{"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/per-clip-video-object-segmentation-1","title":"Per-Clip Video Object Segmentation","arxiv_id":"2208.01924","date":"2022-08-03","proceeding":"CVPR 2022 1","authors":["KwanYong Park","Sanghyun Woo","Seoung Wug Oh","In So Kweon","Joon-Young Lee"],"abstract":"Recently, memory-based approaches show promising results on semi-supervised video object segmentation. These methods predict object masks frame-by-frame with the help of frequently updated memory of the previous mask. Different from this per-frame inference, we investigate an alternative perspective by treating video object segmentation as clip-wise mask propagation. In this per-clip inference scheme, we update the memory with an interval and simultaneously process a set of consecutive frames (i.e. clip) between the memory updates. The scheme provides two potential benefits: accuracy gain by clip-level optimization and efficiency gain by parallel computation of multiple frames. To this end, we propose a new method tailored for the per-clip inference. Specifically, we first introduce a clip-wise operation to refine the features based on intra-clip correlation. In addition, we employ a progressive matching mechanism for efficient information-passing within a clip. With the synergy of two modules and a newly proposed per-clip based training, our network achieves state-of-the-art performance on Youtube-VOS 2018/2019 val (84.6% and 84.6%) and DAVIS 2016/2017 val (91.9% and 86.1%). Furthermore, our model shows a great speed-accuracy trade-off with varying memory update intervals, which leads to huge flexibility.","url_abs":"https://arxiv.org/abs/2208.01924v1","url_pdf":"https://arxiv.org/pdf/2208.01924v1.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":"per-clip-video-object-segmentation-1","repo_url":"https://github.com/pkyong95/PCVOS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"semi-supervised-video-object-segmentation","task_name":"Semi-Supervised Video Object Segmentation"},{"task_slug":"video-object-segmentation","task_name":"Video Object Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2208.01924","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.01924"}},"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/pkyong95/PCVOS","reach":null}],"summary":{"ran_draft_wrong":3,"ran_fixture":1,"unverified":8},"by_repo_kind":{"official":{"samples":12,"ran":4,"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":12,"samples":[{"code_sha256_prefix":"e7f0c41c3a51a187","entry":"aggregate","repo":"pkyong95/PCVOS","repo_kind":"official","path":"inference_core_yv.py","file_url":"https://github.com/pkyong95/PCVOS/blob/HEAD/inference_core_yv.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"e7f0c41c3a51a187"}},{"code_sha256_prefix":"16139a51bd773319","entry":"compute_mask","repo":"pkyong95/PCVOS","repo_kind":"official","path":"inference_core_yv.py","file_url":"https://github.com/pkyong95/PCVOS/blob/HEAD/inference_core_yv.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"16139a51bd773319"}},{"code_sha256_prefix":"d062b5d27d1addee","entry":"softmax_w_top","repo":"pkyong95/PCVOS","repo_kind":"official","path":"inference_core_yv.py","file_url":"https://github.com/pkyong95/PCVOS/blob/HEAD/inference_core_yv.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"d062b5d27d1addee"}},{"code_sha256_prefix":"4876d8faacbd6927","entry":"window_partition","repo":"pkyong95/PCVOS","repo_kind":"official","path":"inference_core_yv.py","file_url":"https://github.com/pkyong95/PCVOS/blob/HEAD/inference_core_yv.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"4876d8faacbd6927"}},{"code_sha256_prefix":"4efb16c4894ebc50","entry":"BasicLayer","repo":"pkyong95/PCVOS","repo_kind":"official","path":"inference_core_yv.py","file_url":"https://github.com/pkyong95/PCVOS/blob/HEAD/inference_core_yv.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"4efb16c4894ebc50"}},{"code_sha256_prefix":"0b794cfed5a3d19c","entry":"ICR","repo":"pkyong95/PCVOS","repo_kind":"official","path":"inference_core_yv.py","file_url":"https://github.com/pkyong95/PCVOS/blob/HEAD/inference_core_yv.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"0b794cfed5a3d19c"}},{"code_sha256_prefix":"f4eaf70ba0d5babe","entry":"InferenceCore_Per_Clip","repo":"pkyong95/PCVOS","repo_kind":"official","path":"inference_core_yv.py","file_url":"https://github.com/pkyong95/PCVOS/blob/HEAD/inference_core_yv.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"f4eaf70ba0d5babe"}},{"code_sha256_prefix":"e1b6bc0bb5d9568c","entry":"MemoryBank","repo":"pkyong95/PCVOS","repo_kind":"official","path":"inference_core_yv.py","file_url":"https://github.com/pkyong95/PCVOS/blob/HEAD/inference_core_yv.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"e1b6bc0bb5d9568c"}},{"code_sha256_prefix":"d8b149bcaec9e608","entry":"PCVOS","repo":"pkyong95/PCVOS","repo_kind":"official","path":"inference_core_yv.py","file_url":"https://github.com/pkyong95/PCVOS/blob/HEAD/inference_core_yv.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"d8b149bcaec9e608"}},{"code_sha256_prefix":"100ffb20b54172cc","entry":"SwinTransformerBlock3D","repo":"pkyong95/PCVOS","repo_kind":"official","path":"inference_core_yv.py","file_url":"https://github.com/pkyong95/PCVOS/blob/HEAD/inference_core_yv.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"100ffb20b54172cc"}},{"code_sha256_prefix":"4a096c4688483280","entry":"WindowAttention3D","repo":"pkyong95/PCVOS","repo_kind":"official","path":"inference_core_yv.py","file_url":"https://github.com/pkyong95/PCVOS/blob/HEAD/inference_core_yv.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"4a096c4688483280"}},{"code_sha256_prefix":"e2791c3e738b1049","entry":"build_Intra_Clip_Refinement","repo":"pkyong95/PCVOS","repo_kind":"official","path":"inference_core_yv.py","file_url":"https://github.com/pkyong95/PCVOS/blob/HEAD/inference_core_yv.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"e2791c3e738b1049"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}