Department of Computer Engineering2024-11-092022978-1-6654-8739-910.1109/CVPRW56347.2022.005072-s2.0-85137780572http://dx.doi.org/10.1109/CVPRW56347.2022.00507https://hdl.handle.net/20.500.14288/11902How to best integrate linguistic and perceptual processing in multi-modal tasks that involve language and vision is an important open problem. In this work, we argue that the common practice of using language in a top-down manner, to direct visual attention over high-level visual features, may not be optimal. We hypothesize that the use of language to also condition the bottom-up processing from pixels to high-level features can provide benefits to the overall performance. To support our claim, we propose a U-Net-based model and perform experiments on two language-vision dense-prediction tasks: referring expression segmentation and language-guided image colorization. We compare results where either one or both of the top-down and bottom-up visual branches are conditioned on language. Our experiments reveal that using language to control the filters for bottom-up visual processing in addition to top-down attention leads to better results on both tasks and achieves competitive performance. Our linguistic analysis suggests that bottom-up conditioning improves segmentation of objects especially when input text refers to low-level visual concepts. Code is available at https://github.com/ilkerkesen/bvpr.Computer scienceArtificial intelligenceConference proceeding8616127040724541