{"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/vlap-efficient-video-language-alignment-via","title":"ViLA: Efficient Video-Language Alignment for Video Question Answering","arxiv_id":"2312.08367","date":"2023-12-13","proceeding":null,"authors":["Xijun Wang","Junbang Liang","Chun-Kai Wang","Kenan Deng","Yu Lou","Ming Lin","Shan Yang"],"abstract":"In this work, we propose an efficient Video-Language Alignment (ViLA) network. Our ViLA model addresses both efficient frame sampling and effective cross-modal alignment in a unified way. In our ViLA network, we design a new learnable text-guided Frame-Prompter together with a new cross-modal distillation (QFormer-Distiller) module. Pre-trained large image-language models have shown promising results on problems such as visual question answering (VQA). However, how to efficiently and effectively sample video frames when adapting pre-trained large image-language model to video-language alignment is still the major challenge. Compared with prior work, our ViLA model demonstrates the capability of selecting key frames with critical contents, thus improving the video-language alignment accuracy while reducing the inference latency +3.3% on NExT-QA Temporal with 3.0X speed up). Overall, our ViLA network outperforms the state-of-the-art methods on the video question-answering benchmarks: +4.6% on STAR Interaction, +2.2% on STAR average with 3.0X speed up, ours 2-frames out-perform SeViLA 4-frames on the VLEP dataset with 4.2X speed-up. The code will be available at https://github.com/xijun-cs/ViLA.","url_abs":"https://arxiv.org/abs/2312.08367v4","url_pdf":"https://arxiv.org/pdf/2312.08367v4.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":"vlap-efficient-video-language-alignment-via","repo_url":"https://github.com/xijun-cs/vila","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"video-question-answering","task_name":"Video Question Answering"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"},{"task_slug":"cross-modal-alignment","task_name":"cross-modal alignment"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-question-answering-on-next-qa","task":"Video Question Answering","dataset":"NExT-QA","model":"ViLA (3B)","rank_in_archive_order":22,"of":47,"metrics":{"Accuracy":"75.6"},"uses_additional_data":false},{"leaderboard":"/sota/video-question-answering-on-next-qa","task":"Video Question Answering","dataset":"NExT-QA","model":"ViLA (3B, 4 frames)","rank_in_archive_order":25,"of":47,"metrics":{"Accuracy":"74.4"},"uses_additional_data":false},{"leaderboard":"/sota/video-question-answering-on-next-qa-efficient","task":"Video Question Answering","dataset":"NExT-QA (Efficient)","model":"ViLA (3B, 4 frames)","rank_in_archive_order":1,"of":2,"metrics":{"1:1 Accuracy":"74.4"},"uses_additional_data":false},{"leaderboard":"/sota/video-question-answering-on-situated","task":"Video Question Answering","dataset":"STAR Benchmark","model":"VLAP (4 frames)","rank_in_archive_order":1,"of":17,"metrics":{"Average Accuracy":"67.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.08367","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.08367"}},"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/xijun-cs/vila","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":2},"by_repo_kind":{"official":{"samples":2,"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":"f1d1cccccf038785","entry":"load_jsonl","repo":"xijun-cs/vila","repo_kind":"official","path":"vila_data/how2qa.py","file_url":"https://github.com/xijun-cs/vila/blob/HEAD/vila_data/how2qa.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f1d1cccccf038785"}},{"code_sha256_prefix":"a6ec89ee62f1d465","entry":"load_jsonl","repo":"xijun-cs/vila","repo_kind":"official","path":"vila_data/prepare_how2qa_download_pool.py","file_url":"https://github.com/xijun-cs/vila/blob/HEAD/vila_data/prepare_how2qa_download_pool.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a6ec89ee62f1d465"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}