{"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/hourvideo-1-hour-video-language-understanding","title":"HourVideo: 1-Hour Video-Language Understanding","arxiv_id":"2411.04998","date":"2024-11-07","proceeding":null,"authors":["Keshigeyan Chandrasegaran","Agrim Gupta","Lea M. Hadzic","Taran Kota","Jimming He","Cristóbal Eyzaguirre","Zane Durante","Manling Li","Jiajun Wu","Li Fei-Fei"],"abstract":"We present HourVideo, a benchmark dataset for hour-long video-language understanding. Our dataset consists of a novel task suite comprising summarization, perception (recall, tracking), visual reasoning (spatial, temporal, predictive, causal, counterfactual), and navigation (room-to-room, object retrieval) tasks. HourVideo includes 500 manually curated egocentric videos from the Ego4D dataset, spanning durations of 20 to 120 minutes, and features 12,976 high-quality, five-way multiple-choice questions. Benchmarking results reveal that multimodal models, including GPT-4 and LLaVA-NeXT, achieve marginal improvements over random chance. In stark contrast, human experts significantly outperform the state-of-the-art long-context multimodal model, Gemini Pro 1.5 (85.0% vs. 37.3%), highlighting a substantial gap in multimodal capabilities. Our benchmark, evaluation toolkit, prompts, and documentation are available at https://hourvideo.stanford.edu","url_abs":"https://arxiv.org/abs/2411.04998v1","url_pdf":"https://arxiv.org/pdf/2411.04998v1.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":"hourvideo-1-hour-video-language-understanding","repo_url":"https://github.com/keshik6/HourVideo","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"multiple-choice","task_name":"Multiple-choice"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"},{"task_slug":null,"task_name":"counterfactual"}],"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":"gpt-4","method_name":"GPT-4"},{"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":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[{"slug":"hourvideo","name":"HourVideo","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2411.04998","atlas_url":"https://app.syntology.ai/?focus=2411.04998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04998"}},"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/keshik6/HourVideo","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":1,"unverified":15},"by_repo_kind":{"official":{"samples":16,"ran":1,"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":"f41cb1a19b154297","entry":"encode_image","repo":"keshik6/HourVideo","repo_kind":"official","path":"hourvideo/gpt4_utils.py","file_url":"https://github.com/keshik6/HourVideo/blob/HEAD/hourvideo/gpt4_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f41cb1a19b154297"}},{"code_sha256_prefix":"d31b2cfa1a2eabc8","entry":"check_caption_completion_status","repo":"keshik6/HourVideo","repo_kind":"official","path":"hourvideo/form_world_state_history.py","file_url":"https://github.com/keshik6/HourVideo/blob/HEAD/hourvideo/form_world_state_history.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":"d31b2cfa1a2eabc8"}},{"code_sha256_prefix":"aca03fd411a5b059","entry":"convert_seconds_to_hms","repo":"keshik6/HourVideo","repo_kind":"official","path":"hourvideo/llm_utils.py","file_url":"https://github.com/keshik6/HourVideo/blob/HEAD/hourvideo/llm_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":"aca03fd411a5b059"}},{"code_sha256_prefix":"8c8de8a6584771d2","entry":"correct_keys_in_list","repo":"keshik6/HourVideo","repo_kind":"official","path":"hourvideo/gpt4_utils.py","file_url":"https://github.com/keshik6/HourVideo/blob/HEAD/hourvideo/gpt4_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":"8c8de8a6584771d2"}},{"code_sha256_prefix":"e06becb29bf68207","entry":"create_index_lists","repo":"keshik6/HourVideo","repo_kind":"official","path":"hourvideo/gpt4_captioner.py","file_url":"https://github.com/keshik6/HourVideo/blob/HEAD/hourvideo/gpt4_captioner.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":"e06becb29bf68207"}},{"code_sha256_prefix":"1a60d839f3eb71b4","entry":"extract_first_letter","repo":"keshik6/HourVideo","repo_kind":"official","path":"hourvideo/gemini_utils.py","file_url":"https://github.com/keshik6/HourVideo/blob/HEAD/hourvideo/gemini_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":"1a60d839f3eb71b4"}},{"code_sha256_prefix":"65d9bfa83974ba96","entry":"filter_intervals","repo":"keshik6/HourVideo","repo_kind":"official","path":"hourvideo/form_world_state_history.py","file_url":"https://github.com/keshik6/HourVideo/blob/HEAD/hourvideo/form_world_state_history.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":"65d9bfa83974ba96"}},{"code_sha256_prefix":"132f9da86c87ad0d","entry":"get_color","repo":"keshik6/HourVideo","repo_kind":"official","path":"hourvideo/hv_utils.py","file_url":"https://github.com/keshik6/HourVideo/blob/HEAD/hourvideo/hv_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":"132f9da86c87ad0d"}},{"code_sha256_prefix":"d37eb61fd6663794","entry":"get_openai_completion","repo":"keshik6/HourVideo","repo_kind":"official","path":"hourvideo/gpt4_captioner.py","file_url":"https://github.com/keshik6/HourVideo/blob/HEAD/hourvideo/gpt4_captioner.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":"d37eb61fd6663794"}},{"code_sha256_prefix":"d21c0d0cbe00da28","entry":"get_world_state_history","repo":"keshik6/HourVideo","repo_kind":"official","path":"hourvideo/form_world_state_history.py","file_url":"https://github.com/keshik6/HourVideo/blob/HEAD/hourvideo/form_world_state_history.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":"d21c0d0cbe00da28"}},{"code_sha256_prefix":"8ddb08051f41a1c4","entry":"load_json","repo":"keshik6/HourVideo","repo_kind":"official","path":"hourvideo/hv_utils.py","file_url":"https://github.com/keshik6/HourVideo/blob/HEAD/hourvideo/hv_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":"8ddb08051f41a1c4"}},{"code_sha256_prefix":"8b1c14fc5481eb57","entry":"load_openai_client","repo":"keshik6/HourVideo","repo_kind":"official","path":"hourvideo/gpt4_utils.py","file_url":"https://github.com/keshik6/HourVideo/blob/HEAD/hourvideo/gpt4_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":"8b1c14fc5481eb57"}},{"code_sha256_prefix":"6483832049cc55d0","entry":"load_yaml_files","repo":"keshik6/HourVideo","repo_kind":"official","path":"hourvideo/hv_utils.py","file_url":"https://github.com/keshik6/HourVideo/blob/HEAD/hourvideo/hv_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":"6483832049cc55d0"}},{"code_sha256_prefix":"dfc109b0a442de2e","entry":"num_tokens_from_string","repo":"keshik6/HourVideo","repo_kind":"official","path":"hourvideo/llm_utils.py","file_url":"https://github.com/keshik6/HourVideo/blob/HEAD/hourvideo/llm_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":"dfc109b0a442de2e"}},{"code_sha256_prefix":"5bf0c932374156bb","entry":"preprocess_llm_output","repo":"keshik6/HourVideo","repo_kind":"official","path":"hourvideo/llm_utils.py","file_url":"https://github.com/keshik6/HourVideo/blob/HEAD/hourvideo/llm_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":"5bf0c932374156bb"}},{"code_sha256_prefix":"6ad55351c4f42d8f","entry":"timestamp_to_seconds","repo":"keshik6/HourVideo","repo_kind":"official","path":"hourvideo/gemini_utils.py","file_url":"https://github.com/keshik6/HourVideo/blob/HEAD/hourvideo/gemini_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":"6ad55351c4f42d8f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}