{"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/snag-scalable-and-accurate-video-grounding","title":"SnAG: Scalable and Accurate Video Grounding","arxiv_id":"2404.02257","date":"2024-04-02","proceeding":"CVPR 2024 1","authors":["Fangzhou Mu","Sicheng Mo","Yin Li"],"abstract":"Temporal grounding of text descriptions in videos is a central problem in vision-language learning and video understanding. Existing methods often prioritize accuracy over scalability -- they have been optimized for grounding only a few text queries within short videos, and fail to scale up to long videos with hundreds of queries. In this paper, we study the effect of cross-modal fusion on the scalability of video grounding models. Our analysis establishes late fusion as a more cost-effective fusion scheme for long-form videos with many text queries. Moreover, it leads us to a novel, video-centric sampling scheme for efficient training. Based on these findings, we present SnAG, a simple baseline for scalable and accurate video grounding. Without bells and whistles, SnAG is 43% more accurate and 1.5x faster than CONE, a state of the art for long-form video grounding on the challenging MAD dataset, while achieving highly competitive results on short videos.","url_abs":"https://arxiv.org/abs/2404.02257v2","url_pdf":"https://arxiv.org/pdf/2404.02257v2.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":"snag-scalable-and-accurate-video-grounding","repo_url":"https://github.com/happyharrycn/actionformer_release","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"video-grounding","task_name":"Video Grounding"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2404.02257","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.02257"}},"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/happyharrycn/actionformer_release","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/fmu2/snag_release","reach":null}],"summary":{"ran_fixture":2,"ran_honours":1,"ran":2,"unverified":15},"by_repo_kind":{"listed":{"samples":15,"ran":5,"repositories":1},"found_in_text":{"samples":5,"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":5,"samples":[{"code_sha256_prefix":"a34c005ba2203f35","entry":"drop_path","repo":"happyharrycn/actionformer_release","repo_kind":"listed","path":"libs/modeling/blocks.py","file_url":"https://github.com/happyharrycn/actionformer_release/blob/HEAD/libs/modeling/blocks.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a34c005ba2203f35"}},{"code_sha256_prefix":"3531df7b0c9b0791","entry":"get_sinusoid_encoding","repo":"happyharrycn/actionformer_release","repo_kind":"listed","path":"libs/modeling/blocks.py","file_url":"https://github.com/happyharrycn/actionformer_release/blob/HEAD/libs/modeling/blocks.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3531df7b0c9b0791"}},{"code_sha256_prefix":"a957fa06c95c422f","entry":"load_config","repo":"happyharrycn/actionformer_release","repo_kind":"listed","path":"libs/core/config.py","file_url":"https://github.com/happyharrycn/actionformer_release/blob/HEAD/libs/core/config.py","link_basis":"first_harvest_node","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":"a957fa06c95c422f"}},{"code_sha256_prefix":"02566da69866c48c","entry":"trunc_normal_","repo":"happyharrycn/actionformer_release","repo_kind":"listed","path":"libs/modeling/weight_init.py","file_url":"https://github.com/happyharrycn/actionformer_release/blob/HEAD/libs/modeling/weight_init.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"02566da69866c48c"}},{"code_sha256_prefix":"073b23d898943c73","entry":"truncate_feats","repo":"happyharrycn/actionformer_release","repo_kind":"listed","path":"libs/datasets/data_utils.py","file_url":"https://github.com/happyharrycn/actionformer_release/blob/HEAD/libs/datasets/data_utils.py","link_basis":"first_harvest_node","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":"073b23d898943c73"}},{"code_sha256_prefix":"61e4463bc2eaf08c","entry":"PtTransformer","repo":"fmu2/snag_release","repo_kind":"found_in_text","path":"libs/modeling/model.py","file_url":"https://github.com/fmu2/snag_release/blob/HEAD/libs/modeling/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"61e4463bc2eaf08c"}},{"code_sha256_prefix":"12d8ba65aabcb2b4","entry":"ctr_diou_loss_1d","repo":"happyharrycn/actionformer_release","repo_kind":"listed","path":"libs/modeling/losses.py","file_url":"https://github.com/happyharrycn/actionformer_release/blob/HEAD/libs/modeling/losses.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":"12d8ba65aabcb2b4"}},{"code_sha256_prefix":"66693d03280664b1","entry":"ctr_giou_loss_1d","repo":"happyharrycn/actionformer_release","repo_kind":"listed","path":"libs/modeling/losses.py","file_url":"https://github.com/happyharrycn/actionformer_release/blob/HEAD/libs/modeling/losses.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":"66693d03280664b1"}},{"code_sha256_prefix":"635369f63ec96b89","entry":"make_data_loader","repo":"happyharrycn/actionformer_release","repo_kind":"listed","path":"libs/datasets/datasets.py","file_url":"https://github.com/happyharrycn/actionformer_release/blob/HEAD/libs/datasets/datasets.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":"635369f63ec96b89"}},{"code_sha256_prefix":"ffebfbb8094c0dcc","entry":"make_dataset","repo":"happyharrycn/actionformer_release","repo_kind":"listed","path":"libs/datasets/datasets.py","file_url":"https://github.com/happyharrycn/actionformer_release/blob/HEAD/libs/datasets/datasets.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":"ffebfbb8094c0dcc"}},{"code_sha256_prefix":"c4eba9d35a22d565","entry":"make_fusion","repo":"fmu2/snag_release","repo_kind":"found_in_text","path":"libs/modeling/model.py","file_url":"https://github.com/fmu2/snag_release/blob/HEAD/libs/modeling/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c4eba9d35a22d565"}},{"code_sha256_prefix":"10c20d3c7447a10c","entry":"make_head","repo":"fmu2/snag_release","repo_kind":"found_in_text","path":"libs/modeling/model.py","file_url":"https://github.com/fmu2/snag_release/blob/HEAD/libs/modeling/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"10c20d3c7447a10c"}},{"code_sha256_prefix":"45cd753de473cb89","entry":"make_text_net","repo":"fmu2/snag_release","repo_kind":"found_in_text","path":"libs/modeling/model.py","file_url":"https://github.com/fmu2/snag_release/blob/HEAD/libs/modeling/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"45cd753de473cb89"}},{"code_sha256_prefix":"e0b4f1cbb0de076d","entry":"make_video_net","repo":"fmu2/snag_release","repo_kind":"found_in_text","path":"libs/modeling/model.py","file_url":"https://github.com/fmu2/snag_release/blob/HEAD/libs/modeling/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e0b4f1cbb0de076d"}},{"code_sha256_prefix":"cee845f405ecf37e","entry":"register_backbone","repo":"happyharrycn/actionformer_release","repo_kind":"listed","path":"libs/modeling/models.py","file_url":"https://github.com/happyharrycn/actionformer_release/blob/HEAD/libs/modeling/models.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":"cee845f405ecf37e"}},{"code_sha256_prefix":"2ee0df0825339a6e","entry":"register_dataset","repo":"happyharrycn/actionformer_release","repo_kind":"listed","path":"libs/datasets/datasets.py","file_url":"https://github.com/happyharrycn/actionformer_release/blob/HEAD/libs/datasets/datasets.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":"2ee0df0825339a6e"}},{"code_sha256_prefix":"3db1c5ab5f3f0198","entry":"register_generator","repo":"happyharrycn/actionformer_release","repo_kind":"listed","path":"libs/modeling/models.py","file_url":"https://github.com/happyharrycn/actionformer_release/blob/HEAD/libs/modeling/models.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":"3db1c5ab5f3f0198"}},{"code_sha256_prefix":"e5ef13b176081594","entry":"register_neck","repo":"happyharrycn/actionformer_release","repo_kind":"listed","path":"libs/modeling/models.py","file_url":"https://github.com/happyharrycn/actionformer_release/blob/HEAD/libs/modeling/models.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":"e5ef13b176081594"}},{"code_sha256_prefix":"0d06c0983d985a4a","entry":"sigmoid_focal_loss","repo":"happyharrycn/actionformer_release","repo_kind":"listed","path":"libs/modeling/losses.py","file_url":"https://github.com/happyharrycn/actionformer_release/blob/HEAD/libs/modeling/losses.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":"0d06c0983d985a4a"}},{"code_sha256_prefix":"0c250bf03b8c9311","entry":"trivial_batch_collator","repo":"happyharrycn/actionformer_release","repo_kind":"listed","path":"libs/datasets/data_utils.py","file_url":"https://github.com/happyharrycn/actionformer_release/blob/HEAD/libs/datasets/data_utils.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":"0c250bf03b8c9311"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}