{"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 (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":119,"tagged_in_all":310,"items":[{"url":"/paper/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":15,"n_unverified":69,"n_pointer_only":7}},{"url":"/paper/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":4,"n_unverified":3,"n_pointer_only":3}},{"url":"/paper/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_unverified":4,"n_pointer_only":6}},{"url":"/paper/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","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","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","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_unverified":0,"n_pointer_only":0}},{"url":"/paper/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_unverified":1,"n_pointer_only":4}},{"url":"/paper/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","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":3,"n_unverified":14,"n_pointer_only":0}},{"url":"/paper/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_unverified":1,"n_pointer_only":0}},{"url":"/paper/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_unverified":0,"n_pointer_only":0}},{"url":"/paper/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","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","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":3,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/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_unverified":1,"n_pointer_only":1}},{"url":"/paper/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","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","title":"Tensor Product Generation Networks for Deep NLP Modeling","date":"2017-09-26","arxiv_id":"1709.09118","repositories_listed":2,"syntology":null},{"url":"/paper/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/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/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","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","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","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","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","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","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","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","title":"VideoMultiAgents: A Multi-Agent Framework for Video Question Answering","date":"2025-04-25","arxiv_id":"2504.20091","repositories_listed":1,"syntology":null}],"syntology_records":10,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}