Dataset Groups Activity Stream Talk2Car The Talk2Car dataset is a benchmark for language grounding for autonomous vehicles. It contains images of urban scenes and natural language commands referring to objects in the images. BibTex: @dataset{Hou_Pong_Chan_and_Mingxi_Guo_and_Cheng-Zhong_Xu_2025, abstract = {The Talk2Car dataset is a benchmark for language grounding for autonomous vehicles. It contains images of urban scenes and natural language commands referring to objects in the images.}, author = {Hou Pong Chan and Mingxi Guo and Cheng-Zhong Xu}, doi = {10.57702/i5a7vdwt}, institution = {No Organization}, keyword = {'autonomous vehicles', 'image-text matching', 'language grounding', 'natural language instructions', 'self-driving cars', 'trajectory prediction'}, month = {jan}, publisher = {TIB}, title = {Talk2Car}, url = {https://service.tib.eu/ldmservice/dataset/talk2car}, year = {2025} }
