{"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/state-aware-tracker-for-real-time-video","title":"State-Aware Tracker for Real-Time Video Object Segmentation","arxiv_id":"2003.00482","date":"2020-03-01","proceeding":"CVPR 2020 6","authors":["Xi Chen","Zuoxin Li","Ye Yuan","Gang Yu","Jianxin Shen","Donglian Qi"],"abstract":"In this work, we address the task of semi-supervised video object segmentation(VOS) and explore how to make efficient use of video property to tackle the challenge of semi-supervision. We propose a novel pipeline called State-Aware Tracker(SAT), which can produce accurate segmentation results with real-time speed. For higher efficiency, SAT takes advantage of the inter-frame consistency and deals with each target object as a tracklet. For more stable and robust performance over video sequences, SAT gets awareness for each state and makes self-adaptation via two feedback loops. One loop assists SAT in generating more stable tracklets. The other loop helps to construct a more robust and holistic target representation. SAT achieves a promising result of 72.3% J&F mean with 39 FPS on DAVIS2017-Val dataset, which shows a decent trade-off between efficiency and accuracy. Code will be released at github.com/MegviiDetection/video_analyst.","url_abs":"https://arxiv.org/abs/2003.00482v1","url_pdf":"https://arxiv.org/pdf/2003.00482v1.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":"state-aware-tracker-for-real-time-video","repo_url":"https://github.com/MegviiDetection/video_analyst","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"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":[{"method_slug":"state-aware-tracker","method_name":"State-Aware Tracker"}],"datasets_introduced":[],"methods_introduced":[{"slug":"state-aware-tracker","name":"State-Aware Tracker","full_name":"State-Aware Tracker"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2003.00482","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.00482"}},"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/MegviiDetection/video_analyst","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":6},"by_repo_kind":{"official":{"samples":7,"ran":1,"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":"9d103c391b8dbe33","entry":"to_numpy","repo":"MegviiDetection/video_analyst","repo_kind":"official","path":"main/cvt_trt.py","file_url":"https://github.com/MegviiDetection/video_analyst/blob/HEAD/main/cvt_trt.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9d103c391b8dbe33"}},{"code_sha256_prefix":"e127c82cc613f1d9","entry":"build","repo":"MegviiDetection/video_analyst","repo_kind":"official","path":"videoanalyst/model/builder.py","file_url":"https://github.com/MegviiDetection/video_analyst/blob/HEAD/videoanalyst/model/builder.py","link_basis":"first_harvest_node","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":"e127c82cc613f1d9"}},{"code_sha256_prefix":"6eaaca85a808b3e1","entry":"convert_numpy_to_tensor","repo":"MegviiDetection/video_analyst","repo_kind":"official","path":"videoanalyst/utils/torch_module.py","file_url":"https://github.com/MegviiDetection/video_analyst/blob/HEAD/videoanalyst/utils/torch_module.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":"6eaaca85a808b3e1"}},{"code_sha256_prefix":"fa51e84d318a9b7d","entry":"get_config","repo":"MegviiDetection/video_analyst","repo_kind":"official","path":"videoanalyst/model/builder.py","file_url":"https://github.com/MegviiDetection/video_analyst/blob/HEAD/videoanalyst/model/builder.py","link_basis":"first_harvest_node","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":"fa51e84d318a9b7d"}},{"code_sha256_prefix":"d06d2a6e7019c137","entry":"move_data_to_device","repo":"MegviiDetection/video_analyst","repo_kind":"official","path":"videoanalyst/utils/torch_module.py","file_url":"https://github.com/MegviiDetection/video_analyst/blob/HEAD/videoanalyst/utils/torch_module.py","link_basis":"first_harvest_node","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":"d06d2a6e7019c137"}},{"code_sha256_prefix":"df5b6d48d5678fc1","entry":"specify_task","repo":"MegviiDetection/video_analyst","repo_kind":"official","path":"videoanalyst/config/config.py","file_url":"https://github.com/MegviiDetection/video_analyst/blob/HEAD/videoanalyst/config/config.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":"df5b6d48d5678fc1"}},{"code_sha256_prefix":"99a642ee770823da","entry":"unwrap_model","repo":"MegviiDetection/video_analyst","repo_kind":"official","path":"videoanalyst/utils/torch_module.py","file_url":"https://github.com/MegviiDetection/video_analyst/blob/HEAD/videoanalyst/utils/torch_module.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":"99a642ee770823da"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}