{"list":"other","total":57,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"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":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"1709.04875","title":"Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting","created":"2017-09-14","cited_by_count":1136},{"id":"1901.07291","title":"Cross-lingual Language Model Pretraining","created":"2019-01-22","cited_by_count":1090},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"2207.02696","title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","created":"2022-07-06","cited_by_count":982},{"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":"2104.08860","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","created":"2021-04-18","cited_by_count":651},{"id":"1810.02508","title":"MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations","created":"2018-10-05","cited_by_count":643},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"2112.01518","title":"DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting","created":"2021-12-02","cited_by_count":532},{"id":"2005.00547","title":"GoEmotions: A Dataset of Fine-Grained Emotions","created":"2020-05-01","cited_by_count":486},{"id":"2102.06183","title":"Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling","created":"2021-02-11","cited_by_count":484},{"id":"2112.02413","title":"PointCLIP: Point Cloud Understanding by CLIP","created":"2021-12-04","cited_by_count":463},{"id":"2111.03930","title":"Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling","created":"2021-11-06","cited_by_count":431},{"id":"2005.00200","title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","created":"2020-05-01","cited_by_count":362},{"id":"2208.02816","title":"Expanding Language-Image Pretrained Models for General Video Recognition","created":"2022-08-04","cited_by_count":321},{"id":"2112.04478","title":"Prompting Visual-Language Models for Efficient Video Understanding","created":"2021-12-08","cited_by_count":310},{"id":"1705.02953","title":"Temporal Segment Networks for Action Recognition in Videos","created":"2017-05-08","cited_by_count":279},{"id":"1804.08348","title":"Deep Facial Expression Recognition: A Survey","created":"2018-04-23","cited_by_count":270},{"id":"2109.11797","title":"CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models","created":"2021-09-24","cited_by_count":183},{"id":"2208.03550","title":"Frozen CLIP Models are Efficient Video Learners","created":"2022-08-06","cited_by_count":182},{"id":"2002.10392","title":"Suppressing Uncertainties for Large-Scale Facial Expression Recognition","created":"2020-02-24","cited_by_count":157},{"id":"1908.05913","title":"Context-Aware Emotion Recognition Networks","created":"2019-08-16","cited_by_count":99},{"id":"2108.11116","title":"TransFER: Learning Relation-aware Facial Expression Representations with Transformers","created":"2021-08-25","cited_by_count":85},{"id":"1802.08379","title":"EmotionLines: An Emotion Corpus of Multi-Party Conversations","created":"2018-02-23","cited_by_count":80},{"id":"2112.05142","title":"HairCLIP: Design Your Hair by Text and Reference Image","created":"2021-12-09","cited_by_count":80},{"id":"1712.06761","title":"MovieGraphs: Towards Understanding Human-Centric Situations from Videos","created":"2017-12-19","cited_by_count":67},{"id":"1810.04635","title":"Multimodal Speech Emotion Recognition Using Audio and Text","created":"2018-10-10","cited_by_count":55},{"id":"2003.06692","title":"EmotiCon: Context-Aware Multimodal Emotion Recognition using Frege's Principle","created":"2020-03-14","cited_by_count":50},{"id":"2206.02187","title":"M2FNet: Multi-modal Fusion Network for Emotion Recognition in Conversation","created":"2022-06-05","cited_by_count":47},{"id":"1808.09568","title":"ARBEE: Towards Automated Recognition of Bodily Expression of Emotion In the Wild","created":"2018-08-28","cited_by_count":34},{"id":"2103.06541","title":"Affect2MM: Affective Analysis of Multimedia Content Using Emotion Causality","created":"2021-03-11","cited_by_count":17},{"id":"2010.16396","title":"Emotion Understanding in Videos Through Body, Context, and Visual-Semantic Embedding Loss","created":"2020-10-30","cited_by_count":14},{"id":"2105.07484","title":"Leveraging Semantic Scene Characteristics and Multi-Stream Convolutional Architectures in a Contextual Approach for Video-Based Visual Emotion Recognition in the Wild","created":"2021-05-16","cited_by_count":12},{"id":"1911.12361","title":"GLA in MediaEval 2018 Emotional Impact of Movies Task","created":"2019-11-27","cited_by_count":6},{"id":"2206.07593","title":"HICEM: A High-Coverage Emotion Model for Artificial Emotional Intelligence","created":"2022-06-15","cited_by_count":5},{"id":"1701.01096","title":"Probabilistic Multigraph Modeling for Improving the Quality of Crowdsourced Affective Data","created":"2017-01-04","cited_by_count":4},{"id":"1909.01763","title":"Video Affective Effects Prediction with Multi-modal Fusion and Shot-Long Temporal Context","created":"2019-09-01","cited_by_count":1}],"next_cursor":null}