{"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/video-clip-baseline-for-ego4d-long-term","title":"Video + CLIP Baseline for Ego4D Long-term Action Anticipation","arxiv_id":"2207.00579","date":"2022-07-01","proceeding":null,"authors":["Srijan Das","Michael S. Ryoo"],"abstract":"In this report, we introduce our adaptation of image-text models for long-term action anticipation. Our Video + CLIP framework makes use of a large-scale pre-trained paired image-text model: CLIP and a video encoder Slowfast network. The CLIP embedding provides fine-grained understanding of objects relevant for an action whereas the slowfast network is responsible for modeling temporal information within a video clip of few frames. We show that the features obtained from both encoders are complementary to each other, thus outperforming the baseline on Ego4D for the task of long-term action anticipation. Our code is available at github.com/srijandas07/clip_baseline_LTA_Ego4d.","url_abs":"https://arxiv.org/abs/2207.00579v1","url_pdf":"https://arxiv.org/pdf/2207.00579v1.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":"video-clip-baseline-for-ego4d-long-term","repo_url":"https://github.com/srijandas07/clip_baseline_lta_ego4d","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"action-anticipation","task_name":"Action Anticipation"},{"task_slug":"long-term-action-anticipation","task_name":"Long Term Action Anticipation"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2207.00579","atlas_url":"https://app.syntology.ai/?focus=2207.00579","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.00579"}},"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/srijandas07/clip_baseline_lta_ego4d","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"unverified":6},"by_repo_kind":{"official":{"samples":9,"ran":3,"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":"b07e3607b90c1e7c","entry":"round_width","repo":"srijandas07/clip_baseline_lta_ego4d","repo_kind":"official","path":"ego4d/models/video_model_builder.py","file_url":"https://github.com/srijandas07/clip_baseline_lta_ego4d/blob/HEAD/ego4d/models/video_model_builder.py","link_basis":"harvester_set","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":"b07e3607b90c1e7c"}},{"code_sha256_prefix":"10e9b4ea0c092f82","entry":"topk_errors","repo":"srijandas07/clip_baseline_lta_ego4d","repo_kind":"official","path":"ego4d/evaluation/lta_metrics.py","file_url":"https://github.com/srijandas07/clip_baseline_lta_ego4d/blob/HEAD/ego4d/evaluation/lta_metrics.py","link_basis":"harvester_set","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":"10e9b4ea0c092f82"}},{"code_sha256_prefix":"eea7a73a4935fff4","entry":"topks_correct","repo":"srijandas07/clip_baseline_lta_ego4d","repo_kind":"official","path":"ego4d/evaluation/lta_metrics.py","file_url":"https://github.com/srijandas07/clip_baseline_lta_ego4d/blob/HEAD/ego4d/evaluation/lta_metrics.py","link_basis":"harvester_set","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":"eea7a73a4935fff4"}},{"code_sha256_prefix":"b6dd75b900cecbb8","entry":"distributed_topk_errors","repo":"srijandas07/clip_baseline_lta_ego4d","repo_kind":"official","path":"ego4d/evaluation/lta_metrics.py","file_url":"https://github.com/srijandas07/clip_baseline_lta_ego4d/blob/HEAD/ego4d/evaluation/lta_metrics.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":"b6dd75b900cecbb8"}},{"code_sha256_prefix":"bcc1cdae3bb3212c","entry":"drop_path","repo":"srijandas07/clip_baseline_lta_ego4d","repo_kind":"official","path":"ego4d/models/video_model_builder.py","file_url":"https://github.com/srijandas07/clip_baseline_lta_ego4d/blob/HEAD/ego4d/models/video_model_builder.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":"bcc1cdae3bb3212c"}},{"code_sha256_prefix":"dd72775d1ea00db7","entry":"get_loss_func","repo":"srijandas07/clip_baseline_lta_ego4d","repo_kind":"official","path":"ego4d/models/losses.py","file_url":"https://github.com/srijandas07/clip_baseline_lta_ego4d/blob/HEAD/ego4d/models/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":"dd72775d1ea00db7"}},{"code_sha256_prefix":"952f23f7aff7ce7d","entry":"get_norm","repo":"srijandas07/clip_baseline_lta_ego4d","repo_kind":"official","path":"ego4d/models/batchnorm_helper.py","file_url":"https://github.com/srijandas07/clip_baseline_lta_ego4d/blob/HEAD/ego4d/models/batchnorm_helper.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":"952f23f7aff7ce7d"}},{"code_sha256_prefix":"4d6991202a8d6097","entry":"get_trans_func","repo":"srijandas07/clip_baseline_lta_ego4d","repo_kind":"official","path":"ego4d/models/resnet_helper.py","file_url":"https://github.com/srijandas07/clip_baseline_lta_ego4d/blob/HEAD/ego4d/models/resnet_helper.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":"4d6991202a8d6097"}},{"code_sha256_prefix":"a99430fceaa1dc2d","entry":"is_detection_enabled","repo":"srijandas07/clip_baseline_lta_ego4d","repo_kind":"official","path":"ego4d/models/video_model_builder.py","file_url":"https://github.com/srijandas07/clip_baseline_lta_ego4d/blob/HEAD/ego4d/models/video_model_builder.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":"a99430fceaa1dc2d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}