{"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/towards-long-form-video-understanding-1","title":"Towards Long-Form Video Understanding","arxiv_id":"2106.11310","date":"2021-06-21","proceeding":"CVPR 2021 1","authors":["Chao-yuan Wu","Philipp Krähenbühl"],"abstract":"Our world offers a never-ending stream of visual stimuli, yet today's vision systems only accurately recognize patterns within a few seconds. These systems understand the present, but fail to contextualize it in past or future events. In this paper, we study long-form video understanding. We introduce a framework for modeling long-form videos and develop evaluation protocols on large-scale datasets. We show that existing state-of-the-art short-term models are limited for long-form tasks. A novel object-centric transformer-based video recognition architecture performs significantly better on 7 diverse tasks. It also outperforms comparable state-of-the-art on the AVA dataset.","url_abs":"https://arxiv.org/abs/2106.11310v1","url_pdf":"https://arxiv.org/pdf/2106.11310v1.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":"towards-long-form-video-understanding-1","repo_url":"https://github.com/chaoyuaw/lvu","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"towards-long-form-video-understanding-1","repo_url":"https://github.com/md-mohaiminul/ViS4mer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"form","task_name":"Form"},{"task_slug":"video-recognition","task_name":"Video Recognition"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-recognition-on-ava-v2-2","task":"Action Recognition","dataset":"AVA v2.2","model":"Object Transformer","rank_in_archive_order":26,"of":38,"metrics":{"mAP":"31.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.11310","atlas_url":"https://app.syntology.ai/?focus=2106.11310","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.11310"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/chaoyuaw/lvu","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/md-mohaiminul/ViS4mer","reach":null}],"summary":{"ran_draft_wrong":2,"ran_honours":2,"ran":1,"unverified":14},"by_repo_kind":{"official":{"samples":19,"ran":5,"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":"0f786c407fb1ee4c","entry":"swish","repo":"chaoyuaw/lvu","repo_kind":"official","path":"src/models/modeling_bert.py","file_url":"https://github.com/chaoyuaw/lvu/blob/HEAD/src/models/modeling_bert.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0f786c407fb1ee4c"}},{"code_sha256_prefix":"211753ba29188d4e","entry":"gelu","repo":"chaoyuaw/lvu","repo_kind":"official","path":"src/models/modeling_bert.py","file_url":"https://github.com/chaoyuaw/lvu/blob/HEAD/src/models/modeling_bert.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"211753ba29188d4e"}},{"code_sha256_prefix":"77601724cad03f95","entry":"gelu_new","repo":"chaoyuaw/lvu","repo_kind":"official","path":"src/models/modeling_bert.py","file_url":"https://github.com/chaoyuaw/lvu/blob/HEAD/src/models/modeling_bert.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"77601724cad03f95"}},{"code_sha256_prefix":"d30d6c3098df2c42","entry":"prune_linear_layer","repo":"chaoyuaw/lvu","repo_kind":"official","path":"src/models/modeling_utils.py","file_url":"https://github.com/chaoyuaw/lvu/blob/HEAD/src/models/modeling_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d30d6c3098df2c42"}},{"code_sha256_prefix":"e827d94caab33f59","entry":"url_to_filename","repo":"chaoyuaw/lvu","repo_kind":"official","path":"src/models/file_utils.py","file_url":"https://github.com/chaoyuaw/lvu/blob/HEAD/src/models/file_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e827d94caab33f59"}},{"code_sha256_prefix":"a788ae380900c50e","entry":"MaskedBCEWithLogitsLoss","repo":"chaoyuaw/lvu","repo_kind":"official","path":"src/models/modeling_roberta.py","file_url":"https://github.com/chaoyuaw/lvu/blob/HEAD/src/models/modeling_roberta.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":"a788ae380900c50e"}},{"code_sha256_prefix":"4575f85aa7122560","entry":"get_constant_schedule","repo":"chaoyuaw/lvu","repo_kind":"official","path":"src/models/optimization.py","file_url":"https://github.com/chaoyuaw/lvu/blob/HEAD/src/models/optimization.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":"4575f85aa7122560"}},{"code_sha256_prefix":"a2003a42a1bf5632","entry":"get_constant_schedule_with_warmup","repo":"chaoyuaw/lvu","repo_kind":"official","path":"src/models/optimization.py","file_url":"https://github.com/chaoyuaw/lvu/blob/HEAD/src/models/optimization.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":"a2003a42a1bf5632"}},{"code_sha256_prefix":"a3c458ae06a14711","entry":"get_linear_schedule_with_warmup","repo":"chaoyuaw/lvu","repo_kind":"official","path":"src/models/optimization.py","file_url":"https://github.com/chaoyuaw/lvu/blob/HEAD/src/models/optimization.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":"a3c458ae06a14711"}},{"code_sha256_prefix":"4f76173dfe4b0c11","entry":"get_pairs","repo":"chaoyuaw/lvu","repo_kind":"official","path":"src/models/tokenization_gpt2.py","file_url":"https://github.com/chaoyuaw/lvu/blob/HEAD/src/models/tokenization_gpt2.py","link_basis":"plan_row","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":"4f76173dfe4b0c11"}},{"code_sha256_prefix":"b2be6c932ce41084","entry":"hf_bucket_url","repo":"chaoyuaw/lvu","repo_kind":"official","path":"src/models/file_utils.py","file_url":"https://github.com/chaoyuaw/lvu/blob/HEAD/src/models/file_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":"b2be6c932ce41084"}},{"code_sha256_prefix":"4381d1f588a7f42a","entry":"is_remote_url","repo":"chaoyuaw/lvu","repo_kind":"official","path":"src/models/file_utils.py","file_url":"https://github.com/chaoyuaw/lvu/blob/HEAD/src/models/file_utils.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":"4381d1f588a7f42a"}},{"code_sha256_prefix":"15e577f3614f1586","entry":"make_image_key","repo":"chaoyuaw/lvu","repo_kind":"official","path":"src/utils/ava_eval_helper.py","file_url":"https://github.com/chaoyuaw/lvu/blob/HEAD/src/utils/ava_eval_helper.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":"15e577f3614f1586"}},{"code_sha256_prefix":"8cc492d40c50497b","entry":"prune_conv1d_layer","repo":"chaoyuaw/lvu","repo_kind":"official","path":"src/models/modeling_utils.py","file_url":"https://github.com/chaoyuaw/lvu/blob/HEAD/src/models/modeling_utils.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":"8cc492d40c50497b"}},{"code_sha256_prefix":"a49fc9f33754fd90","entry":"read_csv","repo":"chaoyuaw/lvu","repo_kind":"official","path":"src/utils/ava_eval_helper.py","file_url":"https://github.com/chaoyuaw/lvu/blob/HEAD/src/utils/ava_eval_helper.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":"a49fc9f33754fd90"}},{"code_sha256_prefix":"66b0d97a822e992a","entry":"read_exclusions","repo":"chaoyuaw/lvu","repo_kind":"official","path":"src/utils/ava_eval_helper.py","file_url":"https://github.com/chaoyuaw/lvu/blob/HEAD/src/utils/ava_eval_helper.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":"66b0d97a822e992a"}},{"code_sha256_prefix":"9547eabe3165408d","entry":"soft_label_loss_sigmoid","repo":"chaoyuaw/lvu","repo_kind":"official","path":"src/models/modeling_roberta.py","file_url":"https://github.com/chaoyuaw/lvu/blob/HEAD/src/models/modeling_roberta.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":"9547eabe3165408d"}},{"code_sha256_prefix":"f8a333d6a2819774","entry":"soft_label_loss_softmax","repo":"chaoyuaw/lvu","repo_kind":"official","path":"src/models/modeling_roberta.py","file_url":"https://github.com/chaoyuaw/lvu/blob/HEAD/src/models/modeling_roberta.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":"f8a333d6a2819774"}},{"code_sha256_prefix":"8e873fc150477bd1","entry":"top_k_top_p_filtering","repo":"chaoyuaw/lvu","repo_kind":"official","path":"src/models/modeling_utils.py","file_url":"https://github.com/chaoyuaw/lvu/blob/HEAD/src/models/modeling_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":"8e873fc150477bd1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}