{"task":"Audio captioning","dataset":"AudioCaps","metric_names":["SPIDEr","CIDEr","SPICE","BLEU-4","METEOR","ROUGE-L","FENSE","SPIDEr-FL"],"rows":[{"id":113359,"task":"Audio captioning","parent_task":null,"dataset":"AudioCaps","model_name":"MQ-Cap","metrics":{"BLEU-4":"0.301","CIDEr":"0.845","METEOR":"0.266","SPICE":"0.194","SPIDEr":"0.519"},"paper_url":"https://arxiv.org/abs/2410.10913v3","paper_title":"Enhancing Retrieval-Augmented Audio Captioning with Generation-Assisted Multimodal Querying and Progressive Learning","paper_date":"2024-10-14","code_links":[],"metrics_order":"[\"SPIDEr\", \"CIDEr\", \"SPICE\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"FENSE\", \"SPIDEr-FL\", \"#params (M)\", \"ROUGE\", \"Sentence-BERT\"]","area":"Audio","uses_additional_data":1,"source":"archive","tags":[]},{"id":113360,"task":"Audio captioning","parent_task":null,"dataset":"AudioCaps","model_name":"SLAM-AAC","metrics":{"CIDEr":"0.841","FENSE":"0.668","METEOR":"0.268","SPICE":"0.194","SPIDEr":"0.518","SPIDEr-FL":"0.515"},"paper_url":"https://arxiv.org/abs/2410.09503v1","paper_title":"SLAM-AAC: Enhancing Audio Captioning with Paraphrasing Augmentation and CLAP-Refine through LLMs","paper_date":"2024-10-12","code_links":[{"title":"X-LANCE/SLAM-LLM","url":"https://github.com/X-LANCE/SLAM-LLM"}],"metrics_order":"[\"SPIDEr\", \"CIDEr\", \"SPICE\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"FENSE\", \"SPIDEr-FL\", \"#params (M)\", \"ROUGE\", \"Sentence-BERT\"]","area":"Audio","uses_additional_data":1,"source":"archive","tags":[]},{"id":113361,"task":"Audio captioning","parent_task":null,"dataset":"AudioCaps","model_name":"LAVCap","metrics":{"BLEU-4":"0.297","CIDEr":"0.849","METEOR":"0.262","ROUGE-L":"0.510","SPICE":"0.185","SPIDEr":"0.517"},"paper_url":"https://arxiv.org/abs/2501.09291v2","paper_title":"LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport","paper_date":"2025-01-16","code_links":[{"title":"naver-intel-co-lab/gaudi-lavcap","url":"https://github.com/naver-intel-co-lab/gaudi-lavcap"},{"title":"Hyeongkeun/LAVCap","url":"https://github.com/Hyeongkeun/LAVCap"}],"metrics_order":"[\"SPIDEr\", \"CIDEr\", \"SPICE\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"FENSE\", \"SPIDEr-FL\", \"#params (M)\", \"ROUGE\", \"Sentence-BERT\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":113362,"task":"Audio captioning","parent_task":null,"dataset":"AudioCaps","model_name":"EnCLAP++-large","metrics":{"CIDEr":"0.823","FENSE":"0.665","METEOR":"0.269","SPICE":"0.197","SPIDEr":"0.510"},"paper_url":"https://arxiv.org/abs/2409.01201v1","paper_title":"EnCLAP++: Analyzing the EnCLAP Framework for Optimizing Automated Audio Captioning Performance","paper_date":"2024-09-02","code_links":[{"title":"jaeyeonkim99/enclap","url":"https://github.com/jaeyeonkim99/enclap"}],"metrics_order":"[\"SPIDEr\", \"CIDEr\", \"SPICE\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"FENSE\", \"SPIDEr-FL\", \"#params (M)\", \"ROUGE\", \"Sentence-BERT\"]","area":"Audio","uses_additional_data":1,"source":"archive","tags":[]},{"id":113363,"task":"Audio captioning","parent_task":null,"dataset":"AudioCaps","model_name":"AutoCap","metrics":{"CIDEr":"0.832","METEOR":"0.253","ROUGE":"0.518","ROUGE-L":"0.518","SPICE":"0.182","SPIDEr":"0.507"},"paper_url":"https://arxiv.org/abs/2406.19388v4","paper_title":"Taming Data and Transformers for Audio Generation","paper_date":"2024-06-27","code_links":[{"title":"snap-research/GenAU","url":"https://github.com/snap-research/GenAU"}],"metrics_order":"[\"SPIDEr\", \"CIDEr\", \"SPICE\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"FENSE\", \"SPIDEr-FL\", \"#params (M)\", \"ROUGE\", \"Sentence-BERT\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":113364,"task":"Audio captioning","parent_task":null,"dataset":"AudioCaps","model_name":"LOAE","metrics":{"CIDEr":"0.816","FENSE":"0.664","METEOR":"0.267","SPICE":"0.193","SPIDEr":"0.505","Sentence-BERT":"0.664"},"paper_url":"https://arxiv.org/abs/2406.13275v2","paper_title":"Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding","paper_date":"2024-06-19","code_links":[{"title":"frankenliu/LOAE","url":"https://github.com/frankenliu/LOAE"}],"metrics_order":"[\"SPIDEr\", \"CIDEr\", \"SPICE\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"FENSE\", \"SPIDEr-FL\", \"#params (M)\", \"ROUGE\", \"Sentence-BERT\"]","area":"Audio","uses_additional_data":1,"source":"archive","tags":[]},{"id":113365,"task":"Audio captioning","parent_task":null,"dataset":"AudioCaps","model_name":"EnCLAP++-base","metrics":{"CIDEr":"0.815","FENSE":"0.661","METEOR":"0.257","SPICE":"0.188","SPIDEr":"0.501"},"paper_url":"https://arxiv.org/abs/2409.01201v1","paper_title":"EnCLAP++: Analyzing the EnCLAP Framework for Optimizing Automated Audio Captioning Performance","paper_date":"2024-09-02","code_links":[{"title":"jaeyeonkim99/enclap","url":"https://github.com/jaeyeonkim99/enclap"}],"metrics_order":"[\"SPIDEr\", \"CIDEr\", \"SPICE\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"FENSE\", \"SPIDEr-FL\", \"#params (M)\", \"ROUGE\", \"Sentence-BERT\"]","area":"Audio","uses_additional_data":1,"source":"archive","tags":[]},{"id":113366,"task":"Audio captioning","parent_task":null,"dataset":"AudioCaps","model_name":"EnCLAP-large","metrics":{"CIDEr":"0.8029","METEOR":"0.2554","SPICE":"0.1879","SPIDEr":"0.4954"},"paper_url":"https://arxiv.org/abs/2401.17690v1","paper_title":"EnCLAP: Combining Neural Audio Codec and Audio-Text Joint Embedding for Automated Audio Captioning","paper_date":"2024-01-31","code_links":[{"title":"jaeyeonkim99/enclap","url":"https://github.com/jaeyeonkim99/enclap"}],"metrics_order":"[\"SPIDEr\", \"CIDEr\", \"SPICE\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"FENSE\", \"SPIDEr-FL\", \"#params (M)\", \"ROUGE\", \"Sentence-BERT\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":113367,"task":"Audio captioning","parent_task":null,"dataset":"AudioCaps","model_name":"CNext-trans","metrics":{"#params (M)":"40","CIDEr":"0.8061","FENSE":"0.6431","METEOR":"0.2527","SPICE":"0.1841","SPIDEr":"0.4951","SPIDEr-FL":"0.4945"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"SPIDEr\", \"CIDEr\", \"SPICE\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"FENSE\", \"SPIDEr-FL\", \"#params (M)\", \"ROUGE\", \"Sentence-BERT\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":113368,"task":"Audio captioning","parent_task":null,"dataset":"AudioCaps","model_name":"EnCLAP-base","metrics":{"CIDEr":"0.7795","METEOR":"0.2473","SPICE":"0.1863","SPIDEr":"0.4829"},"paper_url":"https://arxiv.org/abs/2401.17690v1","paper_title":"EnCLAP: Combining Neural Audio Codec and Audio-Text Joint Embedding for Automated Audio Captioning","paper_date":"2024-01-31","code_links":[{"title":"jaeyeonkim99/enclap","url":"https://github.com/jaeyeonkim99/enclap"}],"metrics_order":"[\"SPIDEr\", \"CIDEr\", \"SPICE\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"FENSE\", \"SPIDEr-FL\", \"#params (M)\", \"ROUGE\", \"Sentence-BERT\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":113369,"task":"Audio captioning","parent_task":null,"dataset":"AudioCaps","model_name":"AL-MixGen + Multi-TTA","metrics":{"CIDEr":"0.769","SPICE":"0.181","SPIDEr":"0.475"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"SPIDEr\", \"CIDEr\", \"SPICE\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"FENSE\", \"SPIDEr-FL\", \"#params (M)\", \"ROUGE\", \"Sentence-BERT\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":113370,"task":"Audio captioning","parent_task":null,"dataset":"AudioCaps","model_name":"Rethink-ACT (AST + TF + MIL)","metrics":{"BLEU-4":"0.285","CIDEr":"0.764","METEOR":"0.242","ROUGE-L":"0.504","SPICE":"0.180","SPIDEr":"0.472"},"paper_url":"https://www.isca-speech.org/archive/interspeech_2023/shin23_interspeech.html","paper_title":"Rethinking Transfer and Auxiliary Learning for Improving Audio Captioning Transformer","paper_date":"2023-08-20","code_links":[],"metrics_order":"[\"SPIDEr\", \"CIDEr\", \"SPICE\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"FENSE\", \"SPIDEr-FL\", \"#params (M)\", \"ROUGE\", \"Sentence-BERT\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":113371,"task":"Audio captioning","parent_task":null,"dataset":"AudioCaps","model_name":"AL-MixGen","metrics":{"CIDEr":"0.755","SPICE":"0.177","SPIDEr":"0.466"},"paper_url":"https://arxiv.org/abs/2210.17143v2","paper_title":"Exploring Train and Test-Time Augmentations for Audio-Language Learning","paper_date":"2022-10-31","code_links":[],"metrics_order":"[\"SPIDEr\", \"CIDEr\", \"SPICE\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"FENSE\", \"SPIDEr-FL\", \"#params (M)\", \"ROUGE\", \"Sentence-BERT\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":113372,"task":"Audio captioning","parent_task":null,"dataset":"AudioCaps","model_name":"BART + YAMNet + PANNs","metrics":{"CIDEr":"0.753","SPICE":"0.176","SPIDEr":"0.465"},"paper_url":"https://dcase.community/documents/workshop2021/proceedings/DCASE2021Workshop_Gontier_57.pdf","paper_title":"AUTOMATED AUDIO CAPTIONING BY FINE-TUNING BART WITH AUDIOSET TAGS","paper_date":"2021-11-15","code_links":[{"title":"felixgontier/dcase2021aac","url":"https://github.com/felixgontier/dcase2021aac"}],"metrics_order":"[\"SPIDEr\", \"CIDEr\", \"SPICE\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"FENSE\", \"SPIDEr-FL\", \"#params (M)\", \"ROUGE\", \"Sentence-BERT\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":113373,"task":"Audio captioning","parent_task":null,"dataset":"AudioCaps","model_name":"CNN+Transformer","metrics":{"CIDEr":"0.693","SPICE":"0.159","SPIDEr":"0.426"},"paper_url":"https://arxiv.org/abs/2107.09817v1","paper_title":"Audio Captioning Transformer","paper_date":"2021-07-21","code_links":[{"title":"XinhaoMei/ACT","url":"https://github.com/XinhaoMei/ACT"}],"metrics_order":"[\"SPIDEr\", \"CIDEr\", \"SPICE\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"FENSE\", \"SPIDEr-FL\", \"#params (M)\", \"ROUGE\", \"Sentence-BERT\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":113374,"task":"Audio captioning","parent_task":null,"dataset":"AudioCaps","model_name":"TopDown-AlignedAtt (1NN)","metrics":{"CIDEr":"0.593","SPICE":"0.144","SPIDEr":"0.369"},"paper_url":"https://aclanthology.org/N19-1011","paper_title":"AudioCaps: Generating Captions for Audios in The Wild","paper_date":"2019-06-01","code_links":[],"metrics_order":"[\"SPIDEr\", \"CIDEr\", \"SPICE\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"FENSE\", \"SPIDEr-FL\", \"#params (M)\", \"ROUGE\", \"Sentence-BERT\"]","area":"Audio","uses_additional_data":0,"source":"archive","tags":[]},{"id":113375,"task":"Audio captioning","parent_task":null,"dataset":"AudioCaps","model_name":"VAST","metrics":{"BLEU-4":"0.295","CIDEr":"0.781","METEOR":"0.247","ROUGE-L":"0.509"},"paper_url":"https://arxiv.org/abs/2305.18500v2","paper_title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","paper_date":"2023-05-29","code_links":[{"title":"TXH-mercury/VALOR","url":"https://github.com/TXH-mercury/VALOR"},{"title":"txh-mercury/vast","url":"https://github.com/txh-mercury/vast"}],"metrics_order":"[\"SPIDEr\", \"CIDEr\", \"SPICE\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"FENSE\", \"SPIDEr-FL\", \"#params (M)\", \"ROUGE\", \"Sentence-BERT\"]","area":"Audio","uses_additional_data":1,"source":"archive","tags":[]},{"id":113376,"task":"Audio captioning","parent_task":null,"dataset":"AudioCaps","model_name":"VALOR","metrics":{"BLEU-4":"0.270","CIDEr":"0.741","METEOR":"0.231","ROUGE-L":"0.494"},"paper_url":"https://arxiv.org/abs/2304.08345v2","paper_title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","paper_date":"2023-04-17","code_links":[{"title":"TXH-mercury/VALOR","url":"https://github.com/TXH-mercury/VALOR"}],"metrics_order":"[\"SPIDEr\", \"CIDEr\", \"SPICE\", \"BLEU-4\", \"METEOR\", \"ROUGE-L\", \"FENSE\", \"SPIDEr-FL\", \"#params (M)\", \"ROUGE\", \"Sentence-BERT\"]","area":"Audio","uses_additional_data":1,"source":"archive","tags":[]}]}