{"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":"/dataset/msvd","name":"MSVD","full_name":"Microsoft Research Video Description Corpus","description_markdown":"The **Microsoft Research Video Description Corpus** (**MSVD**) dataset consists of about 120K sentences collected during the summer of 2010. Workers on Mechanical Turk were paid to watch a short video snippet and then summarize the action in a single sentence. The result is a set of roughly parallel descriptions of more than 2,000 video snippets. Because the workers were urged to complete the task in the language of their choice, both paraphrase and bilingual alternations are captured in the data.\r\n\r\nSource: [https://www.microsoft.com/en-us/download/details.aspx?id=52422&from=https%3A%2F%2Fresearch.microsoft.com%2Fen-us%2Fdownloads%2F38cf15fd-b8df-477e-a4e4-a4680caa75af%2F](https://www.microsoft.com/en-us/download/details.aspx?id=52422&from=https%3A%2F%2Fresearch.microsoft.com%2Fen-us%2Fdownloads%2F38cf15fd-b8df-477e-a4e4-a4680caa75af%2F)\r\nImage Source: [https://arxiv.org/pdf/1609.06782.pdf](https://arxiv.org/pdf/1609.06782.pdf)","description_withheld":null,"homepage":"https://www.cs.utexas.edu/users/ml/clamp/videoDescription/","introduced_date":"2011-01-01","introduced_date_note":null,"introduced_by":{"paper":null,"title":"Collecting Highly Parallel Data for Paraphrase Evaluation","first_author":null,"url":"https://www.aclweb.org/anthology/P11-1020/"},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Video Retrieval","url":"/task/video-retrieval","datasets_with_task":"/datasets/task/video-retrieval"},{"name":"Video Captioning","url":"/task/video-captioning","datasets_with_task":"/datasets/task/video-captioning"},{"name":"Zero-Shot Video Retrieval","url":"/task/zero-shot-video-retrieval","datasets_with_task":"/datasets/task/zero-shot-video-retrieval"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["MSVD"],"data_loaders":[],"num_papers_in_archive":327,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/video-retrieval-on-msvd","task":"Video Retrieval","dataset_variant":"MSVD","rows":24,"metrics":["text-to-video R@1","text-to-video R@5","text-to-video R@10","text-to-video Median Rank","text-to-video Mean Rank","text-to-video R@50","video-to-text R@1","video-to-text R@5","video-to-text R@10","video-to-text Median Rank","video-to-text Mean Rank"],"first_row_in_archive_order":{"model":"InternVideo2-6B","paper":"/paper/internvideo2-scaling-video-foundation-models","metrics":{"text-to-video R@1":"61.4","video-to-text R@1":"85.2"},"code_links":[{"title":"opengvlab/internvideo","url":"https://github.com/opengvlab/internvideo"},{"title":"opengvlab/internvideo2","url":"https://github.com/opengvlab/internvideo2"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/video-captioning-on-msvd-1","task":"Video Captioning","dataset_variant":"MSVD","rows":16,"metrics":["CIDEr","BLEU-4","METEOR","ROUGE-L","GS"],"first_row_in_archive_order":{"model":"MaMMUT","paper":"/paper/mammut-a-simple-architecture-for-joint","metrics":{"CIDEr":"195.6"},"code_links":[{"title":"lucidrains/mammut-pytorch","url":"https://github.com/lucidrains/mammut-pytorch"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/zero-shot-video-retrieval-on-msvd","task":"Zero-Shot Video Retrieval","dataset_variant":"MSVD","rows":14,"metrics":["text-to-video R@1","text-to-video R@5","text-to-video R@10","text-to-video Median Rank","text-to-video Mean Rank","video-to-text R@1","video-to-text R@5","video-to-text R@10","video-to-text Median Rank"],"first_row_in_archive_order":{"model":"InternVideo2-6B","paper":"/paper/internvideo2-scaling-video-foundation-models","metrics":{"text-to-video R@1":"59.3","text-to-video R@10":"89.6","text-to-video R@5":"84.4","video-to-text R@1":"83.1","video-to-text R@10":"97.0","video-to-text R@5":"94.2"},"code_links":[{"title":"opengvlab/internvideo","url":"https://github.com/opengvlab/internvideo"},{"title":"opengvlab/internvideo2","url":"https://github.com/opengvlab/internvideo2"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":40,"of":40,"counts":{"papers_with_a_benchmark_row":40,"with_a_code_link":33,"where_syntology_ran_a_sample":18,"not_listed_spam_title":0,"listed":40,"listed_where_code_ran":18,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":15,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":15,"listed_every_run_a_failure_of_syntologys_instrument":3,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/internvideo2-scaling-video-foundation-models","slug":"internvideo2-scaling-video-foundation-models","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","date":"2024-03-22","arxiv_id":"2403.15377","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/vid-tldr-training-free-token-merging-for","slug":"vid-tldr-training-free-token-merging-for","title":"vid-TLDR: Training Free Token merging for Light-weight Video Transformer","date":"2024-03-20","arxiv_id":"2403.13347","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["mlvlab/vid-tldr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vid-tldr-training-free-token-merging-for#ran","syntology_url":"https://syntology.ai/paper/2403.13347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13347"}}}},{"paper":"/paper/rtq-rethinking-video-language-understanding","slug":"rtq-rethinking-video-language-understanding","title":"RTQ: Rethinking Video-language Understanding Based on Image-text Model","date":"2023-12-01","arxiv_id":"2312.00347","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/side4video-spatial-temporal-side-network-for","slug":"side4video-spatial-temporal-side-network-for","title":"Side4Video: Spatial-Temporal Side Network for Memory-Efficient Image-to-Video Transfer Learning","date":"2023-11-27","arxiv_id":"2311.15769","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/howtocaption-prompting-llms-to-transform","slug":"howtocaption-prompting-llms-to-transform","title":"HowToCaption: Prompting LLMs to Transform Video Annotations at Scale","date":"2023-10-07","arxiv_id":"2310.04900","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":5,"official":{"repos":["ninatu/howtocaption"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/howtocaption-prompting-llms-to-transform#ran","syntology_url":"https://syntology.ai/paper/2310.04900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04900"}}}},{"paper":"/paper/icocap-improving-video-captioning-by","slug":"icocap-improving-video-captioning-by","title":"IcoCap: Improving Video Captioning by Compounding Images","date":"2023-10-05","arxiv_id":null,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/languagebind-extending-video-language","slug":"languagebind-extending-video-language","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","date":"2023-10-03","arxiv_id":"2310.01852","rows_on_this_dataset":2,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":3,"official":{"repos":["pku-yuangroup/languagebind"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/languagebind-extending-video-language#ran","syntology_url":"https://syntology.ai/paper/2310.01852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01852"}}}},{"paper":"/paper/prototype-based-aleatoric-uncertainty-1","slug":"prototype-based-aleatoric-uncertainty-1","title":"Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval","date":"2023-09-29","arxiv_id":"2309.17093","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":19,"samples_ran":17,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":8,"samples_unverified":2,"pointer_only_for_licence":8,"official":{"repos":["leolee99/pau"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/prototype-based-aleatoric-uncertainty-1#ran","syntology_url":"https://syntology.ai/paper/2309.17093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17093"}}}},{"paper":"/paper/accurate-and-fast-compressed-video-captioning","slug":"accurate-and-fast-compressed-video-captioning","title":"Accurate and Fast Compressed Video Captioning","date":"2023-09-22","arxiv_id":"2309.12867","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":10,"samples_constructed":8,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["acherstyx/CoCap"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":8,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/accurate-and-fast-compressed-video-captioning#ran","syntology_url":"https://syntology.ai/paper/2309.12867","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.12867"}}}},{"paper":"/paper/dual-modal-attention-enhanced-text-video","slug":"dual-modal-attention-enhanced-text-video","title":"Dual-Modal Attention-Enhanced Text-Video Retrieval with Triplet Partial Margin Contrastive Learning","date":"2023-09-20","arxiv_id":"2309.11082","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cosa-concatenated-sample-pretrained-vision","slug":"cosa-concatenated-sample-pretrained-vision","title":"COSA: Concatenated Sample Pretrained Vision-Language Foundation Model","date":"2023-06-15","arxiv_id":"2306.09085","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vlab-enhancing-video-language-pre-training-by","slug":"vlab-enhancing-video-language-pre-training-by","title":"VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending","date":"2023-05-22","arxiv_id":"2305.13167","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/valor-vision-audio-language-omni-perception","slug":"valor-vision-audio-language-omni-perception","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","date":"2023-04-17","arxiv_id":"2304.08345","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mammut-a-simple-architecture-for-joint","slug":"mammut-a-simple-architecture-for-joint","title":"MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks","date":"2023-03-29","arxiv_id":"2303.16839","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mammut-a-simple-architecture-for-joint#ran","syntology_url":"https://syntology.ai/paper/2303.16839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16839"}}}},{"paper":"/paper/unmasked-teacher-towards-training-efficient","slug":"unmasked-teacher-towards-training-efficient","title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models","date":"2023-03-28","arxiv_id":"2303.16058","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["opengvlab/unmasked_teacher"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unmasked-teacher-towards-training-efficient#ran","syntology_url":"https://syntology.ai/paper/2303.16058","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16058"}}}},{"paper":"/paper/sem-pos-grammatically-and-semantically","slug":"sem-pos-grammatically-and-semantically","title":"SEM-POS: Grammatically and Semantically Correct Video Captioning","date":"2023-03-26","arxiv_id":"2303.14829","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/diffusionret-generative-text-video-retrieval","slug":"diffusionret-generative-text-video-retrieval","title":"DiffusionRet: Generative Text-Video Retrieval with Diffusion Model","date":"2023-03-17","arxiv_id":"2303.09867","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["jpthu17/diffusionret"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/diffusionret-generative-text-video-retrieval#ran","syntology_url":"https://syntology.ai/paper/2303.09867","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.09867"}}}},{"paper":"/paper/vid2seq-large-scale-pretraining-of-a-visual","slug":"vid2seq-large-scale-pretraining-of-a-visual","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","date":"2023-02-27","arxiv_id":"2302.14115","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/mplug-2-a-modularized-multi-modal-foundation","slug":"mplug-2-a-modularized-multi-modal-foundation","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","date":"2023-02-01","arxiv_id":"2302.00402","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":19,"samples_ran":17,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":9,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["alibaba/AliceMind"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mplug-2-a-modularized-multi-modal-foundation#ran","syntology_url":"https://syntology.ai/paper/2302.00402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.00402"}}}},{"paper":"/paper/cap4video-what-can-auxiliary-captions-do-for","slug":"cap4video-what-can-auxiliary-captions-do-for","title":"Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?","date":"2022-12-31","arxiv_id":"2301.00184","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":25,"samples_ran":20,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":11,"samples_unverified":5,"pointer_only_for_licence":11,"official":{"repos":["whwu95/Cap4Video"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/cap4video-what-can-auxiliary-captions-do-for#ran","syntology_url":"https://syntology.ai/paper/2301.00184","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.00184"}}}},{"paper":"/paper/hitea-hierarchical-temporal-aware-video","slug":"hitea-hierarchical-temporal-aware-video","title":"HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training","date":"2022-12-30","arxiv_id":"2212.14546","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/internvideo-general-video-foundation-models","slug":"internvideo-general-video-foundation-models","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","date":"2022-12-06","arxiv_id":"2212.03191","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["opengvlab/internvideo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/internvideo-general-video-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2212.03191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03191"}}}},{"paper":"/paper/an-empirical-study-of-end-to-end-video","slug":"an-empirical-study-of-end-to-end-video","title":"An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling","date":"2022-09-04","arxiv_id":"2209.01540","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/diverse-video-captioning-by-adaptive-spatio","slug":"diverse-video-captioning-by-adaptive-spatio","title":"Diverse Video Captioning by Adaptive Spatio-temporal Attention","date":"2022-08-19","arxiv_id":"2208.09266","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/x-clip-end-to-end-multi-grained-contrastive","slug":"x-clip-end-to-end-multi-grained-contrastive","title":"X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval","date":"2022-07-15","arxiv_id":"2207.07285","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["xuguohai/X-CLIP"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/x-clip-end-to-end-multi-grained-contrastive#ran","syntology_url":"https://syntology.ai/paper/2207.07285","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.07285"}}}},{"paper":"/paper/lat-latent-translation-with-cycle-consistency","slug":"lat-latent-translation-with-cycle-consistency","title":"LaT: Latent Translation with Cycle-Consistency for Video-Text Retrieval","date":"2022-07-11","arxiv_id":"2207.04858","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/centerclip-token-clustering-for-efficient","slug":"centerclip-token-clustering-for-efficient","title":"CenterCLIP: Token Clustering for Efficient Text-Video Retrieval","date":"2022-05-02","arxiv_id":"2205.00823","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["mzhaoshuai/CenterCLIP"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/centerclip-token-clustering-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2205.00823","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.00823"}}}},{"paper":"/paper/miles-visual-bert-pre-training-with-injected","slug":"miles-visual-bert-pre-training-with-injected","title":"MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval","date":"2022-04-26","arxiv_id":"2204.12408","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hunyuan-tvr-for-text-video-retrivial","slug":"hunyuan-tvr-for-text-video-retrivial","title":"Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations","date":"2022-04-07","arxiv_id":"2204.03382","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/x-pool-cross-modal-language-video-attention","slug":"x-pool-cross-modal-language-video-attention","title":"X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval","date":"2022-03-28","arxiv_id":"2203.15086","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["layer6ai-labs/xpool"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/x-pool-cross-modal-language-video-attention#ran","syntology_url":"https://syntology.ai/paper/2203.15086","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15086"}}}},{"paper":"/paper/mdmmt-2-multidomain-multimodal-transformer","slug":"mdmmt-2-multidomain-multimodal-transformer","title":"MDMMT-2: Multidomain Multimodal Transformer for Video Retrieval, One More Step Towards Generalization","date":"2022-03-14","arxiv_id":"2203.07086","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/bridgeformer-bridging-video-text-retrieval","slug":"bridgeformer-bridging-video-text-retrieval","title":"Bridging Video-text Retrieval with Multiple Choice Questions","date":"2022-01-13","arxiv_id":"2201.04850","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":24,"samples_ran":13,"samples_constructed":8,"samples_ran_checked":9,"samples_ran_instrument_failed":4,"samples_unverified":11,"pointer_only_for_licence":6,"official":{"repos":["tencentarc/mcq"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bridgeformer-bridging-video-text-retrieval#ran","syntology_url":"https://syntology.ai/paper/2201.04850","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.04850"}}}},{"paper":"/paper/cross-modal-retrieval-with-querybank","slug":"cross-modal-retrieval-with-querybank","title":"Cross Modal Retrieval with Querybank Normalisation","date":"2021-12-23","arxiv_id":"2112.12777","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["ioanacroi/qb-norm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/cross-modal-retrieval-with-querybank#ran","syntology_url":"https://syntology.ai/paper/2112.12777","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.12777"}}}},{"paper":"/paper/lightweight-attentional-feature-fusion-for","slug":"lightweight-attentional-feature-fusion-for","title":"Lightweight Attentional Feature Fusion: A New Baseline for Text-to-Video Retrieval","date":"2021-12-03","arxiv_id":"2112.01832","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improving-video-text-retrieval-by-multi","slug":"improving-video-text-retrieval-by-multi","title":"Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss","date":"2021-09-09","arxiv_id":"2109.04290","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/clip4clip-an-empirical-study-of-clip-for-end","slug":"clip4clip-an-empirical-study-of-clip-for-end","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","date":"2021-04-18","arxiv_id":"2104.08860","rows_on_this_dataset":2,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["ArrowLuo/CLIP4Clip"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/clip4clip-an-empirical-study-of-clip-for-end#ran","syntology_url":"https://syntology.ai/paper/2104.08860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08860"}}}},{"paper":"/paper/frozen-in-time-a-joint-video-and-image","slug":"frozen-in-time-a-joint-video-and-image","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","date":"2021-04-01","arxiv_id":"2104.00650","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":3,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["m-bain/frozen-in-time"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/frozen-in-time-a-joint-video-and-image#ran","syntology_url":"https://syntology.ai/paper/2104.00650","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.00650"}}}},{"paper":"/paper/a-straightforward-framework-for-video","slug":"a-straightforward-framework-for-video","title":"A Straightforward Framework For Video Retrieval Using CLIP","date":"2021-02-24","arxiv_id":"2102.12443","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/noise-estimation-using-density-estimation-for","slug":"noise-estimation-using-density-estimation-for","title":"Noise Estimation Using Density Estimation for Self-Supervised Multimodal Learning","date":"2020-03-06","arxiv_id":"2003.03186","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/use-what-you-have-video-retrieval-using","slug":"use-what-you-have-video-retrieval-using","title":"Use What You Have: Video Retrieval Using Representations From Collaborative Experts","date":"2019-07-31","arxiv_id":"1907.13487","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/use-what-you-have-video-retrieval-using#ran","syntology_url":"https://syntology.ai/paper/1907.13487","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.13487"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/internvideo2-scaling-video-foundation-models","slug":"internvideo2-scaling-video-foundation-models","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","date":"2024-03-22","arxiv_id":"2403.15377","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/vid-tldr-training-free-token-merging-for","slug":"vid-tldr-training-free-token-merging-for","title":"vid-TLDR: Training Free Token merging for Light-weight Video Transformer","date":"2024-03-20","arxiv_id":"2403.13347","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["mlvlab/vid-tldr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vid-tldr-training-free-token-merging-for#ran","syntology_url":"https://syntology.ai/paper/2403.13347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13347"}}}},{"paper":"/paper/rtq-rethinking-video-language-understanding","slug":"rtq-rethinking-video-language-understanding","title":"RTQ: Rethinking Video-language Understanding Based on Image-text Model","date":"2023-12-01","arxiv_id":"2312.00347","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/side4video-spatial-temporal-side-network-for","slug":"side4video-spatial-temporal-side-network-for","title":"Side4Video: Spatial-Temporal Side Network for Memory-Efficient Image-to-Video Transfer Learning","date":"2023-11-27","arxiv_id":"2311.15769","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/howtocaption-prompting-llms-to-transform","slug":"howtocaption-prompting-llms-to-transform","title":"HowToCaption: Prompting LLMs to Transform Video Annotations at Scale","date":"2023-10-07","arxiv_id":"2310.04900","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":5,"official":{"repos":["ninatu/howtocaption"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/howtocaption-prompting-llms-to-transform#ran","syntology_url":"https://syntology.ai/paper/2310.04900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04900"}}}},{"paper":"/paper/icocap-improving-video-captioning-by","slug":"icocap-improving-video-captioning-by","title":"IcoCap: Improving Video Captioning by Compounding Images","date":"2023-10-05","arxiv_id":null,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/languagebind-extending-video-language","slug":"languagebind-extending-video-language","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","date":"2023-10-03","arxiv_id":"2310.01852","rows_on_this_dataset":2,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":3,"official":{"repos":["pku-yuangroup/languagebind"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/languagebind-extending-video-language#ran","syntology_url":"https://syntology.ai/paper/2310.01852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01852"}}}},{"paper":"/paper/prototype-based-aleatoric-uncertainty-1","slug":"prototype-based-aleatoric-uncertainty-1","title":"Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval","date":"2023-09-29","arxiv_id":"2309.17093","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":19,"samples_ran":17,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":8,"samples_unverified":2,"pointer_only_for_licence":8,"official":{"repos":["leolee99/pau"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/prototype-based-aleatoric-uncertainty-1#ran","syntology_url":"https://syntology.ai/paper/2309.17093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17093"}}}},{"paper":"/paper/accurate-and-fast-compressed-video-captioning","slug":"accurate-and-fast-compressed-video-captioning","title":"Accurate and Fast Compressed Video Captioning","date":"2023-09-22","arxiv_id":"2309.12867","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":10,"samples_constructed":8,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["acherstyx/CoCap"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":8,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/accurate-and-fast-compressed-video-captioning#ran","syntology_url":"https://syntology.ai/paper/2309.12867","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.12867"}}}},{"paper":"/paper/dual-modal-attention-enhanced-text-video","slug":"dual-modal-attention-enhanced-text-video","title":"Dual-Modal Attention-Enhanced Text-Video Retrieval with Triplet Partial Margin Contrastive Learning","date":"2023-09-20","arxiv_id":"2309.11082","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cosa-concatenated-sample-pretrained-vision","slug":"cosa-concatenated-sample-pretrained-vision","title":"COSA: Concatenated Sample Pretrained Vision-Language Foundation Model","date":"2023-06-15","arxiv_id":"2306.09085","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vlab-enhancing-video-language-pre-training-by","slug":"vlab-enhancing-video-language-pre-training-by","title":"VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending","date":"2023-05-22","arxiv_id":"2305.13167","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/valor-vision-audio-language-omni-perception","slug":"valor-vision-audio-language-omni-perception","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","date":"2023-04-17","arxiv_id":"2304.08345","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mammut-a-simple-architecture-for-joint","slug":"mammut-a-simple-architecture-for-joint","title":"MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks","date":"2023-03-29","arxiv_id":"2303.16839","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mammut-a-simple-architecture-for-joint#ran","syntology_url":"https://syntology.ai/paper/2303.16839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16839"}}}},{"paper":"/paper/unmasked-teacher-towards-training-efficient","slug":"unmasked-teacher-towards-training-efficient","title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models","date":"2023-03-28","arxiv_id":"2303.16058","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["opengvlab/unmasked_teacher"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unmasked-teacher-towards-training-efficient#ran","syntology_url":"https://syntology.ai/paper/2303.16058","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16058"}}}},{"paper":"/paper/sem-pos-grammatically-and-semantically","slug":"sem-pos-grammatically-and-semantically","title":"SEM-POS: Grammatically and Semantically Correct Video Captioning","date":"2023-03-26","arxiv_id":"2303.14829","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/diffusionret-generative-text-video-retrieval","slug":"diffusionret-generative-text-video-retrieval","title":"DiffusionRet: Generative Text-Video Retrieval with Diffusion Model","date":"2023-03-17","arxiv_id":"2303.09867","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["jpthu17/diffusionret"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/diffusionret-generative-text-video-retrieval#ran","syntology_url":"https://syntology.ai/paper/2303.09867","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.09867"}}}},{"paper":"/paper/vid2seq-large-scale-pretraining-of-a-visual","slug":"vid2seq-large-scale-pretraining-of-a-visual","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","date":"2023-02-27","arxiv_id":"2302.14115","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/mplug-2-a-modularized-multi-modal-foundation","slug":"mplug-2-a-modularized-multi-modal-foundation","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","date":"2023-02-01","arxiv_id":"2302.00402","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":19,"samples_ran":17,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":9,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["alibaba/AliceMind"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mplug-2-a-modularized-multi-modal-foundation#ran","syntology_url":"https://syntology.ai/paper/2302.00402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.00402"}}}},{"paper":"/paper/cap4video-what-can-auxiliary-captions-do-for","slug":"cap4video-what-can-auxiliary-captions-do-for","title":"Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?","date":"2022-12-31","arxiv_id":"2301.00184","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":25,"samples_ran":20,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":11,"samples_unverified":5,"pointer_only_for_licence":11,"official":{"repos":["whwu95/Cap4Video"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/cap4video-what-can-auxiliary-captions-do-for#ran","syntology_url":"https://syntology.ai/paper/2301.00184","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.00184"}}}},{"paper":"/paper/hitea-hierarchical-temporal-aware-video","slug":"hitea-hierarchical-temporal-aware-video","title":"HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training","date":"2022-12-30","arxiv_id":"2212.14546","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/internvideo-general-video-foundation-models","slug":"internvideo-general-video-foundation-models","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","date":"2022-12-06","arxiv_id":"2212.03191","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["opengvlab/internvideo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/internvideo-general-video-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2212.03191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03191"}}}},{"paper":"/paper/an-empirical-study-of-end-to-end-video","slug":"an-empirical-study-of-end-to-end-video","title":"An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling","date":"2022-09-04","arxiv_id":"2209.01540","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/diverse-video-captioning-by-adaptive-spatio","slug":"diverse-video-captioning-by-adaptive-spatio","title":"Diverse Video Captioning by Adaptive Spatio-temporal Attention","date":"2022-08-19","arxiv_id":"2208.09266","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/x-clip-end-to-end-multi-grained-contrastive","slug":"x-clip-end-to-end-multi-grained-contrastive","title":"X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval","date":"2022-07-15","arxiv_id":"2207.07285","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["xuguohai/X-CLIP"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/x-clip-end-to-end-multi-grained-contrastive#ran","syntology_url":"https://syntology.ai/paper/2207.07285","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.07285"}}}},{"paper":"/paper/lat-latent-translation-with-cycle-consistency","slug":"lat-latent-translation-with-cycle-consistency","title":"LaT: Latent Translation with Cycle-Consistency for Video-Text Retrieval","date":"2022-07-11","arxiv_id":"2207.04858","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/centerclip-token-clustering-for-efficient","slug":"centerclip-token-clustering-for-efficient","title":"CenterCLIP: Token Clustering for Efficient Text-Video Retrieval","date":"2022-05-02","arxiv_id":"2205.00823","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["mzhaoshuai/CenterCLIP"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/centerclip-token-clustering-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2205.00823","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.00823"}}}},{"paper":"/paper/miles-visual-bert-pre-training-with-injected","slug":"miles-visual-bert-pre-training-with-injected","title":"MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval","date":"2022-04-26","arxiv_id":"2204.12408","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hunyuan-tvr-for-text-video-retrivial","slug":"hunyuan-tvr-for-text-video-retrivial","title":"Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations","date":"2022-04-07","arxiv_id":"2204.03382","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/x-pool-cross-modal-language-video-attention","slug":"x-pool-cross-modal-language-video-attention","title":"X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval","date":"2022-03-28","arxiv_id":"2203.15086","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["layer6ai-labs/xpool"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/x-pool-cross-modal-language-video-attention#ran","syntology_url":"https://syntology.ai/paper/2203.15086","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15086"}}}},{"paper":"/paper/mdmmt-2-multidomain-multimodal-transformer","slug":"mdmmt-2-multidomain-multimodal-transformer","title":"MDMMT-2: Multidomain Multimodal Transformer for Video Retrieval, One More Step Towards Generalization","date":"2022-03-14","arxiv_id":"2203.07086","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/bridgeformer-bridging-video-text-retrieval","slug":"bridgeformer-bridging-video-text-retrieval","title":"Bridging Video-text Retrieval with Multiple Choice Questions","date":"2022-01-13","arxiv_id":"2201.04850","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":24,"samples_ran":13,"samples_constructed":8,"samples_ran_checked":9,"samples_ran_instrument_failed":4,"samples_unverified":11,"pointer_only_for_licence":6,"official":{"repos":["tencentarc/mcq"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bridgeformer-bridging-video-text-retrieval#ran","syntology_url":"https://syntology.ai/paper/2201.04850","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.04850"}}}},{"paper":"/paper/cross-modal-retrieval-with-querybank","slug":"cross-modal-retrieval-with-querybank","title":"Cross Modal Retrieval with Querybank Normalisation","date":"2021-12-23","arxiv_id":"2112.12777","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["ioanacroi/qb-norm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/cross-modal-retrieval-with-querybank#ran","syntology_url":"https://syntology.ai/paper/2112.12777","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.12777"}}}},{"paper":"/paper/lightweight-attentional-feature-fusion-for","slug":"lightweight-attentional-feature-fusion-for","title":"Lightweight Attentional Feature Fusion: A New Baseline for Text-to-Video Retrieval","date":"2021-12-03","arxiv_id":"2112.01832","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improving-video-text-retrieval-by-multi","slug":"improving-video-text-retrieval-by-multi","title":"Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss","date":"2021-09-09","arxiv_id":"2109.04290","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/clip4clip-an-empirical-study-of-clip-for-end","slug":"clip4clip-an-empirical-study-of-clip-for-end","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","date":"2021-04-18","arxiv_id":"2104.08860","rows_on_this_dataset":2,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["ArrowLuo/CLIP4Clip"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/clip4clip-an-empirical-study-of-clip-for-end#ran","syntology_url":"https://syntology.ai/paper/2104.08860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08860"}}}},{"paper":"/paper/frozen-in-time-a-joint-video-and-image","slug":"frozen-in-time-a-joint-video-and-image","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","date":"2021-04-01","arxiv_id":"2104.00650","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":3,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["m-bain/frozen-in-time"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/frozen-in-time-a-joint-video-and-image#ran","syntology_url":"https://syntology.ai/paper/2104.00650","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.00650"}}}},{"paper":"/paper/a-straightforward-framework-for-video","slug":"a-straightforward-framework-for-video","title":"A Straightforward Framework For Video Retrieval Using CLIP","date":"2021-02-24","arxiv_id":"2102.12443","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/noise-estimation-using-density-estimation-for","slug":"noise-estimation-using-density-estimation-for","title":"Noise Estimation Using Density Estimation for Self-Supervised Multimodal Learning","date":"2020-03-06","arxiv_id":"2003.03186","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/use-what-you-have-video-retrieval-using","slug":"use-what-you-have-video-retrieval-using","title":"Use What You Have: Video Retrieval Using Representations From Collaborative Experts","date":"2019-07-31","arxiv_id":"1907.13487","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/use-what-you-have-video-retrieval-using#ran","syntology_url":"https://syntology.ai/paper/1907.13487","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.13487"}}}}],"papers_where_code_ran":18,"papers_where_code_ran_first_page":"/dataset/msvd/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/msvd/papers/ran/1","json":"/dataset/msvd/papers/ran/1.json","rows":18}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":19,"samples_harvested":172,"samples_ran":133,"samples_constructed":17,"samples_ran_checked":85,"samples_ran_instrument_failed":48,"samples_unverified":39,"pointer_only_for_licence":51,"papers_with_no_sample_that_ran":1,"papers_with_a_sample_that_ran":18,"papers_with_a_run_with_no_instrument_failure":15,"papers_where_every_run_was_an_instrument_failure":3,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/video-retrieval-on-msvd","since_archive":"/sota/video-retrieval-on-msvd#since-judged","papers_judged":1,"placed":0}]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"2c390f05b4799036342de2d0737cccc7b196b59ad7e152d7cd173f84f377bab9","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}