{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/see-it-all-contextualized-late-aggregation","title":"See It All: Contextualized Late Aggregation for 3D Dense Captioning","arxiv_id":"2408.07648","date":"2024-08-14","proceeding":null,"authors":["Minjung Kim","Hyung Suk Lim","Seung Hwan Kim","Soonyoung Lee","Bumsoo Kim","Gunhee Kim"],"abstract":"3D dense captioning is a task to localize objects in a 3D scene and generate descriptive sentences for each object. Recent approaches in 3D dense captioning have adopted transformer encoder-decoder frameworks from object detection to build an end-to-end pipeline without hand-crafted components. However, these approaches struggle with contradicting objectives where a single query attention has to simultaneously view both the tightly localized object regions and contextual environment. To overcome this challenge, we introduce SIA (See-It-All), a transformer pipeline that engages in 3D dense captioning with a novel paradigm called late aggregation. SIA simultaneously decodes two sets of queries-context query and instance query. The instance query focuses on localization and object attribute descriptions, while the context query versatilely captures the region-of-interest of relationships between multiple objects or with the global scene, then aggregated afterwards (i.e., late aggregation) via simple distance-based measures. To further enhance the quality of contextualized caption generation, we design a novel aggregator to generate a fully informed caption based on the surrounding context, the global environment, and object instances. Extensive experiments on two of the most widely-used 3D dense captioning datasets demonstrate that our proposed method achieves a significant improvement over prior methods.","url_abs":"https://arxiv.org/abs/2408.07648v1","url_pdf":"https://arxiv.org/pdf/2408.07648v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"3d-dense-captioning","task_name":"3D dense captioning"},{"task_slug":"all","task_name":"All"},{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"caption-generation","task_name":"Caption Generation"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"dense-captioning","task_name":"Dense Captioning"},{"task_slug":"descriptive","task_name":"Descriptive"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-dense-captioning-on-scanrefer-dataset","task":"3D dense captioning","dataset":"ScanRefer Dataset","model":"See It All","rank_in_archive_order":2,"of":12,"metrics":{"BLEU-4":"42.17","CIDEr":"83.14","METEOR":"27.92","ROUGE-L":"59.44"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2408.07648","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}