{"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":"/task/video-alignment","name":"Video Alignment","slug":"video-alignment","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":83,"papers_with_code":43,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":4,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/video-alignment-on-msu-video-alignment-and","slug":"video-alignment-on-msu-video-alignment-and","dataset":"MSU Video Alignment and Retrieval Benchmark Suite","dataset_url":"/dataset/msu-video-alignment-and-retrieval-benchmark","rows_in_archive":4,"metrics":["Accuracy w/ 3 frames error (Light)","Accuracy w/ 3 frames error (Medium geometric)","Accuracy w/ 3 frames error (Medium color)","Accuracy w/ 3 frames error (Hard)"],"first_row_in_archive_order":{"model":"VQMT3D","paper_title":"ACCURATE METHOD OF TEMPORAL-SHIFT ESTIMATION FOR 3D VIDEO","paper_url":"/paper/accurate-method-of-temporal-shift-estimation","paper_date":"2018-06-03","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/video-alignment-on-upenn-action","slug":"video-alignment-on-upenn-action","dataset":"UPenn Action","dataset_url":"/dataset/penn-action","rows_in_archive":4,"metrics":["Kendall's Tau"],"first_row_in_archive_order":{"model":"TCC + TCN","paper_title":"Temporal Cycle-Consistency Learning","paper_url":"/paper/temporal-cycle-consistency-learning","paper_date":"2019-04-16","arxiv_id":"1904.07846","code_links":[{"title":"google-research/google-research","url":"https://github.com/google-research/google-research/tree/master/tcc"},{"title":"June01/tcc_Temporal_Cycle_Consistency_Loss.pytorch","url":"https://github.com/June01/tcc_Temporal_Cycle_Consistency_Loss.pytorch"}],"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/temporal-cycle-consistency-learning#ran","syntology_url":"https://syntology.ai/paper/1904.07846","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.07846"}},"official":null}}}],"datasets":[{"url":"/dataset/penn-action","name":"Penn Action","full_name":"","num_papers_in_archive":110},{"url":"/dataset/n-digit-mnist","name":"N-Digit MNIST","full_name":"","num_papers_in_archive":5},{"url":"/dataset/msu-video-alignment-and-retrieval-benchmark","name":"MSU Video Alignment and Retrieval Benchmark Suite","full_name":"MSU Video Alignment and Retrieval Benchmark Suite","num_papers_in_archive":3},{"url":"/dataset/ikea-assembly-in-the-wild-dataset","name":"IAW Dataset","full_name":"Ikea Assembly In The Wild Dataset","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/video-understanding","name":"Video Understanding"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":83,"of":83,"of_with_code":43,"tagged_in_all":83,"counts":{"archive_papers_tagged":83,"with_a_code_link":43,"where_syntology_ran_a_sample":17,"not_listed_spam_title":0,"listed":83,"listed_where_code_ran":17,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":13,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":13,"listed_every_run_a_failure_of_syntologys_instrument":4,"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 the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/time-contrastive-networks-self-supervised","slug":"time-contrastive-networks-self-supervised","title":"Time-Contrastive Networks: Self-Supervised Learning from Video","date":"2017-04-23","arxiv_id":"1704.06888","repositories_listed":7,"syntology":null},{"url":"/paper/hunyuanvideo-a-systematic-framework-for-large","slug":"hunyuanvideo-a-systematic-framework-for-large","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","date":"2024-12-03","arxiv_id":"2412.03603","repositories_listed":2,"syntology":{"n":27,"n_ran":18,"n_constructed":6,"n_ran_checked":6,"n_instrument":12,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":27,"phrase":"18 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 12 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/hunyuanvideo-a-systematic-framework-for-large#ran","syntology_url":"https://syntology.ai/paper/2412.03603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.03603"}},"official":{"repos":["tencent/hunyuanvideo"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":6,"n_ran_no_instrument_failure":6,"n_unverified":9,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/e-bench-subjective-aligned-benchmark-suite","slug":"e-bench-subjective-aligned-benchmark-suite","title":"VE-Bench: Subjective-Aligned Benchmark Suite for Text-Driven Video Editing Quality Assessment","date":"2024-08-21","arxiv_id":"2408.11481","repositories_listed":2,"syntology":null},{"url":"/paper/cogvideox-text-to-video-diffusion-models-with","slug":"cogvideox-text-to-video-diffusion-models-with","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","date":"2024-08-12","arxiv_id":"2408.06072","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cogvideox-text-to-video-diffusion-models-with#ran","syntology_url":"https://syntology.ai/paper/2408.06072","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.06072"}},"official":{"repos":["thudm/cogvideo"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/miradata-a-large-scale-video-dataset-with","slug":"miradata-a-large-scale-video-dataset-with","title":"MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions","date":"2024-07-08","arxiv_id":"2407.06358","repositories_listed":2,"syntology":null},{"url":"/paper/aigcbench-comprehensive-evaluation-of-image","slug":"aigcbench-comprehensive-evaluation-of-image","title":"AIGCBench: Comprehensive Evaluation of Image-to-Video Content Generated by AI","date":"2024-01-03","arxiv_id":"2401.01651","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/aigcbench-comprehensive-evaluation-of-image#ran","syntology_url":"https://syntology.ai/paper/2401.01651","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.01651"}},"official":{"repos":["benchcouncil/aigcbench"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/view-invariant-occlusion-robust-probabilistic","slug":"view-invariant-occlusion-robust-probabilistic","title":"View-Invariant, Occlusion-Robust Probabilistic Embedding for Human Pose","date":"2020-10-23","arxiv_id":"2010.13321","repositories_listed":2,"syntology":null},{"url":"/paper/view-invariant-probabilistic-embedding-for","slug":"view-invariant-probabilistic-embedding-for","title":"View-Invariant Probabilistic Embedding for Human Pose","date":"2019-12-02","arxiv_id":"1912.01001","repositories_listed":2,"syntology":null},{"url":"/paper/temporal-cycle-consistency-learning","slug":"temporal-cycle-consistency-learning","title":"Temporal Cycle-Consistency Learning","date":"2019-04-16","arxiv_id":"1904.07846","repositories_listed":2,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/temporal-cycle-consistency-learning#ran","syntology_url":"https://syntology.ai/paper/1904.07846","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.07846"}},"official":null}},{"url":"/paper/learning-from-video-and-text-via-large-scale","slug":"learning-from-video-and-text-via-large-scale","title":"Learning from Video and Text via Large-Scale Discriminative Clustering","date":"2017-07-27","arxiv_id":"1707.09074","repositories_listed":2,"syntology":null},{"url":"/paper/discovla-discrepancy-reduction-in-vision-1","slug":"discovla-discrepancy-reduction-in-vision-1","title":"DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval","date":"2025-06-10","arxiv_id":"2506.08887","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/discovla-discrepancy-reduction-in-vision-1#ran","syntology_url":"https://syntology.ai/paper/2506.08887","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.08887"}},"official":{"repos":["lunarshen/dsicovla"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hallo4-high-fidelity-dynamic-portrait","slug":"hallo4-high-fidelity-dynamic-portrait","title":"Hallo4: High-Fidelity Dynamic Portrait Animation via Direct Preference Optimization and Temporal Motion Modulation","date":"2025-05-29","arxiv_id":"2505.23525","repositories_listed":1,"syntology":null},{"url":"/paper/love-benchmarking-and-evaluating-text-to","slug":"love-benchmarking-and-evaluating-text-to","title":"LOVE: Benchmarking and Evaluating Text-to-Video Generation and Video-to-Text Interpretation","date":"2025-05-17","arxiv_id":"2505.12098","repositories_listed":1,"syntology":null},{"url":"/paper/hunyuancustom-a-multimodal-driven","slug":"hunyuancustom-a-multimodal-driven","title":"HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation","date":"2025-05-07","arxiv_id":"2505.04512","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hunyuancustom-a-multimodal-driven#ran","syntology_url":"https://syntology.ai/paper/2505.04512","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.04512"}},"official":null}},{"url":"/paper/video4dgen-enhancing-video-and-4d-generation","slug":"video4dgen-enhancing-video-and-4d-generation","title":"Video4DGen: Enhancing Video and 4D Generation through Mutual Optimization","date":"2025-04-05","arxiv_id":"2504.04153","repositories_listed":1,"syntology":null},{"url":"/paper/vrmdiff-text-guided-video-referring-matting","slug":"vrmdiff-text-guided-video-referring-matting","title":"VRMDiff: Text-Guided Video Referring Matting Generation of Diffusion","date":"2025-03-11","arxiv_id":"2503.10678","repositories_listed":1,"syntology":null},{"url":"/paper/deep-understanding-of-sign-language-for-sign","slug":"deep-understanding-of-sign-language-for-sign","title":"Deep Understanding of Sign Language for Sign to Subtitle Alignment","date":"2025-03-05","arxiv_id":"2503.03287","repositories_listed":1,"syntology":null},{"url":"/paper/inference-time-text-to-video-alignment-with","slug":"inference-time-text-to-video-alignment-with","title":"Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search","date":"2025-01-31","arxiv_id":"2501.19252","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":1,"n_honours":3,"n_violates":0,"n_no_contract":1,"n_pointer_only":6,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/inference-time-text-to-video-alignment-with#ran","syntology_url":"https://syntology.ai/paper/2501.19252","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.19252"}},"official":null}},{"url":"/paper/sound-bridge-associating-egocentric-and","slug":"sound-bridge-associating-egocentric-and","title":"Sound Bridge: Associating Egocentric and Exocentric Videos via Audio Cues","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/neuro-symbolic-evaluation-of-text-to-video","slug":"neuro-symbolic-evaluation-of-text-to-video","title":"Neuro-Symbolic Evaluation of Text-to-Video Models using Formal Verification","date":"2024-11-22","arxiv_id":"2411.16718","repositories_listed":1,"syntology":null},{"url":"/paper/t2v-turbo-v2-enhancing-video-generation-model","slug":"t2v-turbo-v2-enhancing-video-generation-model","title":"T2V-Turbo-v2: Enhancing Video Generation Model Post-Training through Data, Reward, and Conditional Guidance Design","date":"2024-10-08","arxiv_id":"2410.05677","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/t2v-turbo-v2-enhancing-video-generation-model#ran","syntology_url":"https://syntology.ai/paper/2410.05677","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05677"}},"official":null}},{"url":"/paper/mamba-enhanced-text-audio-video-alignment","slug":"mamba-enhanced-text-audio-video-alignment","title":"Mamba-Enhanced Text-Audio-Video Alignment Network for Emotion Recognition in Conversations","date":"2024-09-08","arxiv_id":"2409.05243","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-contrastive-learning-for-9","slug":"self-supervised-contrastive-learning-for-9","title":"Self-Supervised Contrastive Learning for Videos using Differentiable Local Alignment","date":"2024-09-06","arxiv_id":"2409.04607","repositories_listed":1,"syntology":null},{"url":"/paper/foleycrafter-bring-silent-videos-to-life-with","slug":"foleycrafter-bring-silent-videos-to-life-with","title":"FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds","date":"2024-07-01","arxiv_id":"2407.01494","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":7,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/foleycrafter-bring-silent-videos-to-life-with#ran","syntology_url":"https://syntology.ai/paper/2407.01494","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01494"}},"official":{"repos":["open-mmlab/foleycrafter"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/safesora-towards-safety-alignment-of","slug":"safesora-towards-safety-alignment-of","title":"SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset","date":"2024-06-20","arxiv_id":"2406.14477","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/safesora-towards-safety-alignment-of#ran","syntology_url":"https://syntology.ai/paper/2406.14477","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14477"}},"official":{"repos":["pku-alignment/safe-sora"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/listen-then-see-video-alignment-with-speaker","slug":"listen-then-see-video-alignment-with-speaker","title":"Listen Then See: Video Alignment with Speaker Attention","date":"2024-04-21","arxiv_id":"2404.13530","repositories_listed":1,"syntology":null},{"url":"/paper/cococo-improving-text-guided-video-inpainting","slug":"cococo-improving-text-guided-video-inpainting","title":"CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Controllability and Compatibility","date":"2024-03-18","arxiv_id":"2403.12035","repositories_listed":1,"syntology":null},{"url":"/paper/subjective-aligned-dateset-and-metric-for","slug":"subjective-aligned-dateset-and-metric-for","title":"Subjective-Aligned Dataset and Metric for Text-to-Video Quality Assessment","date":"2024-03-18","arxiv_id":"2403.11956","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/subjective-aligned-dateset-and-metric-for#ran","syntology_url":"https://syntology.ai/paper/2403.11956","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11956"}},"official":{"repos":["qmme/t2vqa"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/evalcrafter-benchmarking-and-evaluating-large","slug":"evalcrafter-benchmarking-and-evaluating-large","title":"EvalCrafter: Benchmarking and Evaluating Large Video Generation Models","date":"2023-10-17","arxiv_id":"2310.11440","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":11,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/evalcrafter-benchmarking-and-evaluating-large#ran","syntology_url":"https://syntology.ai/paper/2310.11440","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.11440"}},"official":{"repos":["EvalCrafter/EvalCrafter"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/show-1-marrying-pixel-and-latent-diffusion","slug":"show-1-marrying-pixel-and-latent-diffusion","title":"Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation","date":"2023-09-27","arxiv_id":"2309.15818","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/show-1-marrying-pixel-and-latent-diffusion#ran","syntology_url":"https://syntology.ai/paper/2309.15818","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.15818"}},"official":{"repos":["showlab/show-1"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-solution-to-cvpr-2023-aqtc-challenge-video","slug":"a-solution-to-cvpr-2023-aqtc-challenge-video","title":"A Solution to CVPR'2023 AQTC Challenge: Video Alignment for Multi-Step Inference","date":"2023-06-26","arxiv_id":"2306.14412","repositories_listed":1,"syntology":null},{"url":"/paper/seeing-the-pose-in-the-pixels-learning-pose","slug":"seeing-the-pose-in-the-pixels-learning-pose","title":"Seeing the Pose in the Pixels: Learning Pose-Aware Representations in Vision Transformers","date":"2023-06-15","arxiv_id":"2306.09331","repositories_listed":1,"syntology":null},{"url":"/paper/videofactory-swap-attention-in-spatiotemporal","slug":"videofactory-swap-attention-in-spatiotemporal","title":"Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation","date":"2023-05-18","arxiv_id":"2305.10874","repositories_listed":1,"syntology":null},{"url":"/paper/edit-as-you-wish-video-description-editing","slug":"edit-as-you-wish-video-description-editing","title":"Edit As You Wish: Video Caption Editing with Multi-grained User Control","date":"2023-05-15","arxiv_id":"2305.08389","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-video-editing-using-off-the-shelf","slug":"zero-shot-video-editing-using-off-the-shelf","title":"Zero-Shot Video Editing Using Off-The-Shelf Image Diffusion Models","date":"2023-03-30","arxiv_id":"2303.17599","repositories_listed":1,"syntology":null},{"url":"/paper/aligning-step-by-step-instructional-diagrams","slug":"aligning-step-by-step-instructional-diagrams","title":"Aligning Step-by-Step Instructional Diagrams to Video Demonstrations","date":"2023-03-24","arxiv_id":"2303.13800","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/aligning-step-by-step-instructional-diagrams#ran","syntology_url":"https://syntology.ai/paper/2303.13800","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.13800"}},"official":{"repos":["DavidZhang73/AssemblyVideoManualAlignment"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/weakly-supervised-video-representation","slug":"weakly-supervised-video-representation","title":"Weakly Supervised Video Representation Learning with Unaligned Text for Sequential Videos","date":"2023-03-22","arxiv_id":"2303.12370","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/weakly-supervised-video-representation#ran","syntology_url":"https://syntology.ai/paper/2303.12370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.12370"}},"official":{"repos":["svip-lab/weaksvr"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-a-grammar-inducer-from-massive","slug":"learning-a-grammar-inducer-from-massive","title":"Learning a Grammar Inducer from Massive Uncurated Instructional Videos","date":"2022-10-22","arxiv_id":"2210.12309","repositories_listed":1,"syntology":null},{"url":"/paper/learning-viewpoint-agnostic-visual","slug":"learning-viewpoint-agnostic-visual","title":"Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space","date":"2022-06-23","arxiv_id":"2206.11895","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/learning-viewpoint-agnostic-visual#ran","syntology_url":"https://syntology.ai/paper/2206.11895","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.11895"}},"official":{"repos":["elicassion/3dtrl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/frame-wise-action-representations-for-long","slug":"frame-wise-action-representations-for-long","title":"Frame-wise Action Representations for Long Videos via Sequence Contrastive Learning","date":"2022-03-28","arxiv_id":"2203.14957","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/frame-wise-action-representations-for-long#ran","syntology_url":"https://syntology.ai/paper/2203.14957","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.14957"}},"official":{"repos":["minghchen/carl_code"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/adversarial-skill-networks-unsupervised-robot","slug":"adversarial-skill-networks-unsupervised-robot","title":"Adversarial Skill Networks: Unsupervised Robot Skill Learning from Video","date":"2019-10-21","arxiv_id":"1910.09430","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-temporal-alignment-of-speech-to-lips","slug":"dynamic-temporal-alignment-of-speech-to-lips","title":"Dynamic Temporal Alignment of Speech to Lips","date":"2018-08-19","arxiv_id":"1808.06250","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dynamic-temporal-alignment-of-speech-to-lips#ran","syntology_url":"https://syntology.ai/paper/1808.06250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.06250"}},"official":{"repos":["tavihalperin/AV-sync"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lamv-learning-to-align-and-match-videos-with","slug":"lamv-learning-to-align-and-match-videos-with","title":"LAMV: Learning to Align and Match Videos With Kernelized Temporal Layers","date":"2018-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":null,"slug":"audio-sync-video-generation-with-multi-stream","title":"Audio-Sync Video Generation with Multi-Stream Temporal Control","date":"2025-06-09","arxiv_id":"2506.08003","repositories_listed":0,"syntology":null},{"url":null,"slug":"dape-dual-stage-parameter-efficient-fine","title":"DAPE: Dual-Stage Parameter-Efficient Fine-Tuning for Consistent Video Editing with Diffusion Models","date":"2025-05-11","arxiv_id":"2505.07057","repositories_listed":0,"syntology":null},{"url":null,"slug":"dyst-xl-dynamic-layout-planning-and-content","title":"DyST-XL: Dynamic Layout Planning and Content Control for Compositional Text-to-Video Generation","date":"2025-04-21","arxiv_id":"2504.15032","repositories_listed":0,"syntology":null},{"url":null,"slug":"smooth-foley-creating-continuous-sound-for","title":"Smooth-Foley: Creating Continuous Sound for Video-to-Audio Generation Under Semantic Guidance","date":"2024-12-24","arxiv_id":"2412.18157","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-dynamic-object-interactions-in-text","title":"Improving Dynamic Object Interactions in Text-to-Video Generation with AI Feedback","date":"2024-12-03","arxiv_id":"2412.02617","repositories_listed":0,"syntology":null},{"url":null,"slug":"videorepair-improving-text-to-video","title":"VideoRepair: Improving Text-to-Video Generation via Misalignment Evaluation and Localized Refinement","date":"2024-11-22","arxiv_id":"2411.15115","repositories_listed":0,"syntology":null},{"url":null,"slug":"koala-36m-a-large-scale-video-dataset","title":"Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Content","date":"2024-10-10","arxiv_id":"2410.08260","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-localize-actions-in-instructional","title":"Learning to Localize Actions in Instructional Videos with LLM-Based Multi-Pathway Text-Video Alignment","date":"2024-09-22","arxiv_id":"2409.16145","repositories_listed":0,"syntology":null},{"url":null,"slug":"sync-from-the-sea-retrieving-alignable-videos","title":"Sync from the Sea: Retrieving Alignable Videos from Large-Scale Datasets","date":"2024-09-02","arxiv_id":"2409.01445","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-aigc-video-quality-assessment-a","title":"Benchmarking Multi-dimensional AIGC Video Quality Assessment: A Dataset and Unified Model","date":"2024-07-31","arxiv_id":"2407.21408","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-review-of-few-shot-action","title":"A Comprehensive Review of Few-shot Action Recognition","date":"2024-07-20","arxiv_id":"2407.14744","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-gui-scene-learning-and-video","title":"Semantic GUI Scene Learning and Video Alignment for Detecting Duplicate Video-based Bug Reports","date":"2024-07-11","arxiv_id":"2407.08610","repositories_listed":0,"syntology":null},{"url":null,"slug":"align-and-aggregate-compositional-reasoning-1","title":"Align and Aggregate: Compositional Reasoning with Video Alignment and Answer Aggregation for Video Question-Answering","date":"2024-07-03","arxiv_id":"2407.03008","repositories_listed":0,"syntology":null},{"url":null,"slug":"aniclipart-clipart-animation-with-text-to","title":"AniClipart: Clipart Animation with Text-to-Video Priors","date":"2024-04-18","arxiv_id":"2404.12347","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-up-video-summarization-pretraining","title":"Scaling Up Video Summarization Pretraining with Large Language Models","date":"2024-04-04","arxiv_id":"2404.03398","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-effects-of-short-video-sharing-services","title":"The Effects of Short Video-Sharing Services on Video Copy Detection","date":"2024-03-26","arxiv_id":"2403.18158","repositories_listed":0,"syntology":null},{"url":null,"slug":"fastvideoedit-leveraging-consistency-models","title":"FastVideoEdit: Leveraging Consistency Models for Efficient Text-to-Video Editing","date":"2024-03-10","arxiv_id":"2403.06269","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-better-metric-for-text-to-video","title":"Towards A Better Metric for Text-to-Video Generation","date":"2024-01-15","arxiv_id":"2401.07781","repositories_listed":0,"syntology":null},{"url":null,"slug":"frequency-aware-event-based-video-deblurring","title":"Frequency-aware Event-based Video Deblurring for Real-World Motion Blur","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-predict-activity-progress-by-self","title":"Learning to Predict Activity Progress by Self-Supervised Video Alignment","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lifelong-audio-video-masked-autoencoder-with","title":"STELLA: Continual Audio-Video Pre-training with Spatio-Temporal Localized Alignment","date":"2023-10-12","arxiv_id":"2310.08204","repositories_listed":0,"syntology":null},{"url":"/paper/audio-enhanced-text-to-video-retrieval-using","slug":"audio-enhanced-text-to-video-retrieval-using","title":"Audio-Enhanced Text-to-Video Retrieval using Text-Conditioned Feature Alignment","date":"2023-07-24","arxiv_id":"2307.12964","repositories_listed":0,"syntology":null},{"url":null,"slug":"contentctr-frame-level-live-streaming-click","title":"ContentCTR: Frame-level Live Streaming Click-Through Rate Prediction with Multimodal Transformer","date":"2023-06-26","arxiv_id":"2306.14392","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-ground-instructional-articles-in","title":"Learning to Ground Instructional Articles in Videos through Narrations","date":"2023-06-06","arxiv_id":"2306.03802","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-by-aligning-2d-skeleton-sequences-in","title":"Learning by Aligning 2D Skeleton Sequences and Multi-Modality Fusion","date":"2023-05-31","arxiv_id":"2305.19480","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-alignment-using-unsupervised-learning","title":"Video alignment using unsupervised learning of local and global features","date":"2023-04-13","arxiv_id":"2304.06841","repositories_listed":0,"syntology":null},{"url":null,"slug":"vader-video-alignment-differencing-and","title":"VADER: Video Alignment Differencing and Retrieval","date":"2023-03-23","arxiv_id":"2303.13193","repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-representation-learning-for-1","title":"Weakly-supervised Representation Learning for Video Alignment and Analysis","date":"2023-02-08","arxiv_id":"2302.04064","repositories_listed":0,"syntology":null},{"url":"/paper/pidro-parallel-isomeric-attention-with","slug":"pidro-parallel-isomeric-attention-with","title":"PIDRo: Parallel Isomeric Attention with Dynamic Routing for Text-Video Retrieval","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-and-weakly-supervised","title":"Self-supervised and Weakly Supervised Contrastive Learning for Frame-wise Action Representations","date":"2022-12-06","arxiv_id":"2212.03125","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-by-aligning-videos-in-time","title":"Learning by Aligning Videos in Time","date":"2021-03-31","arxiv_id":"2103.17260","repositories_listed":0,"syntology":null},{"url":null,"slug":"normalized-human-pose-features-for-human","title":"Normalized Human Pose Features for Human Action Video Alignment","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/shot-by-shot-movie-version-comparison","slug":"shot-by-shot-movie-version-comparison","title":"Shot-by-Shot Movie Version Comparison","date":"2018-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"teaching-machines-to-understand-baseball","title":"Teaching Machines to Understand Baseball Games: Large-Scale Baseball Video Database for Multiple Video Understanding Tasks","date":"2018-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-align-images-using-weak-geometric","title":"Learning to Align Images using Weak Geometric Supervision","date":"2018-08-04","arxiv_id":"1808.01424","repositories_listed":0,"syntology":null},{"url":"/paper/accurate-method-of-temporal-shift-estimation","slug":"accurate-method-of-temporal-shift-estimation","title":"ACCURATE METHOD OF TEMPORAL-SHIFT ESTIMATION FOR 3D VIDEO","date":"2018-06-03","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-robust-video-synchronization-without","title":"Learning Robust Video Synchronization without Annotations","date":"2016-10-19","arxiv_id":"1610.05985","repositories_listed":0,"syntology":null},{"url":"/paper/shuffle-and-learn-unsupervised-learning-using","slug":"shuffle-and-learn-unsupervised-learning-using","title":"Shuffle and Learn: Unsupervised Learning using Temporal Order Verification","date":"2016-03-28","arxiv_id":"1603.08561","repositories_listed":0,"syntology":null},{"url":null,"slug":"book2movie-aligning-video-scenes-with-book","title":"Book2Movie: Aligning Video Scenes With Book Chapters","date":"2015-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"road-detection-via-on-line-label-transfer","title":"Road Detection via On--line Label Transfer","date":"2014-12-10","arxiv_id":"1412.3159","repositories_listed":0,"syntology":null}],"syntology_records":18,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_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'","n_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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"papers_where_code_ran":17,"papers_where_code_ran_first_page":"/task/video-alignment/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/video-alignment/papers/ran/1","json":"/task/video-alignment/papers/ran/1.json","rows":17}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper 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"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"870b8c1c817fb08139370cd9b2e1adb0b31aec0edadb9f41d199223a687e6700","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}