{"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/vlog-video-language-models-by-generative","title":"VLog: Video-Language Models by Generative Retrieval of Narration Vocabulary","arxiv_id":"2503.09402","date":"2025-03-12","proceeding":"CVPR 2025 1","authors":["Kevin Qinghong Lin","Mike Zheng Shou"],"abstract":"Human daily activities can be concisely narrated as sequences of routine events (e.g., turning off an alarm) in video streams, forming an event vocabulary. Motivated by this, we introduce VLog, a novel video understanding framework that define video narrations as vocabulary, going beyond the typical subword vocabularies in existing generative video-language models. Built on the lightweight language model GPT-2, VLog feature three key innovations: (i) A generative retrieval model, marrying language model's complex reasoning capabilities with contrastive retrieval's efficient similarity search. (ii) A hierarchical vocabulary derived from large-scale video narrations using our narration pair encoding algorithm, enabling efficient indexing of specific events (e.g., cutting a tomato) by identifying broader scenarios (e.g., kitchen) with expressive postfixes (e.g., by the left hand). (iii) A vocabulary update strategy leveraging generative models to extend the vocabulary for novel events encountered during inference. To validate our approach, we introduce VidCap-Eval, a development set requiring concise narrations with reasoning relationships (e.g., before and after). Experiments on EgoSchema, COIN, and HiREST further demonstrate the effectiveness of VLog, highlighting its ability to generate concise, contextually accurate, and efficient narrations, offering a novel perspective on video understanding. Codes are released at https://github.com/showlab/VLog.","url_abs":"https://arxiv.org/abs/2503.09402v1","url_pdf":"https://arxiv.org/pdf/2503.09402v1.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":"vlog-video-language-models-by-generative","repo_url":"https://github.com/showlab/vlog","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":null,"task_name":"EgoSchema"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"discriminative-fine-tuning","method_name":"Discriminative Fine-Tuning"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-2","method_name":"GPT-2"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"set","method_name":"SET"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.09402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.09402"}},"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/showlab/vlog","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/showlab/VLog","reach":{"status":"ok"}}],"summary":{"ran":5,"ran_draft_wrong":1,"ran_fixture":1,"unverified":3},"by_repo_kind":{"official":{"samples":10,"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":10,"samples":[{"code_sha256_prefix":"eb3438f3ff649ddf","entry":"DropPath","repo":"showlab/VLog","repo_kind":"official","path":"VLog/model/models.py","file_url":"https://github.com/showlab/VLog/blob/HEAD/VLog/model/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eb3438f3ff649ddf"}},{"code_sha256_prefix":"77fa2643a3a1c67a","entry":"PositionEmbeddingSine","repo":"showlab/VLog","repo_kind":"official","path":"VLog/model/models.py","file_url":"https://github.com/showlab/VLog/blob/HEAD/VLog/model/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"77fa2643a3a1c67a"}},{"code_sha256_prefix":"3b38513f46a92d3f","entry":"Transformer","repo":"showlab/VLog","repo_kind":"official","path":"VLog/model/models.py","file_url":"https://github.com/showlab/VLog/blob/HEAD/VLog/model/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3b38513f46a92d3f"}},{"code_sha256_prefix":"b2e7f0187d163a01","entry":"TransformerEncoder","repo":"showlab/VLog","repo_kind":"official","path":"VLog/model/models.py","file_url":"https://github.com/showlab/VLog/blob/HEAD/VLog/model/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b2e7f0187d163a01"}},{"code_sha256_prefix":"f33ffe92f2473798","entry":"TransformerEncoderLayer","repo":"showlab/VLog","repo_kind":"official","path":"VLog/model/models.py","file_url":"https://github.com/showlab/VLog/blob/HEAD/VLog/model/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f33ffe92f2473798"}},{"code_sha256_prefix":"020b7f70a236fb97","entry":"build_position_encoding","repo":"showlab/VLog","repo_kind":"official","path":"VLog/model/models.py","file_url":"https://github.com/showlab/VLog/blob/HEAD/VLog/model/models.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"020b7f70a236fb97"}},{"code_sha256_prefix":"10e67144852e5fce","entry":"drop_path","repo":"showlab/VLog","repo_kind":"official","path":"VLog/model/models.py","file_url":"https://github.com/showlab/VLog/blob/HEAD/VLog/model/models.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"10e67144852e5fce"}},{"code_sha256_prefix":"35622089c9d95b72","entry":"ModelArgs","repo":"showlab/VLog","repo_kind":"official","path":"VLog/model/models.py","file_url":"https://github.com/showlab/VLog/blob/HEAD/VLog/model/models.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":"35622089c9d95b72"}},{"code_sha256_prefix":"ce55dd9224e4a28a","entry":"VLog","repo":"showlab/VLog","repo_kind":"official","path":"VLog/model/models.py","file_url":"https://github.com/showlab/VLog/blob/HEAD/VLog/model/models.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":"ce55dd9224e4a28a"}},{"code_sha256_prefix":"c8d145f15e26a93d","entry":"build_transformer","repo":"showlab/VLog","repo_kind":"official","path":"VLog/model/models.py","file_url":"https://github.com/showlab/VLog/blob/HEAD/VLog/model/models.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":"c8d145f15e26a93d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}