{"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/bridging-episodes-and-semantics-a-novel","title":"HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics","arxiv_id":"2408.17443","date":"2024-08-30","proceeding":null,"authors":["Gueter Josmy Faure","Jia-Fong Yeh","Min-Hung Chen","Hung-Ting Su","Shang-Hong Lai","Winston H. Hsu"],"abstract":"Existing research often treats long-form videos as extended short videos, leading to several limitations: inadequate capture of long-range dependencies, inefficient processing of redundant information, and failure to extract high-level semantic concepts. To address these issues, we propose a novel approach that more accurately reflects human cognition. This paper introduces HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics, a model that simulates episodic memory accumulation to capture action sequences and reinforces them with semantic knowledge dispersed throughout the video. Our work makes two key contributions: First, we develop an Episodic COmpressor (ECO) that efficiently aggregates crucial representations from micro to semi-macro levels, overcoming the challenge of long-range dependencies. Second, we propose a Semantics ReTRiever (SeTR) that enhances these aggregated representations with semantic information by focusing on the broader context, dramatically reducing feature dimensionality while preserving relevant macro-level information. This addresses the issues of redundancy and lack of high-level concept extraction. Extensive experiments demonstrate that HERMES achieves state-of-the-art performance across multiple long-video understanding benchmarks in both zero-shot and fully-supervised settings.","url_abs":"https://arxiv.org/abs/2408.17443v3","url_pdf":"https://arxiv.org/pdf/2408.17443v3.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":"bridging-episodes-and-semantics-a-novel","repo_url":"https://github.com/joslefaure/HERMES","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"form","task_name":"Form"},{"task_slug":"video-classification","task_name":"Video Classification"},{"task_slug":null,"task_name":"zero-shot long video breakpoint-mode question answering"},{"task_slug":null,"task_name":"zero-shot long video global-mode question answering"},{"task_slug":null,"task_name":"zero-shot long video global-model question answering"},{"task_slug":"zero-shot-long-video-question-answering","task_name":"zero-shot long video question answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-classification-on-breakfast","task":"Video Classification","dataset":"Breakfast","model":"HERMES","rank_in_archive_order":1,"of":9,"metrics":{"Accuracy (%)":"95.2"},"uses_additional_data":false},{"leaderboard":"/sota/video-classification-on-coin-1","task":"Video Classification","dataset":"COIN","model":"HERMES","rank_in_archive_order":1,"of":7,"metrics":{"Accuracy (%)":"93.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2408.17443","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.17443"}},"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/joslefaure/HERMES","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5,"ran_fixture":1,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":9,"ran":7,"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":"6e0b77da286c6cb3","entry":"calculate_scores","repo":"joslefaure/HERMES","repo_kind":"official","path":"lavis/tasks/moviecore_eval.py","file_url":"https://github.com/joslefaure/HERMES/blob/HEAD/lavis/tasks/moviecore_eval.py","link_basis":"first_harvest_node","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":"6e0b77da286c6cb3"}},{"code_sha256_prefix":"aee911f7b46c600a","entry":"download_cached_file","repo":"joslefaure/HERMES","repo_kind":"official","path":"lavis/common/dist_utils.py","file_url":"https://github.com/joslefaure/HERMES/blob/HEAD/lavis/common/dist_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":"aee911f7b46c600a"}},{"code_sha256_prefix":"7d214655954e2bc6","entry":"getAttMap","repo":"joslefaure/HERMES","repo_kind":"official","path":"lavis/common/gradcam.py","file_url":"https://github.com/joslefaure/HERMES/blob/HEAD/lavis/common/gradcam.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7d214655954e2bc6"}},{"code_sha256_prefix":"c6ec173f19f5c34d","entry":"interpolate_pos_embed","repo":"joslefaure/HERMES","repo_kind":"official","path":"lavis/models/vit.py","file_url":"https://github.com/joslefaure/HERMES/blob/HEAD/lavis/models/vit.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c6ec173f19f5c34d"}},{"code_sha256_prefix":"98589643273920ba","entry":"main_process","repo":"joslefaure/HERMES","repo_kind":"official","path":"lavis/common/dist_utils.py","file_url":"https://github.com/joslefaure/HERMES/blob/HEAD/lavis/common/dist_utils.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":"98589643273920ba"}},{"code_sha256_prefix":"791c72070c0b1cfb","entry":"node_to_dict","repo":"joslefaure/HERMES","repo_kind":"official","path":"lavis/common/config.py","file_url":"https://github.com/joslefaure/HERMES/blob/HEAD/lavis/common/config.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":"791c72070c0b1cfb"}},{"code_sha256_prefix":"cb33571427334815","entry":"tile","repo":"joslefaure/HERMES","repo_kind":"official","path":"lavis/models/base_model.py","file_url":"https://github.com/joslefaure/HERMES/blob/HEAD/lavis/models/base_model.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":"cb33571427334815"}},{"code_sha256_prefix":"0ec9fc2025c16f65","entry":"all_gather_with_grad","repo":"joslefaure/HERMES","repo_kind":"official","path":"lavis/models/base_model.py","file_url":"https://github.com/joslefaure/HERMES/blob/HEAD/lavis/models/base_model.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":"0ec9fc2025c16f65"}},{"code_sha256_prefix":"50228589040ec9ac","entry":"get_prompt","repo":"joslefaure/HERMES","repo_kind":"official","path":"lavis/tasks/moviecore_eval_prompts.py","file_url":"https://github.com/joslefaure/HERMES/blob/HEAD/lavis/tasks/moviecore_eval_prompts.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":"50228589040ec9ac"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}