{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/advancing-high-resolution-video-language","title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions","arxiv_id":"2111.10337","date":"2021-11-19","proceeding":"CVPR 2022 1","authors":["Hongwei Xue","Tiankai Hang","Yanhong Zeng","Yuchong Sun","Bei Liu","Huan Yang","Jianlong Fu","Baining Guo"],"abstract":"We study joint video and language (VL) pre-training to enable cross-modality learning and benefit plentiful downstream VL tasks. Existing works either extract low-quality video features or learn limited text embedding, while neglecting that high-resolution videos and diversified semantics can significantly improve cross-modality learning. In this paper, we propose a novel High-resolution and Diversified VIdeo-LAnguage pre-training model (HD-VILA) for many visual tasks. In particular, we collect a large dataset with two distinct properties: 1) the first high-resolution dataset including 371.5k hours of 720p videos, and 2) the most diversified dataset covering 15 popular YouTube categories. To enable VL pre-training, we jointly optimize the HD-VILA model by a hybrid Transformer that learns rich spatiotemporal features, and a multimodal Transformer that enforces interactions of the learned video features with diversified texts. Our pre-training model achieves new state-of-the-art results in 10 VL understanding tasks and 2 more novel text-to-visual generation tasks. For example, we outperform SOTA models with relative increases of 40.4% R@1 in zero-shot MSR-VTT text-to-video retrieval task and 55.4% in high-resolution dataset LSMDC. The learned VL embedding is also effective in generating visually pleasing and semantically relevant results in text-to-visual editing and super-resolution tasks.","url_abs":"https://arxiv.org/abs/2111.10337v2","url_pdf":"https://arxiv.org/pdf/2111.10337v2.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":"advancing-high-resolution-video-language","repo_url":"https://github.com/microsoft/xpretrain","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"super-resolution","task_name":"Super-Resolution"},{"task_slug":"text-to-video-retrieval","task_name":"Text to Video Retrieval"},{"task_slug":"video-retrieval","task_name":"Video Retrieval"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"},{"task_slug":"zero-shot-video-retrieval","task_name":"Zero-Shot Video Retrieval"}],"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":"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":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-retrieval-on-activitynet","task":"Video Retrieval","dataset":"ActivityNet","model":"HD-VILA","rank_in_archive_order":28,"of":31,"metrics":{"text-to-video Median Rank":"4","text-to-video R@1":"28.5","text-to-video R@5":"57.4","text-to-video R@50":"94"},"uses_additional_data":false},{"leaderboard":"/sota/video-retrieval-on-didemo","task":"Video Retrieval","dataset":"DiDeMo","model":"HD-VILA","rank_in_archive_order":37,"of":40,"metrics":{"text-to-video Median Rank":"4","text-to-video R@1":"28.8","text-to-video R@10":"69.1","text-to-video R@5":"57.4"},"uses_additional_data":false},{"leaderboard":"/sota/video-retrieval-on-lsmdc","task":"Video Retrieval","dataset":"LSMDC","model":"HD-VILA","rank_in_archive_order":26,"of":38,"metrics":{"text-to-video Median Rank":"15","text-to-video R@1":"17.4","text-to-video R@10":"44.1","text-to-video R@5":"34.1"},"uses_additional_data":false},{"leaderboard":"/sota/video-retrieval-on-msr-vtt","task":"Video Retrieval","dataset":"MSR-VTT","model":"HD-VILA","rank_in_archive_order":17,"of":40,"metrics":{"text-to-video MedianR":"3","text-to-video R@1":"35.6","text-to-video R@10":"78","text-to-video R@5":"65.3"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-retrieval-on-msr-vtt","task":"Zero-Shot Video Retrieval","dataset":"MSR-VTT","model":"HD-VILA","rank_in_archive_order":34,"of":41,"metrics":{"text-to-video Median Rank":"15","text-to-video R@1":"14.6","text-to-video R@10":"44.1","text-to-video R@5":"34.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2111.10337","atlas_url":"https://app.syntology.ai/?focus=2111.10337","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2111.10337"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2111.10337\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2111.10337"},"call":"get_concepts_for_paper(arxiv_id=\"2111.10337\")"}],"by_repo":[{"repo":"microsoft/xpretrain","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["2209.06430","2210.06031"],"harvested_for_calls":[{"arxiv_id":"2209.06430","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2209.06430"},"call":"get_harvested_code_for_paper(arxiv_id=\"2209.06430\")"},{"arxiv_id":"2210.06031","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2210.06031"},"call":"get_harvested_code_for_paper(arxiv_id=\"2210.06031\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"08341cd562ce7b177618694f6f09ab46679a1a2f0dae69ac33b6966eec29135f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}