{"list":"other","total":69,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"1707.07998","title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","created":"2017-07-25","cited_by_count":1312},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"1506.06724","title":"Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books","created":"2015-06-22","cited_by_count":1043},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"id":"1706.08612","title":"VoxCeleb: a large-scale speaker identification dataset","created":"2017-06-26","cited_by_count":732},{"id":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661},{"id":"2005.07143","title":"ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification","created":"2020-05-14","cited_by_count":628},{"id":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"1411.4389","title":"Long-term Recurrent Convolutional Networks for Visual Recognition and Description","created":"2014-11-17","cited_by_count":484},{"id":"2111.03930","title":"Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling","created":"2021-11-06","cited_by_count":431},{"id":"1604.01696","title":"A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories","created":"2016-04-06","cited_by_count":417},{"id":"2303.00747","title":"WhisperX: Time-Accurate Speech Transcription of Long-Form Audio","created":"2023-03-01","cited_by_count":326},{"id":"2112.04478","title":"Prompting Visual-Language Models for Efficient Video Understanding","created":"2021-12-08","cited_by_count":310},{"id":"2203.17274","title":"Exploring Visual Prompts for Adapting Large-Scale Models","created":"2022-03-31","cited_by_count":274},{"id":"2206.08155","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","created":"2022-06-16","cited_by_count":229},{"id":"1804.00819","title":"End-to-End Dense Video Captioning with Masked Transformer","created":"2018-04-03","cited_by_count":214},{"id":"1411.2539","title":"Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models","created":"2014-11-10","cited_by_count":198},{"id":"1501.02530","title":"A Dataset for Movie Description","created":"2015-01-12","cited_by_count":195},{"id":"1605.03705","title":"Movie Description","created":"2016-05-12","cited_by_count":181},{"id":"1911.01255","title":"pyannote.audio: neural building blocks for speaker diarization","created":"2019-11-04","cited_by_count":181},{"id":"1604.03968","title":"Visual Storytelling","created":"2016-04-13","cited_by_count":176},{"id":"1505.00487","title":"Sequence to Sequence -- Video to Text","created":"2015-05-03","cited_by_count":158},{"id":"2108.07781","title":"End-to-End Dense Video Captioning with Parallel Decoding","created":"2021-08-17","cited_by_count":133},{"id":"2201.08264","title":"End-to-end Generative Pretraining for Multimodal Video Captioning","created":"2022-01-20","cited_by_count":116},{"id":"2112.00431","title":"MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions","created":"2021-12-01","cited_by_count":108},{"id":"1803.09845","title":"Neural Baby Talk","created":"2018-03-27","cited_by_count":107},{"id":"2005.04208","title":"Condensed Movies: Story Based Retrieval with Contextual Embeddings","created":"2020-05-08","cited_by_count":95},{"id":"2211.00575","title":"Text-Only Training for Image Captioning using Noise-Injected CLIP","created":"2022-11-01","cited_by_count":91},{"id":"2110.06615","title":"CLIP4Caption: CLIP for Video Caption","created":"2021-10-13","cited_by_count":88},{"id":"2104.04045","title":"End-to-end speaker segmentation for overlap-aware resegmentation","created":"2021-04-08","cited_by_count":80},{"id":"2204.00679","title":"Learning Audio-Video Modalities from Image Captions","created":"2022-04-01","cited_by_count":80},{"id":"2011.11760","title":"Multimodal Pretraining for Dense Video Captioning","created":"2020-11-10","cited_by_count":79},{"id":"1804.00100","title":"Bidirectional Attentive Fusion with Context Gating for Dense Video Captioning","created":"2018-03-31","cited_by_count":68},{"id":"1804.08274","title":"Jointly Localizing and Describing Events for Dense Video Captioning","created":"2018-04-23","cited_by_count":60},{"id":"1904.03870","title":"Streamlined Dense Video Captioning","created":"2019-04-08","cited_by_count":57},{"id":"2205.08508","title":"A CLIP-Hitchhiker's Guide to Long Video Retrieval","created":"2022-05-17","cited_by_count":57},{"id":"1909.09944","title":"Watch, Listen and Tell: Multi-modal Weakly Supervised Dense Event Captioning","created":"2019-09-22","cited_by_count":38},{"id":"1908.10328","title":"Movie Plot Analysis via Turning Point Identification","created":"2019-08-27","cited_by_count":34},{"id":"1503.01070","title":"Using Descriptive Video Services to Create a Large Data Source for Video Annotation Research","created":"2015-03-03","cited_by_count":33},{"id":"1812.05634","title":"Adversarial Inference for Multi-Sentence Video Description","created":"2018-12-13","cited_by_count":31},{"id":"1910.11009","title":"A Graph-Based Framework to Bridge Movies and Synopses","created":"2019-10-24","cited_by_count":31},{"id":"2207.14279","title":"The One Where They Reconstructed 3D Humans and Environments in TV Shows","created":"2022-07-28","cited_by_count":30},{"id":"1807.09418","title":"Video Storytelling: Textual Summaries for Events","created":"2018-07-25","cited_by_count":22},{"id":"2003.13158","title":"Learning Interactions and Relationships between Movie Characters","created":"2020-03-29","cited_by_count":22},{"id":"2011.07735","title":"iPerceive: Applying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering","created":"2020-11-16","cited_by_count":20},{"id":"1704.01502","title":"Weakly Supervised Dense Video Captioning","created":"2017-04-05","cited_by_count":18},{"id":"1807.10510","title":"Person Search in Videos with One Portrait Through Visual and Temporal Links","created":"2018-07-27","cited_by_count":14},{"id":"1806.00186","title":"Video Description: A Survey of Methods, Datasets and Evaluation Metrics","created":"2018-06-01","cited_by_count":13},{"id":"1411.5654","title":"Learning a Recurrent Visual Representation for Image Caption Generation","created":"2014-11-20","cited_by_count":12},{"id":"2102.05645","title":"Automated Video Labelling: Identifying Faces by Corroborative Evidence","created":"2021-02-10","cited_by_count":9},{"id":"2203.05711","title":"Synopses of Movie Narratives: a Video-Language Dataset for Story Understanding","created":"2022-03-11","cited_by_count":8}],"next_cursor":null}