{"id":"2302.04676","title":"Stacked Cross-modal Feature Consolidation Attention Networks for Image Captioning","url":"https://codeofpaper.com/paper/2302.04676","arxiv_url":"https://arxiv.org/abs/2302.04676","published":"2023-02-08","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":1}