{"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/mining-relations-among-cross-frame-affinities","title":"Mining Relations among Cross-Frame Affinities for Video Semantic Segmentation","arxiv_id":"2207.10436","date":"2022-07-21","proceeding":null,"authors":["Guolei Sun","Yun Liu","Hao Tang","Ajad Chhatkuli","Le Zhang","Luc van Gool"],"abstract":"The essence of video semantic segmentation (VSS) is how to leverage temporal information for prediction. Previous efforts are mainly devoted to developing new techniques to calculate the cross-frame affinities such as optical flow and attention. Instead, this paper contributes from a different angle by mining relations among cross-frame affinities, upon which better temporal information aggregation could be achieved. We explore relations among affinities in two aspects: single-scale intrinsic correlations and multi-scale relations. Inspired by traditional feature processing, we propose Single-scale Affinity Refinement (SAR) and Multi-scale Affinity Aggregation (MAA). To make it feasible to execute MAA, we propose a Selective Token Masking (STM) strategy to select a subset of consistent reference tokens for different scales when calculating affinities, which also improves the efficiency of our method. At last, the cross-frame affinities strengthened by SAR and MAA are adopted for adaptively aggregating temporal information. Our experiments demonstrate that the proposed method performs favorably against state-of-the-art VSS methods. The code is publicly available at https://github.com/GuoleiSun/VSS-MRCFA","url_abs":"https://arxiv.org/abs/2207.10436v1","url_pdf":"https://arxiv.org/pdf/2207.10436v1.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":"mining-relations-among-cross-frame-affinities","repo_url":"https://github.com/guoleisun/vss-mrcfa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-semantic-segmentation-on-vspw","task":"Video Semantic Segmentation","dataset":"VSPW","model":"MRCFA(MiT-B5)","rank_in_archive_order":4,"of":5,"metrics":{"mIoU":"49.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2207.10436","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.10436"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/guoleisun/vss-mrcfa","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/GuoleiSun/VSS-MRCFA","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"f12c251b12a0b87f","entry":"get_common","repo":"GuoleiSun/VSS-MRCFA","repo_kind":"official","path":"VC_perclip.py","file_url":"https://github.com/GuoleiSun/VSS-MRCFA/blob/HEAD/VC_perclip.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f12c251b12a0b87f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}