desired piece is first designed using a computer programme. Specifications for a part are then transferred from the programme to the printer's computer, which analyses the design.

When your closest sporting rivals are running a business with an annual team budget worth more than three times your own, then you need to be innovative in sustaining a challenge. And when it is in a cutting edge sport like Formula 1, then teams such as Williams Martini have to make sure every penny they spend is put to best inventive use. The UK-based team's IT director Graeme Hackland says they spend about £100m ($154m) a year in F1, compared with what he says is Mercedes' outlay of £300-350m, and Ferrari's of £250-300m. But despite the spending disparity, the UK-based team, which has won the constructor's table nine times, hopes that technology, rather than splashing cash, can help them close the gap. "We believe we can take them on," the 48-year-old South African, who has worked in F1 for 18 years, tells the BBC.

Created by British artist Giles Walker, the cyborg is joined by a robot DJ The robot stripper will appear at this week's Sexpo event in Melbourne It has a CCTV camera for a head and a body made from old shop mannequin pieces car parts The robot stripper will appear at this week's Sexpo event in Melbourne A robotic pole dancer with a CCTV camera for a head is set to put on an interesting display for visitors to an international sex show this week. Created by British artist Giles Walker, the gyrating cyborg is built from old shop mannequin pieces and car parts. The robot will be performing at the Sexpo trade event in Melbourne and is designed to explore the'relationship of voyeurism and power'. In a bizarre video, the robot can be seen gyrating its metal hips to music provided by a robot DJ, with a lamp for a head. The robot is one of a pair that were originally created in 2012 by Mr Walker for a show called'Peepshow'.

AUSTIN, Texas -- The race is on in Formula One. Not just to the checkered flag, but to see which team can marshall the best technology. In its 70th year, the preeminent auto-racing circuit has become a tech arms race. At the U.S. Grand Prix here this past weekend, the Internet of Things, big data, virtual reality, machine learning, 3-D printing, flash storage, predictive analytics and design play integral roles in the success (or failure) of the 22 drivers that compete in 21 races globally each year. The slightest advancement, or tweak, can mean the difference between first place and 10th place -- often the difference of one second.

This paper aims to highlight vision related tasks centered around "car", which has been largely neglected by vision community in comparison to other objects. We show that there are still many interesting car-related problems and applications, which are not yet well explored and researched. To facilitate future car-related research, in this paper we present our ongoing effort in collecting a large-scale dataset, "CompCars", that covers not only different car views, but also their different internal and external parts, and rich attributes. Importantly, the dataset is constructed with a cross-modality nature, containing a surveillancenature set and a web-nature set. We further demonstrate a few important applications exploiting the dataset, namely car model classification, car model verification, and attribute prediction. We also discuss specific challenges of the car-related problems and other potential applications that worth further investigations.