{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"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":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"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":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2210.09461","title":"Token Merging: Your ViT But Faster","created":"2022-10-17","cited_by_count":1021},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766},{"id":"1703.09788","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","created":"2017-03-28","cited_by_count":619},{"id":"1308.0850","title":"Generating Sequences With Recurrent Neural Networks","created":"2013-08-04","cited_by_count":554},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537},{"id":"1603.00831","title":"MOT16: A Benchmark for Multi-Object Tracking","created":"2016-03-02","cited_by_count":532},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"1903.05625","title":"Tracking without bells and whistles","created":"2019-03-13","cited_by_count":382},{"id":"1909.12605","title":"Towards Real-Time Multi-Object Tracking","created":"2019-09-27","cited_by_count":311},{"id":"2306.00989","title":"Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles","created":"2023-06-01","cited_by_count":290},{"id":"2302.14115","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","created":"2023-02-27","cited_by_count":263},{"id":"2305.18565","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","created":"2023-05-29","cited_by_count":255},{"id":"1812.05038","title":"Long-Term Feature Banks for Detailed Video Understanding","created":"2018-12-12","cited_by_count":239},{"id":"2203.08913","title":"Memorizing Transformers","created":"2022-03-16","cited_by_count":226},{"id":"1804.00819","title":"End-to-End Dense Video Captioning with Masked Transformer","created":"2018-04-03","cited_by_count":214},{"id":"2201.08383","title":"MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition","created":"2022-01-20","cited_by_count":189},{"id":"2201.02639","title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","created":"2022-01-07","cited_by_count":184},{"id":"2208.03550","title":"Frozen CLIP Models are Efficient Video Learners","created":"2022-08-06","cited_by_count":182},{"id":"2106.11310","title":"Towards Long-Form Video Understanding","created":"2021-06-21","cited_by_count":146},{"id":"2103.11511","title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","created":"2021-03-21","cited_by_count":135},{"id":"2108.07781","title":"End-to-End Dense Video Captioning with Parallel Decoding","created":"2021-08-17","cited_by_count":133},{"id":"2106.11297","title":"TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?","created":"2021-06-21","cited_by_count":127},{"id":"2211.09552","title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","created":"2022-11-17","cited_by_count":116},{"id":"2003.07758","title":"Multi-modal Dense Video Captioning","created":"2020-03-17","cited_by_count":113},{"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":"1905.00737","title":"The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentation","created":"2019-05-02","cited_by_count":97},{"id":"2006.07976","title":"Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization","created":"2020-06-14","cited_by_count":91},{"id":"2011.11760","title":"Multimodal Pretraining for Dense Video Captioning","created":"2020-11-10","cited_by_count":79},{"id":"2005.08271","title":"A Better Use of Audio-Visual Cues: Dense Video Captioning with Bi-modal Transformer","created":"2020-05-17","cited_by_count":76},{"id":"2110.06915","title":"Object-Region Video Transformers","created":"2021-10-13","cited_by_count":73},{"id":"1604.06506","title":"Online Action Detection","created":"2016-04-21","cited_by_count":69},{"id":"1804.00100","title":"Bidirectional Attentive Fusion with Context Gating for Dense Video Captioning","created":"2018-03-31","cited_by_count":68},{"id":"2209.09236","title":"Real-time Online Video Detection with Temporal Smoothing Transformers","created":"2022-09-19","cited_by_count":58},{"id":"1611.08563","title":"Online Real-time Multiple Spatiotemporal Action Localisation and Prediction","created":"2016-11-25","cited_by_count":57},{"id":"2110.11403","title":"SCENIC: A JAX Library for Computer Vision Research and Beyond","created":"2021-10-18","cited_by_count":57},{"id":"2303.16899","title":"AutoAD: Movie Description in Context","created":"2023-03-29","cited_by_count":50},{"id":"2310.06838","title":"AutoAD II: The Sequel -- Who, When, and What in Movie Audio Description","created":"2023-10-10","cited_by_count":49},{"id":"1807.10018","title":"Move Forward and Tell: A Progressive Generator of Video Descriptions","created":"2018-07-26","cited_by_count":35},{"id":"2204.08121","title":"End-to-end Dense Video Captioning as Sequence Generation","created":"2022-04-18","cited_by_count":27},{"id":"2211.09119","title":"Token Turing Machines","created":"2022-11-16","cited_by_count":25},{"id":"2303.17228","title":"Streaming Video Model","created":"2023-03-30","cited_by_count":10}],"next_cursor":null}