{"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/target-adaptive-context-aggregation-for-video","title":"Target Adaptive Context Aggregation for Video Scene Graph Generation","arxiv_id":"2108.08121","date":"2021-08-18","proceeding":"ICCV 2021 10","authors":["Yao Teng","LiMin Wang","Zhifeng Li","Gangshan Wu"],"abstract":"This paper deals with a challenging task of video scene graph generation (VidSGG), which could serve as a structured video representation for high-level understanding tasks. We present a new {\\em detect-to-track} paradigm for this task by decoupling the context modeling for relation prediction from the complicated low-level entity tracking. Specifically, we design an efficient method for frame-level VidSGG, termed as {\\em Target Adaptive Context Aggregation Network} (TRACE), with a focus on capturing spatio-temporal context information for relation recognition. Our TRACE framework streamlines the VidSGG pipeline with a modular design, and presents two unique blocks of Hierarchical Relation Tree (HRTree) construction and Target-adaptive Context Aggregation. More specific, our HRTree first provides an adpative structure for organizing possible relation candidates efficiently, and guides context aggregation module to effectively capture spatio-temporal structure information. Then, we obtain a contextualized feature representation for each relation candidate and build a classification head to recognize its relation category. Finally, we provide a simple temporal association strategy to track TRACE detected results to yield the video-level VidSGG. We perform experiments on two VidSGG benchmarks: ImageNet-VidVRD and Action Genome, and the results demonstrate that our TRACE achieves the state-of-the-art performance. The code and models are made available at \\url{https://github.com/MCG-NJU/TRACE}.","url_abs":"https://arxiv.org/abs/2108.08121v1","url_pdf":"https://arxiv.org/pdf/2108.08121v1.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":[{"paper_slug":"target-adaptive-context-aggregation-for-video","repo_url":"https://github.com/mcg-nju/trace","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"graph-generation","task_name":"Graph Generation"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-prediction","task_name":"Relation Prediction"},{"task_slug":"scene-graph-generation","task_name":"Scene Graph Generation"},{"task_slug":"video-scene-graph-generation","task_name":"Video scene graph generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2108.08121","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}