{"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/local-all-pair-correspondence-for-point","title":"Local All-Pair Correspondence for Point Tracking","arxiv_id":"2407.15420","date":"2024-07-22","proceeding":null,"authors":["Seokju Cho","Jiahui Huang","Jisu Nam","Honggyu An","Seungryong Kim","Joon-Young Lee"],"abstract":"We introduce LocoTrack, a highly accurate and efficient model designed for the task of tracking any point (TAP) across video sequences. Previous approaches in this task often rely on local 2D correlation maps to establish correspondences from a point in the query image to a local region in the target image, which often struggle with homogeneous regions or repetitive features, leading to matching ambiguities. LocoTrack overcomes this challenge with a novel approach that utilizes all-pair correspondences across regions, i.e., local 4D correlation, to establish precise correspondences, with bidirectional correspondence and matching smoothness significantly enhancing robustness against ambiguities. We also incorporate a lightweight correlation encoder to enhance computational efficiency, and a compact Transformer architecture to integrate long-term temporal information. LocoTrack achieves unmatched accuracy on all TAP-Vid benchmarks and operates at a speed almost 6 times faster than the current state-of-the-art.","url_abs":"https://arxiv.org/abs/2407.15420v1","url_pdf":"https://arxiv.org/pdf/2407.15420v1.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":"local-all-pair-correspondence-for-point","repo_url":"https://github.com/cvlab-kaist/locotrack","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"local-all-pair-correspondence-for-point","repo_url":"https://github.com/ku-cvlab/locotrack","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"point-tracking","task_name":"Point Tracking"},{"task_slug":"visual-tracking","task_name":"Visual Tracking"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"speed","method_name":"SPEED"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/point-tracking-on-tap-vid-davis","task":"Point Tracking","dataset":"TAP-Vid-DAVIS","model":"LocoTrack-B","rank_in_archive_order":1,"of":3,"metrics":{"Average Jaccard":"69.4","Average PCK":"81.3","Occlusion Accuracy":"88.6"},"uses_additional_data":false},{"leaderboard":"/sota/point-tracking-on-tap-vid-davis-first","task":"Point Tracking","dataset":"TAP-Vid-DAVIS-First","model":"LocoTrack-B","rank_in_archive_order":1,"of":2,"metrics":{"Average Jaccard":"64.8","Average PCK":"77.4","Occlusion Accuracy":"86.2"},"uses_additional_data":false},{"leaderboard":"/sota/point-tracking-on-tap-vid-kinetics","task":"Point Tracking","dataset":"TAP-Vid-Kinetics","model":"LocoTrack-B","rank_in_archive_order":2,"of":2,"metrics":{"Average Jaccard":"59.1","Average PCK":"72.5","Occlusion Accuracy":"85.7"},"uses_additional_data":false},{"leaderboard":"/sota/point-tracking-on-tap-vid-kinetics-first","task":"Point Tracking","dataset":"TAP-Vid-Kinetics-First","model":"LocoTrack-B","rank_in_archive_order":1,"of":2,"metrics":{"Average Jaccard":"52.3","Average PCK":"66.4","Occlusion Accuracy":"82.1"},"uses_additional_data":false},{"leaderboard":"/sota/point-tracking-on-tap-vid-rgb-stacking","task":"Point Tracking","dataset":"TAP-Vid-RGB-Stacking","model":"LocoTrack-B","rank_in_archive_order":2,"of":2,"metrics":{"Average Jaccard":"70.8","Average PCK":"83.2","Occlusion Accuracy":"84.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.15420","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.15420"}},"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/ku-cvlab/locotrack","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cvlab-kaist/locotrack","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":6,"unverified":6},"by_repo_kind":{"official":{"samples":12,"ran":6,"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":"8d2089efa5f5af9b","entry":"compute_tapvid_metrics","repo":"cvlab-kaist/locotrack","repo_kind":"official","path":"locotrack/evaluation_datasets.py","file_url":"https://github.com/cvlab-kaist/locotrack/blob/HEAD/locotrack/evaluation_datasets.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8d2089efa5f5af9b"}},{"code_sha256_prefix":"e720140bb5365d49","entry":"get_alibi_slope","repo":"cvlab-kaist/locotrack","repo_kind":"official","path":"locotrack/locotrack_model.py","file_url":"https://github.com/cvlab-kaist/locotrack/blob/HEAD/locotrack/locotrack_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e720140bb5365d49"}},{"code_sha256_prefix":"aa68b05aa2f84e51","entry":"get_relative_positions","repo":"cvlab-kaist/locotrack","repo_kind":"official","path":"locotrack/locotrack_model.py","file_url":"https://github.com/cvlab-kaist/locotrack/blob/HEAD/locotrack/locotrack_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aa68b05aa2f84e51"}},{"code_sha256_prefix":"39fcbdf93dcb4313","entry":"interp","repo":"cvlab-kaist/locotrack","repo_kind":"official","path":"locotrack/utils/model_utils.py","file_url":"https://github.com/cvlab-kaist/locotrack/blob/HEAD/locotrack/utils/model_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"39fcbdf93dcb4313"}},{"code_sha256_prefix":"e392edbfaa7809af","entry":"posenc","repo":"cvlab-kaist/locotrack","repo_kind":"official","path":"locotrack/locotrack_model.py","file_url":"https://github.com/cvlab-kaist/locotrack/blob/HEAD/locotrack/locotrack_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e392edbfaa7809af"}},{"code_sha256_prefix":"2db92844cacf356b","entry":"prob_loss","repo":"cvlab-kaist/locotrack","repo_kind":"official","path":"locotrack/utils/model_utils.py","file_url":"https://github.com/cvlab-kaist/locotrack/blob/HEAD/locotrack/utils/model_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2db92844cacf356b"}},{"code_sha256_prefix":"1b97ac62c8bb2152","entry":"add_weight_decay","repo":"cvlab-kaist/locotrack","repo_kind":"official","path":"locotrack/optimizers.py","file_url":"https://github.com/cvlab-kaist/locotrack/blob/HEAD/locotrack/optimizers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1b97ac62c8bb2152"}},{"code_sha256_prefix":"a8329e1fb8a56308","entry":"conv_block","repo":"cvlab-kaist/locotrack","repo_kind":"official","path":"locotrack/models/cmdtop.py","file_url":"https://github.com/cvlab-kaist/locotrack/blob/HEAD/locotrack/models/cmdtop.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a8329e1fb8a56308"}},{"code_sha256_prefix":"08fd9996236d683e","entry":"huber_loss","repo":"cvlab-kaist/locotrack","repo_kind":"official","path":"locotrack_pytorch/model_utils.py","file_url":"https://github.com/cvlab-kaist/locotrack/blob/HEAD/locotrack_pytorch/model_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"08fd9996236d683e"}},{"code_sha256_prefix":"acafb736be892385","entry":"huber_loss","repo":"cvlab-kaist/locotrack","repo_kind":"official","path":"locotrack/utils/model_utils.py","file_url":"https://github.com/cvlab-kaist/locotrack/blob/HEAD/locotrack/utils/model_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"acafb736be892385"}},{"code_sha256_prefix":"17093d41c0b95c30","entry":"latex_table","repo":"cvlab-kaist/locotrack","repo_kind":"official","path":"locotrack/evaluation_datasets.py","file_url":"https://github.com/cvlab-kaist/locotrack/blob/HEAD/locotrack/evaluation_datasets.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"17093d41c0b95c30"}},{"code_sha256_prefix":"d71c81adf1b0a8dc","entry":"prob_loss","repo":"cvlab-kaist/locotrack","repo_kind":"official","path":"locotrack_pytorch/model_utils.py","file_url":"https://github.com/cvlab-kaist/locotrack/blob/HEAD/locotrack_pytorch/model_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d71c81adf1b0a8dc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}