{"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/infty-video-a-training-free-approach-to-long","title":"$\\infty$-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation","arxiv_id":"2501.19098","date":"2025-01-31","proceeding":null,"authors":["Saul Santos","António Farinhas","Daniel C. McNamee","André F. T. Martins"],"abstract":"Current video-language models struggle with long-video understanding due to limited context lengths and reliance on sparse frame subsampling, often leading to information loss. This paper introduces $\\infty$-Video, which can process arbitrarily long videos through a continuous-time long-term memory (LTM) consolidation mechanism. Our framework augments video Q-formers by allowing them to process unbounded video contexts efficiently and without requiring additional training. Through continuous attention, our approach dynamically allocates higher granularity to the most relevant video segments, forming \"sticky\" memories that evolve over time. Experiments with Video-LLaMA and VideoChat2 demonstrate improved performance in video question-answering tasks, showcasing the potential of continuous-time LTM mechanisms to enable scalable and training-free comprehension of long videos.","url_abs":"https://arxiv.org/abs/2501.19098v2","url_pdf":"https://arxiv.org/pdf/2501.19098v2.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":"infty-video-a-training-free-approach-to-long","repo_url":"https://github.com/deep-spin/infinite-video","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"video-question-answering","task_name":"Video Question Answering"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2501.19098","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.19098"}},"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/deep-spin/infinite-video","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":"5b14ccbef0d4360a","entry":"check_answer_egoschema","repo":"deep-spin/infinite-video","repo_kind":"official","path":"infty-VideoChat2/eval_code/run_nextqa_mistral.py","file_url":"https://github.com/deep-spin/infinite-video/blob/HEAD/infty-VideoChat2/eval_code/run_nextqa_mistral.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5b14ccbef0d4360a"}},{"code_sha256_prefix":"9ed8b954fac93d9d","entry":"process_qa","repo":"deep-spin/infinite-video","repo_kind":"official","path":"infty-Video-LLaMA/eval_code/eval/run_inference_inf_video_llama_egochema.py","file_url":"https://github.com/deep-spin/infinite-video/blob/HEAD/infty-Video-LLaMA/eval_code/eval/run_inference_inf_video_llama_egochema.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9ed8b954fac93d9d"}},{"code_sha256_prefix":"88959200d487da89","entry":"get_video_fragments","repo":"deep-spin/infinite-video","repo_kind":"official","path":"infty-Video-LLaMA/eval_code/eval/run_inference_inf_video_llama_egochema.py","file_url":"https://github.com/deep-spin/infinite-video/blob/HEAD/infty-Video-LLaMA/eval_code/eval/run_inference_inf_video_llama_egochema.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":"88959200d487da89"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}