Dataset Groups Activity Stream RVOS-D RVOS-D provides more complex language descriptions from a broader object categories within relatively longer video sequences. BibTex: @dataset{Seonguk_Seo_and_Joon-Young_Lee_and_Bohyung_Han_2024, abstract = {RVOS-D provides more complex language descriptions from a broader object categories within relatively longer video sequences.}, author = {Seonguk Seo and Joon-Young Lee and Bohyung Han}, doi = {10.57702/7v0gq2jz}, institution = {No Organization}, keyword = {'Complex Language Descriptions', 'Natural Language Reference', 'Referring Video Object Segmentation', 'Video Object Segmentation'}, month = {dec}, publisher = {TIB}, title = {RVOS-D}, url = {https://service.tib.eu/ldmservice/dataset/rvos-d}, year = {2024} }
