{"list":"other","total":70,"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"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":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"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":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"2111.07783","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training","created":"2021-11-09","cited_by_count":627},{"id":"1811.10830","title":"From Recognition to Cognition: Visual Commonsense Reasoning","created":"2018-11-27","cited_by_count":556},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"2005.00200","title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","created":"2020-05-01","cited_by_count":362},{"id":"2006.06195","title":"Large-Scale Adversarial Training for Vision-and-Language Representation Learning","created":"2020-06-11","cited_by_count":327},{"id":"2106.02636","title":"MERLOT: Multimodal Neural Script Knowledge Models","created":"2021-06-04","cited_by_count":311},{"id":"1512.02902","title":"MovieQA: Understanding Stories in Movies through Question-Answering","created":"2015-12-09","cited_by_count":304},{"id":"2006.16228","title":"Self-Supervised MultiModal Versatile Networks","created":"2020-06-29","cited_by_count":276},{"id":"1703.01541","title":"Soft-DTW: a Differentiable Loss Function for Time-Series","created":"2017-03-05","cited_by_count":271},{"id":"2011.07231","title":"ActBERT: Learning Global-Local Video-Text Representations","created":"2020-11-14","cited_by_count":267},{"id":"1812.02378","title":"Auto-Encoding Scene Graphs for Image Captioning","created":"2018-12-06","cited_by_count":255},{"id":"1909.11740","title":"UNITER: UNiversal Image-TExt Representation Learning","created":"2019-09-25","cited_by_count":228},{"id":"2006.16934","title":"ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph","created":"2020-06-30","cited_by_count":211},{"id":"2007.10937","title":"MovieNet: A Holistic Dataset for Movie Understanding","created":"2020-07-21","cited_by_count":206},{"id":"1501.02530","title":"A Dataset for Movie Description","created":"2015-01-12","cited_by_count":195},{"id":"2111.12681","title":"VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling","created":"2021-11-24","cited_by_count":188},{"id":"2003.00392","title":"Fine-grained Video-Text Retrieval with Hierarchical Graph Reasoning","created":"2020-03-01","cited_by_count":180},{"id":"1604.03968","title":"Visual Storytelling","created":"2016-04-13","cited_by_count":176},{"id":"2002.10698","title":"Hierarchical Conditional Relation Networks for Video Question Answering","created":"2020-02-25","cited_by_count":163},{"id":"1904.11574","title":"TVQA+: Spatio-Temporal Grounding for Video Question Answering","created":"2019-04-25","cited_by_count":154},{"id":"2206.03428","title":"Revealing Single Frame Bias for Video-and-Language Learning","created":"2022-06-07","cited_by_count":133},{"id":"1903.12314","title":"Relation-Aware Graph Attention Network for Visual Question Answering","created":"2019-03-29","cited_by_count":119},{"id":"1511.06984","title":"End-to-end Learning of Action Detection from Frame Glimpses in Videos","created":"2015-11-22","cited_by_count":101},{"id":"1908.05054","title":"Fusion of Detected Objects in Text for Visual Question Answering","created":"2019-08-14","cited_by_count":74},{"id":"2209.01540","title":"An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling","created":"2022-09-04","cited_by_count":74},{"id":"1712.06761","title":"MovieGraphs: Towards Understanding Human-Centric Situations from Videos","created":"2017-12-19","cited_by_count":67},{"id":"2004.02678","title":"A Local-to-Global Approach to Multi-modal Movie Scene Segmentation","created":"2020-04-06","cited_by_count":60},{"id":"2009.12539","title":"Topic-Aware Multi-turn Dialogue Modeling","created":"2020-09-26","cited_by_count":46},{"id":"2104.13537","title":"Shot Contrastive Self-Supervised Learning for Scene Boundary Detection","created":"2021-04-28","cited_by_count":35},{"id":"1910.11009","title":"A Graph-Based Framework to Bridge Movies and Synopses","created":"2019-10-24","cited_by_count":31},{"id":"2012.15688","title":"ERNIE-Doc: A Retrospective Long-Document Modeling Transformer","created":"2020-12-31","cited_by_count":31},{"id":"2106.06719","title":"Improving Unsupervised Dialogue Topic Segmentation with Utterance-Pair Coherence Scoring","created":"2021-06-12","cited_by_count":29},{"id":"2009.08043","title":"Self-supervised pre-training and contrastive representation learning for multiple-choice video QA","created":"2020-09-17","cited_by_count":28},{"id":"2006.15319","title":"Video-Grounded Dialogues with Pretrained Generation Language Models","created":"2020-06-27","cited_by_count":16},{"id":"1603.08561","title":"Shuffle and Learn: Unsupervised Learning using Temporal Order Verification","created":"2016-03-28","cited_by_count":13},{"id":"2101.02337","title":"Learning Temporal Dynamics from Cycles in Narrated Video","created":"2021-01-07","cited_by_count":13},{"id":"1610.03955","title":"Dialogue Session Segmentation by Embedding-Enhanced TextTiling","created":"2016-10-13","cited_by_count":12},{"id":"2104.07921","title":"VGNMN: Video-grounded Neural Module Network to Video-Grounded Language Tasks","created":"2021-04-16","cited_by_count":11},{"id":"2305.18756","title":"VSTAR: A Video-grounded Dialogue Dataset for Situated Semantic Understanding with Scene and Topic Transitions","created":"2023-05-30","cited_by_count":11},{"id":"2108.02174","title":"Knowledge-Grounded Dialogue Flow Management for Social Robots and Conversational Agents","created":"2021-08-04","cited_by_count":7},{"id":"2004.02205","title":"Deep Multimodal Feature Encoding for Video Ordering","created":"2020-04-05","cited_by_count":3},{"id":"2102.08553","title":"Integrating Pre-trained Model into Rule-based Dialogue Management","created":"2021-02-17","cited_by_count":1}],"next_cursor":null}