{"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/caption-generation","name":"Caption Generation","slug":"caption-generation","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":310,"papers_with_code":119,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":2,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/l-m-24","name":"L+M-24","full_name":"","num_papers_in_archive":7},{"url":"/dataset/concadia","name":"Concadia","full_name":"","num_papers_in_archive":4}],"subtasks":[],"parent_tasks":[],"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":4,"rows_per_page":100,"shown":100,"of":310,"of_with_code":119,"tagged_in_all":310,"counts":{"archive_papers_tagged":310,"with_a_code_link":119,"where_syntology_ran_a_sample":33,"not_listed_spam_title":0,"listed":310,"listed_where_code_ran":33,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":28,"every_run_a_failure_of_syntologys_instrument":5,"listed_with_a_run_with_no_instrument_failure":28,"listed_every_run_a_failure_of_syntologys_instrument":5,"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/show-attend-and-tell-neural-image-caption","slug":"show-attend-and-tell-neural-image-caption","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","date":"2015-02-10","arxiv_id":"1502.03044","repositories_listed":92,"syntology":{"n":84,"n_ran":58,"n_constructed":0,"n_ran_checked":45,"n_instrument":13,"n_unverified":26,"n_honours":3,"n_violates":0,"n_no_contract":42,"n_pointer_only":14,"phrase":"58 ran (of which 0 constructed an object rather than computing a result; 45 with no instrument failure: 3 honoured, 0 violated, 42 with no contract checked; 13 where Syntology's instrument failed) · 26 unverified","sample_list":"/paper/show-attend-and-tell-neural-image-caption#ran","syntology_url":"https://syntology.ai/paper/1502.03044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1502.03044"}},"official":null}},{"url":"/paper/grad-cam-improved-visual-explanations-for","slug":"grad-cam-improved-visual-explanations-for","title":"Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks","date":"2017-10-30","arxiv_id":"1710.11063","repositories_listed":24,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"6 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/grad-cam-improved-visual-explanations-for#ran","syntology_url":"https://syntology.ai/paper/1710.11063","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.11063"}},"official":{"repos":["adityac94/Grad_CAM_plus_plus"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/recurrent-neural-network-regularization","slug":"recurrent-neural-network-regularization","title":"Recurrent Neural Network Regularization","date":"2014-09-08","arxiv_id":"1409.2329","repositories_listed":21,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"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) · 4 unverified","sample_list":"/paper/recurrent-neural-network-regularization#ran","syntology_url":"https://syntology.ai/paper/1409.2329","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1409.2329"}},"official":{"repos":["wojzaremba/lstm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/microsoft-coco-captions-data-collection-and","slug":"microsoft-coco-captions-data-collection-and","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","date":"2015-04-01","arxiv_id":"1504.00325","repositories_listed":18,"syntology":null},{"url":"/paper/where-to-put-the-image-in-an-image-caption","slug":"where-to-put-the-image-in-an-image-caption","title":"Where to put the Image in an Image Caption Generator","date":"2017-03-27","arxiv_id":"1703.09137","repositories_listed":12,"syntology":null},{"url":"/paper/sequence-to-sequence-video-to-text","slug":"sequence-to-sequence-video-to-text","title":"Sequence to Sequence -- Video to Text","date":"2015-05-03","arxiv_id":"1505.00487","repositories_listed":4,"syntology":null},{"url":"/paper/scalable-bayesian-optimization-using-deep","slug":"scalable-bayesian-optimization-using-deep","title":"Scalable Bayesian Optimization Using Deep Neural Networks","date":"2015-02-19","arxiv_id":"1502.05700","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scalable-bayesian-optimization-using-deep#ran","syntology_url":"https://syntology.ai/paper/1502.05700","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1502.05700"}},"official":null}},{"url":"/paper/music-understanding-llama-advancing-text-to","slug":"music-understanding-llama-advancing-text-to","title":"Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning","date":"2023-08-22","arxiv_id":"2308.11276","repositories_listed":3,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/music-understanding-llama-advancing-text-to#ran","syntology_url":"https://syntology.ai/paper/2308.11276","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11276"}},"official":{"repos":["crypto-code/mu-llama"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/conceptual-12m-pushing-web-scale-image-text","slug":"conceptual-12m-pushing-web-scale-image-text","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","date":"2021-02-17","arxiv_id":"2102.08981","repositories_listed":3,"syntology":null},{"url":"/paper/deep-reinforcement-learning-for-sequence-to","slug":"deep-reinforcement-learning-for-sequence-to","title":"Deep Reinforcement Learning For Sequence to Sequence Models","date":"2018-05-24","arxiv_id":"1805.09461","repositories_listed":3,"syntology":{"n":17,"n_ran":16,"n_constructed":0,"n_ran_checked":15,"n_instrument":1,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":13,"n_pointer_only":2,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 2 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/deep-reinforcement-learning-for-sequence-to#ran","syntology_url":"https://syntology.ai/paper/1805.09461","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.09461"}},"official":{"repos":["yaserkl/RLSeq2Seq"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/an-actor-critic-algorithm-for-sequence","slug":"an-actor-critic-algorithm-for-sequence","title":"An Actor-Critic Algorithm for Sequence Prediction","date":"2016-07-24","arxiv_id":"1607.07086","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/an-actor-critic-algorithm-for-sequence#ran","syntology_url":"https://syntology.ai/paper/1607.07086","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1607.07086"}},"official":{"repos":["rizar/actor-critic-public"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/vipe-visualise-pretty-much-everything","slug":"vipe-visualise-pretty-much-everything","title":"ViPE: Visualise Pretty-much Everything","date":"2023-10-16","arxiv_id":"2310.10543","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vipe-visualise-pretty-much-everything#ran","syntology_url":"https://syntology.ai/paper/2310.10543","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.10543"}},"official":{"repos":["hazel1994/vipe"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/betrayed-by-captions-joint-caption-grounding","slug":"betrayed-by-captions-joint-caption-grounding","title":"Betrayed by Captions: Joint Caption Grounding and Generation for Open Vocabulary Instance Segmentation","date":"2023-01-02","arxiv_id":"2301.00805","repositories_listed":2,"syntology":null},{"url":"/paper/cosmic-a-coherence-aware-generation-metric","slug":"cosmic-a-coherence-aware-generation-metric","title":"COSMic: A Coherence-Aware Generation Metric for Image Descriptions","date":"2021-09-11","arxiv_id":"2109.05281","repositories_listed":2,"syntology":null},{"url":"/paper/end-to-end-dense-video-captioning-with","slug":"end-to-end-dense-video-captioning-with","title":"End-to-End Dense Video Captioning with Parallel Decoding","date":"2021-08-17","arxiv_id":"2108.07781","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/end-to-end-dense-video-captioning-with#ran","syntology_url":"https://syntology.ai/paper/2108.07781","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.07781"}},"official":{"repos":["ttengwang/pdvc"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/deterministic-non-autoregressive-neural","slug":"deterministic-non-autoregressive-neural","title":"Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement","date":"2018-02-19","arxiv_id":"1802.06901","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/deterministic-non-autoregressive-neural#ran","syntology_url":"https://syntology.ai/paper/1802.06901","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.06901"}},"official":{"repos":["nyu-dl/dl4mt-nonauto"],"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":["listed","official"]}}},{"url":"/paper/exploring-models-and-data-for-remote-sensing","slug":"exploring-models-and-data-for-remote-sensing","title":"Exploring Models and Data for Remote Sensing Image Caption Generation","date":"2017-12-21","arxiv_id":"1712.07835","repositories_listed":2,"syntology":null},{"url":"/paper/attacking-visual-language-grounding-with","slug":"attacking-visual-language-grounding-with","title":"Attacking Visual Language Grounding with Adversarial Examples: A Case Study on Neural Image Captioning","date":"2017-12-06","arxiv_id":"1712.02051","repositories_listed":2,"syntology":null},{"url":"/paper/tensor-product-generation-networks-for-deep","slug":"tensor-product-generation-networks-for-deep","title":"Tensor Product Generation Networks for Deep NLP Modeling","date":"2017-09-26","arxiv_id":"1709.09118","repositories_listed":2,"syntology":null},{"url":"/paper/cnn-fixations-an-unraveling-approach-to","slug":"cnn-fixations-an-unraveling-approach-to","title":"CNN Fixations: An unraveling approach to visualize the discriminative image regions","date":"2017-08-22","arxiv_id":"1708.06670","repositories_listed":2,"syntology":null},{"url":"/paper/twin-networks-matching-the-future-for","slug":"twin-networks-matching-the-future-for","title":"Twin Networks: Matching the Future for Sequence Generation","date":"2017-08-22","arxiv_id":"1708.06742","repositories_listed":2,"syntology":null},{"url":"/paper/an-empirical-study-of-language-cnn-for-image","slug":"an-empirical-study-of-language-cnn-for-image","title":"An Empirical Study of Language CNN for Image Captioning","date":"2016-12-21","arxiv_id":"1612.07086","repositories_listed":2,"syntology":null},{"url":"/paper/dsd-dense-sparse-dense-training-for-deep","slug":"dsd-dense-sparse-dense-training-for-deep","title":"DSD: Dense-Sparse-Dense Training for Deep Neural Networks","date":"2016-07-15","arxiv_id":"1607.04381","repositories_listed":2,"syntology":null},{"url":"/paper/video-captioning-with-recurrent-networks","slug":"video-captioning-with-recurrent-networks","title":"Video captioning with recurrent networks based on frame- and video-level features and visual content classification","date":"2015-12-09","arxiv_id":"1512.02949","repositories_listed":2,"syntology":null},{"url":"/paper/denseworld-1m-towards-detailed-dense-grounded","slug":"denseworld-1m-towards-detailed-dense-grounded","title":"DenseWorld-1M: Towards Detailed Dense Grounded Caption in the Real World","date":"2025-06-30","arxiv_id":"2506.24102","repositories_listed":1,"syntology":null},{"url":"/paper/sonicverse-multi-task-learning-for-music","slug":"sonicverse-multi-task-learning-for-music","title":"SonicVerse: Multi-Task Learning for Music Feature-Informed Captioning","date":"2025-06-18","arxiv_id":"2506.15154","repositories_listed":1,"syntology":null},{"url":"/paper/fusionaudio-1-2m-towards-fine-grained-audio","slug":"fusionaudio-1-2m-towards-fine-grained-audio","title":"FusionAudio-1.2M: Towards Fine-grained Audio Captioning with Multimodal Contextual Fusion","date":"2025-06-01","arxiv_id":"2506.01111","repositories_listed":1,"syntology":null},{"url":"/paper/vcapsbench-a-large-scale-fine-grained","slug":"vcapsbench-a-large-scale-fine-grained","title":"VCapsBench: A Large-scale Fine-grained Benchmark for Video Caption Quality Evaluation","date":"2025-05-29","arxiv_id":"2505.23484","repositories_listed":1,"syntology":null},{"url":"/paper/lovr-a-benchmark-for-long-video-retrieval-in","slug":"lovr-a-benchmark-for-long-video-retrieval-in","title":"LoVR: A Benchmark for Long Video Retrieval in Multimodal Contexts","date":"2025-05-20","arxiv_id":"2505.13928","repositories_listed":1,"syntology":null},{"url":"/paper/videomultiagents-a-multi-agent-framework-for","slug":"videomultiagents-a-multi-agent-framework-for","title":"VideoMultiAgents: A Multi-Agent Framework for Video Question Answering","date":"2025-04-25","arxiv_id":"2504.20091","repositories_listed":1,"syntology":null},{"url":"/paper/3d-coca-contrastive-learners-are-3d","slug":"3d-coca-contrastive-learners-are-3d","title":"3D CoCa: Contrastive Learners are 3D Captioners","date":"2025-04-13","arxiv_id":"2504.09518","repositories_listed":1,"syntology":null},{"url":"/paper/towards-self-improving-systematic-cognition","slug":"towards-self-improving-systematic-cognition","title":"Will Pre-Training Ever End? A First Step Toward Next-Generation Foundation MLLMs via Self-Improving Systematic Cognition","date":"2025-03-16","arxiv_id":"2503.12303","repositories_listed":1,"syntology":null},{"url":"/paper/large-scale-pre-training-for-grounded-video","slug":"large-scale-pre-training-for-grounded-video","title":"Large-scale Pre-training for Grounded Video Caption Generation","date":"2025-03-13","arxiv_id":"2503.10781","repositories_listed":1,"syntology":null},{"url":"/paper/expertized-caption-auto-enhancement-for-video","slug":"expertized-caption-auto-enhancement-for-video","title":"Expertized Caption Auto-Enhancement for Video-Text Retrieval","date":"2025-02-05","arxiv_id":"2502.02885","repositories_listed":1,"syntology":null},{"url":"/paper/llmdet-learning-strong-open-vocabulary-object","slug":"llmdet-learning-strong-open-vocabulary-object","title":"LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models","date":"2025-01-31","arxiv_id":"2501.18954","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":11,"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) · 1 unverified","sample_list":"/paper/llmdet-learning-strong-open-vocabulary-object#ran","syntology_url":"https://syntology.ai/paper/2501.18954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.18954"}},"official":{"repos":["isee-laboratory/llmdet"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-llm-collaborative-caption-generation-in","slug":"multi-llm-collaborative-caption-generation-in","title":"Multi-LLM Collaborative Caption Generation in Scientific Documents","date":"2025-01-05","arxiv_id":"2501.02552","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-preference-data-synthetic","slug":"multimodal-preference-data-synthetic","title":"Multimodal Preference Data Synthetic Alignment with Reward Model","date":"2024-12-23","arxiv_id":"2412.17417","repositories_listed":1,"syntology":null},{"url":"/paper/from-simple-to-professional-a-combinatorial","slug":"from-simple-to-professional-a-combinatorial","title":"From Simple to Professional: A Combinatorial Controllable Image Captioning Agent","date":"2024-12-15","arxiv_id":"2412.11025","repositories_listed":1,"syntology":null},{"url":"/paper/audiosetcaps-an-enriched-audio-caption","slug":"audiosetcaps-an-enriched-audio-caption","title":"AudioSetCaps: An Enriched Audio-Caption Dataset using Automated Generation Pipeline with Large Audio and Language Models","date":"2024-11-28","arxiv_id":"2411.18953","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/audiosetcaps-an-enriched-audio-caption#ran","syntology_url":"https://syntology.ai/paper/2411.18953","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.18953"}},"official":{"repos":["jishengbai/audiosetcaps"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ppllava-varied-video-sequence-understanding","slug":"ppllava-varied-video-sequence-understanding","title":"PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance","date":"2024-11-04","arxiv_id":"2411.02327","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":2,"n_no_contract":2,"n_pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 2 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/ppllava-varied-video-sequence-understanding#ran","syntology_url":"https://syntology.ai/paper/2411.02327","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02327"}},"official":{"repos":["farewellthree/ppllava"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/croc-pretraining-large-multimodal-models-with","slug":"croc-pretraining-large-multimodal-models-with","title":"Croc: Pretraining Large Multimodal Models with Cross-Modal Comprehension","date":"2024-10-18","arxiv_id":"2410.14332","repositories_listed":1,"syntology":null},{"url":"/paper/motionbank-a-large-scale-video-motion","slug":"motionbank-a-large-scale-video-motion","title":"MotionBank: A Large-scale Video Motion Benchmark with Disentangled Rule-based Annotations","date":"2024-10-17","arxiv_id":"2410.13790","repositories_listed":1,"syntology":null},{"url":"/paper/slam-aac-enhancing-audio-captioning-with","slug":"slam-aac-enhancing-audio-captioning-with","title":"SLAM-AAC: Enhancing Audio Captioning with Paraphrasing Augmentation and CLAP-Refine through LLMs","date":"2024-10-12","arxiv_id":"2410.09503","repositories_listed":1,"syntology":null},{"url":"/paper/positive-augmented-contrastive-learning-for","slug":"positive-augmented-contrastive-learning-for","title":"Positive-Augmented Contrastive Learning for Vision-and-Language Evaluation and Training","date":"2024-10-09","arxiv_id":"2410.07336","repositories_listed":1,"syntology":null},{"url":"/paper/synthio-augmenting-small-scale-audio","slug":"synthio-augmenting-small-scale-audio","title":"Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic Data","date":"2024-10-02","arxiv_id":"2410.02056","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/synthio-augmenting-small-scale-audio#ran","syntology_url":"https://syntology.ai/paper/2410.02056","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02056"}},"official":{"repos":["sreyan88/synthio"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mol2lang-vlm-vision-and-text-guided","slug":"mol2lang-vlm-vision-and-text-guided","title":"Mol2Lang-VLM: Vision- and Text-Guided Generative Pre-trained Language Models for Advancing Molecule Captioning through Multimodal Fusion","date":"2024-08-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/2408-03006","slug":"2408-03006","title":"Dual-path Collaborative Generation Network for Emotional Video Captioning","date":"2024-08-06","arxiv_id":"2408.03006","repositories_listed":1,"syntology":null},{"url":"/paper/synthvlm-high-efficiency-and-high-quality","slug":"synthvlm-high-efficiency-and-high-quality","title":"SynthVLM: High-Efficiency and High-Quality Synthetic Data for Vision Language Models","date":"2024-07-30","arxiv_id":"2407.20756","repositories_listed":1,"syntology":null},{"url":"/paper/continual-panoptic-perception-towards-multi","slug":"continual-panoptic-perception-towards-multi","title":"Continual Panoptic Perception: Towards Multi-modal Incremental Interpretation of Remote Sensing Images","date":"2024-07-19","arxiv_id":"2407.14242","repositories_listed":1,"syntology":null},{"url":"/paper/distractors-immune-representation-learning","slug":"distractors-immune-representation-learning","title":"Distractors-Immune Representation Learning with Cross-modal Contrastive Regularization for Change Captioning","date":"2024-07-16","arxiv_id":"2407.11683","repositories_listed":1,"syntology":null},{"url":"/paper/hcqa-ego4d-egoschema-challenge-2024","slug":"hcqa-ego4d-egoschema-challenge-2024","title":"HCQA @ Ego4D EgoSchema Challenge 2024","date":"2024-06-22","arxiv_id":"2406.15771","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"5 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/hcqa-ego4d-egoschema-challenge-2024#ran","syntology_url":"https://syntology.ai/paper/2406.15771","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.15771"}},"official":{"repos":["hyu-zhang/hcqa"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-cross-prompt-transferability-in","slug":"enhancing-cross-prompt-transferability-in","title":"Enhancing Cross-Prompt Transferability in Vision-Language Models through Contextual Injection of Target Tokens","date":"2024-06-19","arxiv_id":"2406.13294","repositories_listed":1,"syntology":null},{"url":"/paper/humor-in-ai-massive-scale-crowd-sourced","slug":"humor-in-ai-massive-scale-crowd-sourced","title":"Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning","date":"2024-06-15","arxiv_id":"2406.10522","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/humor-in-ai-massive-scale-crowd-sourced#ran","syntology_url":"https://syntology.ai/paper/2406.10522","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10522"}},"official":{"repos":["yguooo/cartoon-caption-generation"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/soccernet-echoes-a-soccer-game-audio","slug":"soccernet-echoes-a-soccer-game-audio","title":"SoccerNet-Echoes: A Soccer Game Audio Commentary Dataset","date":"2024-05-12","arxiv_id":"2405.07354","repositories_listed":1,"syntology":null},{"url":"/paper/bcamirs-at-semeval-2024-task-4-beyond-words-a","slug":"bcamirs-at-semeval-2024-task-4-beyond-words-a","title":"BCAmirs at SemEval-2024 Task 4: Beyond Words: A Multimodal and Multilingual Exploration of Persuasion in Memes","date":"2024-04-03","arxiv_id":"2404.03022","repositories_listed":1,"syntology":null},{"url":"/paper/meacap-memory-augmented-zero-shot-image","slug":"meacap-memory-augmented-zero-shot-image","title":"MeaCap: Memory-Augmented Zero-shot Image Captioning","date":"2024-03-06","arxiv_id":"2403.03715","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":1,"n_ran_checked":4,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":10,"phrase":"6 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/meacap-memory-augmented-zero-shot-image#ran","syntology_url":"https://syntology.ai/paper/2403.03715","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03715"}},"official":{"repos":["joeyz0z/meacap"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/automatic-report-generation-for-1","slug":"automatic-report-generation-for-1","title":"Automatic Report Generation for Histopathology images using pre-trained Vision Transformers and BERT","date":"2023-12-03","arxiv_id":"2312.01435","repositories_listed":1,"syntology":null},{"url":"/paper/segment-and-caption-anything","slug":"segment-and-caption-anything","title":"Segment and Caption Anything","date":"2023-12-01","arxiv_id":"2312.00869","repositories_listed":1,"syntology":null},{"url":"/paper/neusyre-neuro-symbolic-visual-understanding","slug":"neusyre-neuro-symbolic-visual-understanding","title":"NeuSyRE: Neuro-Symbolic Visual Understanding and Reasoning Framework based on Scene Graph Enrichment","date":"2023-11-05","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/vlis-unimodal-language-models-guide","slug":"vlis-unimodal-language-models-guide","title":"VLIS: Unimodal Language Models Guide Multimodal Language Generation","date":"2023-10-15","arxiv_id":"2310.09767","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-cross-view-representation-1","slug":"self-supervised-cross-view-representation-1","title":"Self-supervised Cross-view Representation Reconstruction for Change Captioning","date":"2023-09-28","arxiv_id":"2309.16283","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 2 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; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/self-supervised-cross-view-representation-1#ran","syntology_url":"https://syntology.ai/paper/2309.16283","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.16283"}},"official":{"repos":["tuyunbin/scorer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/recap-retrieval-augmented-audio-captioning","slug":"recap-retrieval-augmented-audio-captioning","title":"RECAP: Retrieval-Augmented Audio Captioning","date":"2023-09-18","arxiv_id":"2309.09836","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/recap-retrieval-augmented-audio-captioning#ran","syntology_url":"https://syntology.ai/paper/2309.09836","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.09836"}},"official":{"repos":["sreyan88/recap"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/musilingo-bridging-music-and-text-with-pre","slug":"musilingo-bridging-music-and-text-with-pre","title":"MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response","date":"2023-09-15","arxiv_id":"2309.08730","repositories_listed":1,"syntology":null},{"url":"/paper/vote2cap-detr-decoupling-localization-and","slug":"vote2cap-detr-decoupling-localization-and","title":"Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning","date":"2023-09-06","arxiv_id":"2309.02999","repositories_listed":1,"syntology":null},{"url":"/paper/empowering-vision-language-models-to-follow","slug":"empowering-vision-language-models-to-follow","title":"Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructions","date":"2023-08-08","arxiv_id":"2308.04152","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":2,"n_instrument":8,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/empowering-vision-language-models-to-follow#ran","syntology_url":"https://syntology.ai/paper/2308.04152","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.04152"}},"official":{"repos":["dcdmllm/cheetah"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/transferable-decoding-with-visual-entities","slug":"transferable-decoding-with-visual-entities","title":"Transferable Decoding with Visual Entities for Zero-Shot Image Captioning","date":"2023-07-31","arxiv_id":"2307.16525","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":3,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/transferable-decoding-with-visual-entities#ran","syntology_url":"https://syntology.ai/paper/2307.16525","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.16525"}},"official":{"repos":["feielysia/viecap"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/figcaps-hf-a-figure-to-caption-generative","slug":"figcaps-hf-a-figure-to-caption-generative","title":"FigCaps-HF: A Figure-to-Caption Generative Framework and Benchmark with Human Feedback","date":"2023-07-20","arxiv_id":"2307.10867","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"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) · 2 unverified","sample_list":"/paper/figcaps-hf-a-figure-to-caption-generative#ran","syntology_url":"https://syntology.ai/paper/2307.10867","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.10867"}},"official":{"repos":["figcapshf/figcapshf"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/scicap-a-knowledge-augmented-dataset-to-study","slug":"scicap-a-knowledge-augmented-dataset-to-study","title":"SciCap+: A Knowledge Augmented Dataset to Study the Challenges of Scientific Figure Captioning","date":"2023-06-06","arxiv_id":"2306.03491","repositories_listed":1,"syntology":null},{"url":"/paper/transform-contrast-and-tell-coherent-entity","slug":"transform-contrast-and-tell-coherent-entity","title":"Transform, Contrast and Tell: Coherent Entity-Aware Multi-Image Captioning","date":"2023-02-04","arxiv_id":"2302.02124","repositories_listed":1,"syntology":null},{"url":"/paper/visual-commonsense-aware-representation","slug":"visual-commonsense-aware-representation","title":"Visual Commonsense-aware Representation Network for Video Captioning","date":"2022-11-17","arxiv_id":"2211.09469","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-metadata-extraction-from-dense-video","slug":"semantic-metadata-extraction-from-dense-video","title":"Event and Entity Extraction from Generated Video Captions","date":"2022-11-05","arxiv_id":"2211.02982","repositories_listed":1,"syntology":null},{"url":"/paper/efficientvlm-fast-and-accurate-vision","slug":"efficientvlm-fast-and-accurate-vision","title":"EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning","date":"2022-10-14","arxiv_id":"2210.07795","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":9,"phrase":"7 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; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/efficientvlm-fast-and-accurate-vision#ran","syntology_url":"https://syntology.ai/paper/2210.07795","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07795"}},"official":{"repos":["swaggy-tn/efficientvlm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/belief-revision-based-caption-re-ranker-with","slug":"belief-revision-based-caption-re-ranker-with","title":"Belief Revision based Caption Re-ranker with Visual Semantic Information","date":"2022-09-16","arxiv_id":"2209.08163","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-surgical-captioning-end-to-end","slug":"rethinking-surgical-captioning-end-to-end","title":"Rethinking Surgical Captioning: End-to-End Window-Based MLP Transformer Using Patches","date":"2022-06-30","arxiv_id":"2207.00113","repositories_listed":1,"syntology":null},{"url":"/paper/fine-grained-image-captioning-with-clip","slug":"fine-grained-image-captioning-with-clip","title":"Fine-grained Image Captioning with CLIP Reward","date":"2022-05-26","arxiv_id":"2205.13115","repositories_listed":1,"syntology":null},{"url":"/paper/gl-rg-global-local-representation-granularity","slug":"gl-rg-global-local-representation-granularity","title":"GL-RG: Global-Local Representation Granularity for Video Captioning","date":"2022-05-22","arxiv_id":"2205.10706","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/gl-rg-global-local-representation-granularity#ran","syntology_url":"https://syntology.ai/paper/2205.10706","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.10706"}},"official":{"repos":["ylqi/gl-rg"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/spatiality-guided-transformer-for-3d-dense","slug":"spatiality-guided-transformer-for-3d-dense","title":"Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds","date":"2022-04-22","arxiv_id":"2204.10688","repositories_listed":1,"syntology":null},{"url":"/paper/nicgslowdown-evaluating-the-efficiency","slug":"nicgslowdown-evaluating-the-efficiency","title":"NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Models","date":"2022-03-29","arxiv_id":"2203.15859","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"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 2 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; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/nicgslowdown-evaluating-the-efficiency#ran","syntology_url":"https://syntology.ai/paper/2203.15859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15859"}},"official":{"repos":["seekingdream/nicgslowdown"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/local-information-assisted-attention-free","slug":"local-information-assisted-attention-free","title":"Local Information Assisted Attention-free Decoder for Audio Captioning","date":"2022-01-10","arxiv_id":"2201.03217","repositories_listed":1,"syntology":null},{"url":"/paper/injecting-semantic-concepts-into-end-to-end","slug":"injecting-semantic-concepts-into-end-to-end","title":"Injecting Semantic Concepts into End-to-End Image Captioning","date":"2021-12-09","arxiv_id":"2112.05230","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/injecting-semantic-concepts-into-end-to-end#ran","syntology_url":"https://syntology.ai/paper/2112.05230","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.05230"}},"official":{"repos":["jacobswan1/ViTCAP"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/controllable-video-captioning-with-an","slug":"controllable-video-captioning-with-an","title":"Controllable Video Captioning with an Exemplar Sentence","date":"2021-12-02","arxiv_id":"2112.01073","repositories_listed":1,"syntology":null},{"url":"/paper/clip-meets-video-captioners-attribute-aware","slug":"clip-meets-video-captioners-attribute-aware","title":"CLIP Meets Video Captioning: Concept-Aware Representation Learning Does Matter","date":"2021-11-30","arxiv_id":"2111.15162","repositories_listed":1,"syntology":null},{"url":"/paper/swinbert-end-to-end-transformers-with-sparse","slug":"swinbert-end-to-end-transformers-with-sparse","title":"SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning","date":"2021-11-25","arxiv_id":"2111.13196","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"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, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/swinbert-end-to-end-transformers-with-sparse#ran","syntology_url":"https://syntology.ai/paper/2111.13196","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.13196"}},"official":{"repos":["microsoft/swinbert"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/automated-audio-captioning-by-fine-tuning","slug":"automated-audio-captioning-by-fine-tuning","title":"AUTOMATED AUDIO CAPTIONING BY FINE-TUNING BART WITH AUDIOSET TAGS","date":"2021-11-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/r-3net-relation-embedded-representation","slug":"r-3net-relation-embedded-representation","title":"Rˆ3Net:Relation-embedded Representation Reconstruction Network for Change Captioning","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/bangla-image-caption-generation-through-cnn","slug":"bangla-image-caption-generation-through-cnn","title":"Bangla Image Caption Generation through CNN-Transformer based Encoder-Decoder Network","date":"2021-10-24","arxiv_id":"2110.12442","repositories_listed":1,"syntology":null},{"url":"/paper/cortico-cerebellar-networks-as-decoupling","slug":"cortico-cerebellar-networks-as-decoupling","title":"Cortico-cerebellar networks as decoupling neural interfaces","date":"2021-10-21","arxiv_id":"2110.11501","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":4,"n_ran_checked":8,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":8,"phrase":"9 ran (of which 4 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/cortico-cerebellar-networks-as-decoupling#ran","syntology_url":"https://syntology.ai/paper/2110.11501","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.11501"}},"official":{"repos":["neuralml/ccdni"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":4,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/r-3-net-relation-embedded-representation","slug":"r-3-net-relation-embedded-representation","title":"R$^3$Net:Relation-embedded Representation Reconstruction Network for Change Captioning","date":"2021-10-20","arxiv_id":"2110.10328","repositories_listed":1,"syntology":null},{"url":"/paper/topic-scene-graph-generation-by-attention-1","slug":"topic-scene-graph-generation-by-attention-1","title":"Topic Scene Graph Generation by Attention Distillation from Caption","date":"2021-10-12","arxiv_id":"2110.05731","repositories_listed":1,"syntology":null},{"url":"/paper/journalistic-guidelines-aware-news-image","slug":"journalistic-guidelines-aware-news-image","title":"Journalistic Guidelines Aware News Image Captioning","date":"2021-09-07","arxiv_id":"2109.02865","repositories_listed":1,"syntology":null},{"url":"/paper/laviter-learning-aligned-visual-and-textual","slug":"laviter-learning-aligned-visual-and-textual","title":"LAViTeR: Learning Aligned Visual and Textual Representations Assisted by Image and Caption Generation","date":"2021-09-04","arxiv_id":"2109.04993","repositories_listed":1,"syntology":null},{"url":"/paper/table-caption-generation-in-scholarly","slug":"table-caption-generation-in-scholarly","title":"Table Caption Generation in Scholarly Documents Leveraging Pre-trained Language Models","date":"2021-08-18","arxiv_id":"2108.08111","repositories_listed":1,"syntology":null},{"url":"/paper/global-object-proposals-for-improving-multi","slug":"global-object-proposals-for-improving-multi","title":"Global Object Proposals for Improving Multi-Sentence Video Descriptions","date":"2021-07-18","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/team-ruc-aim3-technical-report-at-activitynet-1","slug":"team-ruc-aim3-technical-report-at-activitynet-1","title":"Team RUC_AIM3 Technical Report at ActivityNet 2021: Entities Object Localization","date":"2021-06-11","arxiv_id":"2106.06138","repositories_listed":1,"syntology":null},{"url":"/paper/connecting-what-to-say-with-where-to-look-by","slug":"connecting-what-to-say-with-where-to-look-by","title":"Connecting What to Say With Where to Look by Modeling Human Attention Traces","date":"2021-05-12","arxiv_id":"2105.05964","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/connecting-what-to-say-with-where-to-look-by#ran","syntology_url":"https://syntology.ai/paper/2105.05964","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.05964"}},"official":{"repos":["facebookresearch/connect-caption-and-trace"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/towards-accurate-text-based-image-captioning","slug":"towards-accurate-text-based-image-captioning","title":"Towards Accurate Text-based Image Captioning with Content Diversity Exploration","date":"2021-04-23","arxiv_id":"2105.03236","repositories_listed":1,"syntology":null},{"url":"/paper/human-like-controllable-image-captioning-with","slug":"human-like-controllable-image-captioning-with","title":"Human-like Controllable Image Captioning with Verb-specific Semantic Roles","date":"2021-03-22","arxiv_id":"2103.12204","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/human-like-controllable-image-captioning-with#ran","syntology_url":"https://syntology.ai/paper/2103.12204","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.12204"}},"official":{"repos":["mad-red/VSR-guided-CIC"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/comparative-evaluation-of-cnn-architectures","slug":"comparative-evaluation-of-cnn-architectures","title":"Comparative evaluation of CNN architectures for Image Caption Generation","date":"2021-02-23","arxiv_id":"2102.11506","repositories_listed":1,"syntology":null},{"url":"/paper/improving-image-captioning-by-leveraging-1","slug":"improving-image-captioning-by-leveraging-1","title":"Improving Image Captioning by Leveraging Intra- and Inter-layer Global Representation in Transformer Network","date":"2020-12-13","arxiv_id":"2012.07061","repositories_listed":1,"syntology":null},{"url":"/paper/tap-text-aware-pre-training-for-text-vqa-and","slug":"tap-text-aware-pre-training-for-text-vqa-and","title":"TAP: Text-Aware Pre-training for Text-VQA and Text-Caption","date":"2020-12-08","arxiv_id":"2012.04638","repositories_listed":1,"syntology":null}],"syntology_records":30,"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":33,"papers_where_code_ran_first_page":"/task/caption-generation/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":4,"url":"/task/caption-generation/papers/2","json":"/task/caption-generation/papers/2.json","rows":100},{"order":"archive","page":3,"of":4,"url":"/task/caption-generation/papers/3","json":"/task/caption-generation/papers/3.json","rows":100},{"order":"archive","page":4,"of":4,"url":"/task/caption-generation/papers/4","json":"/task/caption-generation/papers/4.json","rows":10},{"order":"ran","page":1,"of":1,"url":"/task/caption-generation/papers/ran/1","json":"/task/caption-generation/papers/ran/1.json","rows":33}],"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":"75bc0cd69be3dd7ad39695986ae770eaab326061a72b5fc9e64d719c66d3f0b9","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}