{"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/2408-00169","title":"Strike the Balance: On-the-Fly Uncertainty based User Interactions for Long-Term Video Object Segmentation","arxiv_id":"2408.00169","date":"2024-07-31","proceeding":null,"authors":["Stéphane Vujasinović","Stefan Becker","Sebastian Bullinger","Norbert Scherer-Negenborn","Michael Arens","Rainer Stiefelhagen"],"abstract":"In this paper, we introduce a variant of video object segmentation (VOS) that bridges interactive and semi-automatic approaches, termed Lazy Video Object Segmentation (ziVOS). In contrast, to both tasks, which handle video object segmentation in an off-line manner (i.e., pre-recorded sequences), we propose through ziVOS to target online recorded sequences. Here, we strive to strike a balance between performance and robustness for long-term scenarios by soliciting user feedback's on-the-fly during the segmentation process. Hence, we aim to maximize the tracking duration of an object of interest, while requiring minimal user corrections to maintain tracking over an extended period. We propose a competitive baseline, i.e., Lazy-XMem, as a reference for future works in ziVOS. Our proposed approach uses an uncertainty estimation of the tracking state to determine whether a user interaction is necessary to refine the model's prediction. To quantitatively assess the performance of our method and the user's workload, we introduce complementary metrics alongside those already established in the field. We evaluate our approach using the recently introduced LVOS dataset, which offers numerous long-term videos. Our code is publicly available at https://github.com/Vujas-Eteph/LazyXMem.","url_abs":"https://arxiv.org/abs/2408.00169v2","url_pdf":"https://arxiv.org/pdf/2408.00169v2.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":"2408-00169","repo_url":"https://github.com/vujas-eteph/lazyxmem","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic 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=2408.00169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.00169"}},"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/vujas-eteph/lazyxmem","reach":{"status":"ok","spdx":"GPL-3.0"}}],"summary":{"ran":13,"unverified":2},"by_repo_kind":{"official":{"samples":15,"ran":13,"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":15,"samples":[{"code_sha256_prefix":"add9d1273a2b1e30","entry":"aggregate","repo":"vujas-eteph/lazyxmem","repo_kind":"official","path":"model/aggregate.py","file_url":"https://github.com/vujas-eteph/lazyxmem/blob/HEAD/model/aggregate.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"add9d1273a2b1e30"}},{"code_sha256_prefix":"3903fb53c9bc4ae2","entry":"dice_loss","repo":"vujas-eteph/lazyxmem","repo_kind":"official","path":"model/losses.py","file_url":"https://github.com/vujas-eteph/lazyxmem/blob/HEAD/model/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"3903fb53c9bc4ae2"}},{"code_sha256_prefix":"dc5d821a03594011","entry":"do_softmax","repo":"vujas-eteph/lazyxmem","repo_kind":"official","path":"model/memory_util.py","file_url":"https://github.com/vujas-eteph/lazyxmem/blob/HEAD/model/memory_util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"dc5d821a03594011"}},{"code_sha256_prefix":"2bd3aa89f60c3cec","entry":"downsample_groups","repo":"vujas-eteph/lazyxmem","repo_kind":"official","path":"model/group_modules.py","file_url":"https://github.com/vujas-eteph/lazyxmem/blob/HEAD/model/group_modules.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"2bd3aa89f60c3cec"}},{"code_sha256_prefix":"ff1b427ff6f254ed","entry":"flip_input","repo":"vujas-eteph/lazyxmem","repo_kind":"official","path":"eval_XMem_base.py","file_url":"https://github.com/vujas-eteph/lazyxmem/blob/HEAD/eval_XMem_base.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"ff1b427ff6f254ed"}},{"code_sha256_prefix":"67623c6b41fc3ef8","entry":"gen_kernel","repo":"vujas-eteph/lazyxmem","repo_kind":"official","path":"eval_Lazy_XMem_dummy.py","file_url":"https://github.com/vujas-eteph/lazyxmem/blob/HEAD/eval_Lazy_XMem_dummy.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"67623c6b41fc3ef8"}},{"code_sha256_prefix":"f7c81ce38ecaaa56","entry":"get_IoU","repo":"vujas-eteph/lazyxmem","repo_kind":"official","path":"eval_Lazy_XMem_dummy.py","file_url":"https://github.com/vujas-eteph/lazyxmem/blob/HEAD/eval_Lazy_XMem_dummy.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"f7c81ce38ecaaa56"}},{"code_sha256_prefix":"959eaf745f868b93","entry":"get_masked_entropy","repo":"vujas-eteph/lazyxmem","repo_kind":"official","path":"eval_Lazy_XMem_dummy.py","file_url":"https://github.com/vujas-eteph/lazyxmem/blob/HEAD/eval_Lazy_XMem_dummy.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"959eaf745f868b93"}},{"code_sha256_prefix":"65507ac25f300c43","entry":"get_similarity","repo":"vujas-eteph/lazyxmem","repo_kind":"official","path":"model/memory_util.py","file_url":"https://github.com/vujas-eteph/lazyxmem/blob/HEAD/model/memory_util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"65507ac25f300c43"}},{"code_sha256_prefix":"439e07b7549687ab","entry":"load_msk_data","repo":"vujas-eteph/lazyxmem","repo_kind":"official","path":"eval_XMem_base.py","file_url":"https://github.com/vujas-eteph/lazyxmem/blob/HEAD/eval_XMem_base.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"439e07b7549687ab"}},{"code_sha256_prefix":"7503bd290afdf9d7","entry":"search_options","repo":"vujas-eteph/lazyxmem","repo_kind":"official","path":"merge_multi_scale.py","file_url":"https://github.com/vujas-eteph/lazyxmem/blob/HEAD/merge_multi_scale.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"7503bd290afdf9d7"}},{"code_sha256_prefix":"a01acb94164900db","entry":"select_relevant_mask","repo":"vujas-eteph/lazyxmem","repo_kind":"official","path":"eval_Lazy_XMem_with_lazy_agent.py","file_url":"https://github.com/vujas-eteph/lazyxmem/blob/HEAD/eval_Lazy_XMem_with_lazy_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"a01acb94164900db"}},{"code_sha256_prefix":"797931db27caacdb","entry":"upsample_groups","repo":"vujas-eteph/lazyxmem","repo_kind":"official","path":"model/group_modules.py","file_url":"https://github.com/vujas-eteph/lazyxmem/blob/HEAD/model/group_modules.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"797931db27caacdb"}},{"code_sha256_prefix":"72678d2f039afdfe","entry":"get_affinity","repo":"vujas-eteph/lazyxmem","repo_kind":"official","path":"model/memory_util.py","file_url":"https://github.com/vujas-eteph/lazyxmem/blob/HEAD/model/memory_util.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":"72678d2f039afdfe"}},{"code_sha256_prefix":"8fd49daab6c49086","entry":"interpolate_groups","repo":"vujas-eteph/lazyxmem","repo_kind":"official","path":"model/group_modules.py","file_url":"https://github.com/vujas-eteph/lazyxmem/blob/HEAD/model/group_modules.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":"8fd49daab6c49086"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}