{"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/visual-storytelling","name":"Visual Storytelling","slug":"visual-storytelling","description_markdown":"<span style=\"color:grey; opacity: 0.6\">( Image credit: [No Metrics Are Perfect](https://github.com/eric-xw/AREL) )</span>","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":115,"papers_with_code":37,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":1,"parent_tasks":2},"benchmarks":[{"leaderboard":"/sota/visual-storytelling-on-vist","slug":"visual-storytelling-on-vist","dataset":"VIST","dataset_url":"/dataset/vist","rows_in_archive":33,"metrics":["BLEU-4","CIDEr","METEOR","BLEU-1","BLEU-2","BLEU-3","ROUGE-L","SPICE","BLEURT","MLTD"],"first_row_in_archive_order":{"model":"HEGR","paper_title":"Two Heads are Better Than One: Hypergraph-Enhanced Graph Reasoning for Visual Event Ratiocination","paper_url":"/paper/two-heads-are-better-than-one-hypergraph","paper_date":"2021-07-18","arxiv_id":null,"code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/vist","name":"VIST","full_name":"Visual Storytelling","num_papers_in_archive":107},{"url":"/dataset/visual-writing-prompts","name":"Visual Writing Prompts","full_name":"","num_papers_in_archive":3},{"url":"/dataset/vist-edit","name":"VIST-Edit","full_name":"VIST-Edit","num_papers_in_archive":2},{"url":"/dataset/creative-visual-storytelling-anthology","name":"Creative Visual Storytelling Anthology","full_name":"ARL Creative Visual Storytelling Anthology","num_papers_in_archive":1}],"subtasks":[{"url":"/task/image-guided-story-ending-generation","name":"Image-guided Story Ending Generation"}],"parent_tasks":[{"url":"/task/data-to-text-generation","name":"Data-to-Text Generation"},{"url":"/task/story-generation","name":"Story Generation"}],"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":2,"rows_per_page":100,"shown":100,"of":115,"of_with_code":37,"tagged_in_all":115,"counts":{"archive_papers_tagged":115,"with_a_code_link":37,"where_syntology_ran_a_sample":4,"not_listed_spam_title":0,"listed":115,"listed_where_code_ran":4,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":4,"listed_every_run_a_failure_of_syntologys_instrument":0,"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/alfie-democratising-rgba-image-generation","slug":"alfie-democratising-rgba-image-generation","title":"Alfie: Democratising RGBA Image Generation With No $$$","date":"2024-08-27","arxiv_id":"2408.14826","repositories_listed":2,"syntology":null},{"url":"/paper/aesop-abstract-encoding-of-stories-objects","slug":"aesop-abstract-encoding-of-stories-objects","title":"AESOP: Abstract Encoding of Stories, Objects, and Pictures","date":"2021-01-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/contextualize-show-and-tell-a-neural-visual","slug":"contextualize-show-and-tell-a-neural-visual","title":"Contextualize, Show and Tell: A Neural Visual Storyteller","date":"2018-06-03","arxiv_id":"1806.00738","repositories_listed":2,"syntology":null},{"url":"/paper/no-metrics-are-perfect-adversarial-reward","slug":"no-metrics-are-perfect-adversarial-reward","title":"No Metrics Are Perfect: Adversarial Reward Learning for Visual Storytelling","date":"2018-04-24","arxiv_id":"1804.09160","repositories_listed":2,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 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; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/no-metrics-are-perfect-adversarial-reward#ran","syntology_url":"https://syntology.ai/paper/1804.09160","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.09160"}},"official":{"repos":["littlekobe/AREL"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/consistent-story-generation-with-asymmetry","slug":"consistent-story-generation-with-asymmetry","title":"Consistent Story Generation with Asymmetry Zigzag Sampling","date":"2025-06-11","arxiv_id":"2506.09612","repositories_listed":1,"syntology":null},{"url":"/paper/storyreasoning-dataset-using-chain-of-thought","slug":"storyreasoning-dataset-using-chain-of-thought","title":"StoryReasoning Dataset: Using Chain-of-Thought for Scene Understanding and Grounded Story Generation","date":"2025-05-15","arxiv_id":"2505.10292","repositories_listed":1,"syntology":null},{"url":"/paper/flip-reasoning-challenge","slug":"flip-reasoning-challenge","title":"FLIP Reasoning Challenge","date":"2025-04-16","arxiv_id":"2504.12256","repositories_listed":1,"syntology":null},{"url":"/paper/flipsketch-flipping-static-drawings-to-text","slug":"flipsketch-flipping-static-drawings-to-text","title":"FlipSketch: Flipping Static Drawings to Text-Guided Sketch Animations","date":"2024-11-16","arxiv_id":"2411.10818","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-large-language-models-and-tunings","slug":"multimodal-large-language-models-and-tunings","title":"Multimodal Large Language Models and Tunings: Vision, Language, Sensors, Audio, and Beyond","date":"2024-10-08","arxiv_id":"2410.05608","repositories_listed":1,"syntology":null},{"url":"/paper/openstory-a-large-scale-dataset-and-benchmark","slug":"openstory-a-large-scale-dataset-and-benchmark","title":"Openstory++: A Large-scale Dataset and Benchmark for Instance-aware Open-domain Visual Storytelling","date":"2024-08-07","arxiv_id":"2408.03695","repositories_listed":1,"syntology":null},{"url":"/paper/temporalstory-enhancing-consistency-in-story","slug":"temporalstory-enhancing-consistency-in-story","title":"ContextualStory: Consistent Visual Storytelling with Spatially-Enhanced and Storyline Context","date":"2024-07-13","arxiv_id":"2407.09774","repositories_listed":1,"syntology":null},{"url":"/paper/not-yet-the-whole-story-evaluating-visual","slug":"not-yet-the-whole-story-evaluating-visual","title":"Not (yet) the whole story: Evaluating Visual Storytelling Requires More than Measuring Coherence, Grounding, and Repetition","date":"2024-07-05","arxiv_id":"2407.04559","repositories_listed":1,"syntology":null},{"url":"/paper/comm-a-coherent-interleaved-image-text","slug":"comm-a-coherent-interleaved-image-text","title":"CoMM: A Coherent Interleaved Image-Text Dataset for Multimodal Understanding and Generation","date":"2024-06-15","arxiv_id":"2406.10462","repositories_listed":1,"syntology":null},{"url":"/paper/gorgeous-create-your-desired-character-facial","slug":"gorgeous-create-your-desired-character-facial","title":"Gorgeous: Create Your Desired Character Facial Makeup from Any Ideas","date":"2024-04-22","arxiv_id":"2404.13944","repositories_listed":1,"syntology":null},{"url":"/paper/intelligent-grimm-open-ended-visual-1","slug":"intelligent-grimm-open-ended-visual-1","title":"Intelligent Grimm - Open-ended Visual Storytelling via Latent Diffusion Models","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/inkn-hue-enhancing-manga-colorization-from","slug":"inkn-hue-enhancing-manga-colorization-from","title":"inkn'hue: Enhancing Manga Colorization from Multiple Priors with Alignment Multi-Encoder VAE","date":"2023-11-03","arxiv_id":"2311.01804","repositories_listed":1,"syntology":null},{"url":"/paper/groovist-a-metric-for-grounding-objects-in","slug":"groovist-a-metric-for-grounding-objects-in","title":"GROOViST: A Metric for Grounding Objects in Visual Storytelling","date":"2023-10-26","arxiv_id":"2310.17770","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"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) · 1 unverified","sample_list":"/paper/groovist-a-metric-for-grounding-objects-in#ran","syntology_url":"https://syntology.ai/paper/2310.17770","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.17770"}},"official":{"repos":["akskuchi/groovist"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/envisioning-narrative-intelligence-a-creative","slug":"envisioning-narrative-intelligence-a-creative","title":"Envisioning Narrative Intelligence: A Creative Visual Storytelling Anthology","date":"2023-10-06","arxiv_id":"2310.04529","repositories_listed":1,"syntology":null},{"url":"/paper/touchstone-evaluating-vision-language-models","slug":"touchstone-evaluating-vision-language-models","title":"TouchStone: Evaluating Vision-Language Models by Language Models","date":"2023-08-31","arxiv_id":"2308.16890","repositories_listed":1,"syntology":null},{"url":"/paper/animate-a-story-storytelling-with-retrieval","slug":"animate-a-story-storytelling-with-retrieval","title":"Animate-A-Story: Storytelling with Retrieval-Augmented Video Generation","date":"2023-07-13","arxiv_id":"2307.06940","repositories_listed":1,"syntology":null},{"url":"/paper/intelligent-grimm-open-ended-visual","slug":"intelligent-grimm-open-ended-visual","title":"Intelligent Grimm -- Open-ended Visual Storytelling via Latent Diffusion Models","date":"2023-06-01","arxiv_id":"2306.00973","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/intelligent-grimm-open-ended-visual#ran","syntology_url":"https://syntology.ai/paper/2306.00973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00973"}},"official":{"repos":["haoningwu3639/StoryGen"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/visual-transformation-telling","slug":"visual-transformation-telling","title":"Visual Transformation Telling","date":"2023-05-03","arxiv_id":"2305.01928","repositories_listed":1,"syntology":null},{"url":"/paper/detecting-and-grounding-important-characters","slug":"detecting-and-grounding-important-characters","title":"Detecting and Grounding Important Characters in Visual Stories","date":"2023-03-30","arxiv_id":"2303.17647","repositories_listed":1,"syntology":null},{"url":"/paper/positional-diffusion-ordering-unordered-sets","slug":"positional-diffusion-ordering-unordered-sets","title":"Positional Diffusion: Ordering Unordered Sets with Diffusion Probabilistic Models","date":"2023-03-20","arxiv_id":"2303.11120","repositories_listed":1,"syntology":null},{"url":"/paper/rovist-learning-robust-metrics-for-visual-2","slug":"rovist-learning-robust-metrics-for-visual-2","title":"RoViST: Learning Robust Metrics for Visual Storytelling","date":"2022-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/expressive-scene-graph-generation-using","slug":"expressive-scene-graph-generation-using","title":"Expressive Scene Graph Generation Using Commonsense Knowledge Infusion for Visual Understanding and Reasoning","date":"2022-05-31","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/rovist-learning-robust-metrics-for-visual-1","slug":"rovist-learning-robust-metrics-for-visual-1","title":"RoViST:Learning Robust Metrics for Visual Storytelling","date":"2022-05-08","arxiv_id":"2205.03774","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-rank-visual-stories-from-human-1","slug":"learning-to-rank-visual-stories-from-human-1","title":"Learning to Rank Visual Stories From Human Ranking Data","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/plot-and-rework-modeling-storylines-for","slug":"plot-and-rework-modeling-storylines-for","title":"Plot and Rework: Modeling Storylines for Visual Storytelling","date":"2021-05-14","arxiv_id":"2105.06950","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-enriched-visual-storytelling","slug":"knowledge-enriched-visual-storytelling","title":"Knowledge-Enriched Visual Storytelling","date":"2019-12-03","arxiv_id":"1912.01496","repositories_listed":1,"syntology":null},{"url":"/paper/what-makes-a-good-story-designing-composite","slug":"what-makes-a-good-story-designing-composite","title":"What Makes A Good Story? Designing Composite Rewards for Visual Storytelling","date":"2019-09-11","arxiv_id":"1909.05316","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/what-makes-a-good-story-designing-composite#ran","syntology_url":"https://syntology.ai/paper/1909.05316","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.05316"}},"official":{"repos":["JunjieHu/ReCo-RL"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/informative-visual-storytelling-with-cross","slug":"informative-visual-storytelling-with-cross","title":"Informative Visual Storytelling with Cross-modal Rules","date":"2019-07-07","arxiv_id":"1907.03240","repositories_listed":1,"syntology":null},{"url":"/paper/visual-story-post-editing","slug":"visual-story-post-editing","title":"Visual Story Post-Editing","date":"2019-06-05","arxiv_id":"1906.01764","repositories_listed":1,"syntology":null},{"url":"/paper/knowledgeable-storyteller-a-commonsense","slug":"knowledgeable-storyteller-a-commonsense","title":"Knowledgeable Storyteller: A Commonsense-Driven Generative Model for Visual Storytelling","date":"2019-05-04","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/visual-discourse-parsing","slug":"visual-discourse-parsing","title":"Discourse Parsing in Videos: A Multi-modal Appraoch","date":"2019-03-06","arxiv_id":"1903.02252","repositories_listed":1,"syntology":null},{"url":"/paper/glac-net-glocal-attention-cascading-networks","slug":"glac-net-glocal-attention-cascading-networks","title":"GLAC Net: GLocal Attention Cascading Networks for Multi-image Cued Story Generation","date":"2018-05-28","arxiv_id":"1805.10973","repositories_listed":1,"syntology":null},{"url":"/paper/visual-storytelling","slug":"visual-storytelling","title":"Visual Storytelling","date":"2016-04-13","arxiv_id":"1604.03968","repositories_listed":1,"syntology":null},{"url":null,"slug":"shape2animal-creative-animal-generation-from","title":"Shape2Animal: Creative Animal Generation from Natural Silhouettes","date":"2025-06-25","arxiv_id":"2506.20616","repositories_listed":0,"syntology":null},{"url":null,"slug":"jarvisart-liberating-human-artistic","title":"JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent","date":"2025-06-21","arxiv_id":"2506.17612","repositories_listed":0,"syntology":null},{"url":null,"slug":"camera-trajectory-generation-a-comprehensive","title":"Camera Trajectory Generation: A Comprehensive Survey of Methods, Metrics, and Future Directions","date":"2025-06-01","arxiv_id":"2506.00974","repositories_listed":0,"syntology":null},{"url":null,"slug":"lorashop-training-free-multi-concept-image","title":"LoRAShop: Training-Free Multi-Concept Image Generation and Editing with Rectified Flow Transformers","date":"2025-05-29","arxiv_id":"2505.23758","repositories_listed":0,"syntology":null},{"url":null,"slug":"action2dialogue-generating-character-centric","title":"Action2Dialogue: Generating Character-Centric Narratives from Scene-Level Prompts","date":"2025-05-22","arxiv_id":"2505.16819","repositories_listed":0,"syntology":null},{"url":null,"slug":"vist-gpt-ushering-in-the-era-of-visual","title":"VIST-GPT: Ushering in the Era of Visual Storytelling with LLMs?","date":"2025-04-27","arxiv_id":"2504.19267","repositories_listed":0,"syntology":null},{"url":null,"slug":"gendop-auto-regressive-camera-trajectory","title":"GenDoP: Auto-regressive Camera Trajectory Generation as a Director of Photography","date":"2025-04-09","arxiv_id":"2504.07083","repositories_listed":0,"syntology":null},{"url":null,"slug":"storybooth-training-free-multi-subject","title":"Storybooth: Training-free Multi-Subject Consistency for Improved Visual Storytelling","date":"2025-04-08","arxiv_id":"2504.05800","repositories_listed":0,"syntology":null},{"url":null,"slug":"dante-ad-dual-vision-attention-network-for","title":"DANTE-AD: Dual-Vision Attention Network for Long-Term Audio Description","date":"2025-03-31","arxiv_id":"2503.24096","repositories_listed":0,"syntology":null},{"url":null,"slug":"vinabench-benchmark-for-faithful-and","title":"VinaBench: Benchmark for Faithful and Consistent Visual Narratives","date":"2025-03-26","arxiv_id":"2503.20871","repositories_listed":0,"syntology":null},{"url":null,"slug":"mirage-multimodal-immersive-reasoning-and","title":"MIRAGE: Multimodal Immersive Reasoning and Guided Exploration for Red-Team Jailbreak Attacks","date":"2025-03-24","arxiv_id":"2503.19134","repositories_listed":0,"syntology":null},{"url":null,"slug":"toyteller-ai-powered-visual-storytelling","title":"Toyteller: AI-powered Visual Storytelling Through Toy-Playing with Character Symbols","date":"2025-01-23","arxiv_id":"2501.13284","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-visual-communication-in-the-era-of","title":"Generative Visual Communication in the Era of Vision-Language Models","date":"2024-11-27","arxiv_id":"2411.18727","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-survey-and-guide-to","title":"A Comprehensive Survey and Guide to Multimodal Large Language Models in Vision-Language Tasks","date":"2024-11-09","arxiv_id":"2411.06284","repositories_listed":0,"syntology":null},{"url":null,"slug":"kahani-culturally-nuanced-visual-storytelling","title":"KAHANI: Culturally-Nuanced Visual Storytelling Pipeline for Non-Western Cultures","date":"2024-10-25","arxiv_id":"2410.19419","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-visual-stories-with-grounded-and","title":"Generating Visual Stories with Grounded and Coreferent Characters","date":"2024-09-20","arxiv_id":"2409.13555","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-alignment-for-multimodal-large","title":"Semantic Alignment for Multimodal Large Language Models","date":"2024-08-23","arxiv_id":"2408.12867","repositories_listed":0,"syntology":null},{"url":null,"slug":"story3d-agent-exploring-3d-storytelling","title":"Story3D-Agent: Exploring 3D Storytelling Visualization with Large Language Models","date":"2024-08-21","arxiv_id":"2408.11801","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-aware-visual-storytelling-with-visual","title":"Context-aware Visual Storytelling with Visual Prefix Tuning and Contrastive Learning","date":"2024-08-12","arxiv_id":"2408.06259","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-visual-storytelling-with-multimodal","title":"Improving Visual Storytelling with Multimodal Large Language Models","date":"2024-07-02","arxiv_id":"2407.02586","repositories_listed":0,"syntology":null},{"url":null,"slug":"tarn-vist-topic-aware-reinforcement-network","title":"TARN-VIST: Topic Aware Reinforcement Network for Visual Storytelling","date":"2024-03-18","arxiv_id":"2403.11550","repositories_listed":0,"syntology":null},{"url":null,"slug":"aesopagent-agent-driven-evolutionary-system","title":"AesopAgent: Agent-driven Evolutionary System on Story-to-Video Production","date":"2024-03-12","arxiv_id":"2403.07952","repositories_listed":0,"syntology":null},{"url":null,"slug":"metamorpheus-interactive-affective-and","title":"Metamorpheus: Interactive, Affective, and Creative Dream Narration Through Metaphorical Visual Storytelling","date":"2024-03-01","arxiv_id":"2403.00632","repositories_listed":0,"syntology":null},{"url":null,"slug":"sco-vist-social-interaction-commonsense","title":"SCO-VIST: Social Interaction Commonsense Knowledge-based Visual Storytelling","date":"2024-02-01","arxiv_id":"2402.00319","repositories_listed":0,"syntology":null},{"url":null,"slug":"magicscroll-nontypical-aspect-ratio-image","title":"MagicScroll: Nontypical Aspect-Ratio Image Generation for Visual Storytelling via Multi-Layered Semantic-Aware Denoising","date":"2023-12-18","arxiv_id":"2312.10899","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffuvst-narrating-fictional-scenes-with","title":"DiffuVST: Narrating Fictional Scenes with Global-History-Guided Denoising Models","date":"2023-12-12","arxiv_id":"2312.07066","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-storytelling-with-question-answer","title":"Visual Storytelling with Question-Answer Plans","date":"2023-10-08","arxiv_id":"2310.05295","repositories_listed":0,"syntology":null},{"url":null,"slug":"comics-for-everyone-generating-accessible","title":"Comics for Everyone: Generating Accessible Text Descriptions for Comic Strips","date":"2023-10-01","arxiv_id":"2310.00698","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-only-training-for-visual-storytelling","title":"Text-Only Training for Visual Storytelling","date":"2023-08-17","arxiv_id":"2308.08881","repositories_listed":0,"syntology":null},{"url":"/paper/aog-lstm-an-adaptive-attention-neural-network","slug":"aog-lstm-an-adaptive-attention-neural-network","title":"AOG-LSTM: An adaptive attention neural network for visual storytelling","date":"2023-06-26","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-chain-of-thought-bridging-logical-gaps","title":"Visual Chain of Thought: Bridging Logical Gaps with Multimodal Infillings","date":"2023-05-03","arxiv_id":"2305.02317","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-cap-anticipation-captioning-with","title":"A-CAP: Anticipation Captioning with Commonsense Knowledge","date":"2023-04-13","arxiv_id":"2304.06602","repositories_listed":0,"syntology":null},{"url":"/paper/visual-writing-prompts-character-grounded","slug":"visual-writing-prompts-character-grounded","title":"Visual Writing Prompts: Character-Grounded Story Generation with Curated Image Sequences","date":"2023-01-20","arxiv_id":"2301.08571","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-knowledge-enhanced-multimodal","title":"A survey on knowledge-enhanced multimodal learning","date":"2022-11-19","arxiv_id":"2211.12328","repositories_listed":0,"syntology":null},{"url":null,"slug":"dimbert-learning-vision-language-grounded","title":"DiMBERT: Learning Vision-Language Grounded Representations with Disentangled Multimodal-Attention","date":"2022-10-28","arxiv_id":"2210.16431","repositories_listed":0,"syntology":null},{"url":null,"slug":"bloom-library-multimodal-datasets-in-300","title":"Bloom Library: Multimodal Datasets in 300+ Languages for a Variety of Downstream Tasks","date":"2022-10-26","arxiv_id":"2210.14712","repositories_listed":0,"syntology":null},{"url":"/paper/vision-transformer-based-model-for-describing","slug":"vision-transformer-based-model-for-describing","title":"Vision Transformer Based Model for Describing a Set of Images as a Story","date":"2022-10-06","arxiv_id":"2210.02762","repositories_listed":0,"syntology":null},{"url":"/paper/coherent-visual-storytelling-via-parallel-top","slug":"coherent-visual-storytelling-via-parallel-top","title":"Coherent Visual Storytelling via Parallel Top-Down Visual and Topic Attention","date":"2022-08-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/sentistory-a-multi-layered-sentiment-aware","slug":"sentistory-a-multi-layered-sentiment-aware","title":"SentiStory: A Multi-Layered Sentiment-Aware Generative Model for Visual Storytelling","date":"2022-06-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-enriched-attention-network-with","title":"Knowledge-enriched Attention Network with Group-wise Semantic for Visual Storytelling","date":"2022-03-10","arxiv_id":"2203.05346","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-system-for-image-understanding-using","title":"A System for Image Understanding using Sensemaking and Narrative","date":"2022-01-21","arxiv_id":"2201.09880","repositories_listed":0,"syntology":null},{"url":null,"slug":"discourse-analysis-for-evaluating-coherence","title":"Discourse Analysis for Evaluating Coherence in Video Paragraph Captions","date":"2022-01-17","arxiv_id":"2201.06207","repositories_listed":0,"syntology":null},{"url":"/paper/visual-storytelling-with-hierarchical-bert","slug":"visual-storytelling-with-hierarchical-bert","title":"Visual Storytelling with Hierarchical BERT Semantic Guidance","date":"2022-01-10","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"rovist-learning-robust-metrics-for-visual","title":"RoViST: Learning Robust Metrics for Visual Storytelling","date":"2021-12-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-rank-visual-stories-from-human","title":"Learning to Rank Visual Stories From Human Ranking Data","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-coherent-visual-storytelling-with-1","title":"Towards Coherent Visual Storytelling with Ordered Image Attention","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-similarities-and-dual-approach-for","title":"Graph Similarities and Dual Approach for Sequential Text-to-Image Retrieval","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-coherent-visual-storytelling-with","title":"Ordered Attention for Coherent Visual Storytelling","date":"2021-08-04","arxiv_id":"2108.02180","repositories_listed":0,"syntology":null},{"url":null,"slug":"stretch-vst-getting-flexible-with-visual","title":"Stretch-VST: Getting Flexible With Visual Stories","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/two-heads-are-better-than-one-hypergraph","slug":"two-heads-are-better-than-one-hypergraph","title":"Two Heads are Better Than One: Hypergraph-Enhanced Graph Reasoning for Visual Event Ratiocination","date":"2021-07-18","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/transitional-adaptation-of-pretrained-models","slug":"transitional-adaptation-of-pretrained-models","title":"Transitional Adaptation of Pretrained Models for Visual Storytelling","date":"2021-06-19","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/imagine-reason-and-write-visual-storytelling","slug":"imagine-reason-and-write-visual-storytelling","title":"Imagine, Reason and Write: Visual Storytelling with Graph Knowledge and Relational Reasoning","date":"2021-05-18","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/commonsense-knowledge-aware-concept-selection","slug":"commonsense-knowledge-aware-concept-selection","title":"Commonsense Knowledge Aware Concept Selection For Diverse and Informative Visual Storytelling","date":"2021-02-05","arxiv_id":"2102.02963","repositories_listed":0,"syntology":null},{"url":"/paper/bert-hlstms-bert-and-hierarchical-lstms-for","slug":"bert-hlstms-bert-and-hierarchical-lstms-for","title":"BERT-hLSTMs: BERT and Hierarchical LSTMs for Visual Storytelling","date":"2020-12-03","arxiv_id":"2012.02128","repositories_listed":0,"syntology":null},{"url":"/paper/diverse-and-relevant-visual-storytelling-with","slug":"diverse-and-relevant-visual-storytelling-with","title":"Diverse and Relevant Visual Storytelling with Scene Graph Embeddings","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reading-between-the-lines-exploring-infilling","title":"Reading Between the Lines: Exploring Infilling in Visual Narratives","date":"2020-10-26","arxiv_id":"2010.13944","repositories_listed":0,"syntology":null},{"url":"/paper/hierarchical-memory-decoder-for-visual","slug":"hierarchical-memory-decoder-for-visual","title":"Hierarchical memory decoder for visual narrating","date":"2020-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"topic-adaptation-and-prototype-encoding-for","title":"Topic Adaptation and Prototype Encoding for Few-Shot Visual Storytelling","date":"2020-08-11","arxiv_id":"2008.04504","repositories_listed":0,"syntology":null},{"url":"/paper/storytelling-from-an-image-stream-using-scene","slug":"storytelling-from-an-image-stream-using-scene","title":"Storytelling from an Image Stream Using Scene Graphs","date":"2020-04-03","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/hide-and-tell-learning-to-bridge-photo","slug":"hide-and-tell-learning-to-bridge-photo","title":"Hide-and-Tell: Learning to Bridge Photo Streams for Visual Storytelling","date":"2020-02-03","arxiv_id":"2002.00774","repositories_listed":0,"syntology":null},{"url":"/paper/visual-storytelling-via-predicting-anchor","slug":"visual-storytelling-via-predicting-anchor","title":"Visual Storytelling via Predicting Anchor Word Embeddings in the Stories","date":"2020-01-13","arxiv_id":"2001.04541","repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-textual-evidence-in-visual","title":"Incorporating Textual Evidence in Visual Storytelling","date":"2019-11-21","arxiv_id":"1911.09334","repositories_listed":0,"syntology":null},{"url":"/paper/keep-it-consistent-topic-aware-storytelling","slug":"keep-it-consistent-topic-aware-storytelling","title":"Keep it Consistent: Topic-Aware Storytelling from an Image Stream via Iterative Multi-agent Communication","date":"2019-11-11","arxiv_id":"1911.04192","repositories_listed":0,"syntology":null}],"syntology_records":4,"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":4,"papers_where_code_ran_first_page":"/task/visual-storytelling/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":"archive","page":2,"of":2,"url":"/task/visual-storytelling/papers/2","json":"/task/visual-storytelling/papers/2.json","rows":15},{"order":"ran","page":1,"of":1,"url":"/task/visual-storytelling/papers/ran/1","json":"/task/visual-storytelling/papers/ran/1.json","rows":4}],"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":"b28a35c32e3ae5bb3044d71fa8b71e435f45ce496f160fd1b31c40534d04b271","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}