{"list":"other","total":249,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"2001.07685","title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","created":"2020-01-21","cited_by_count":2085},{"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":"2103.03230","title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","created":"2021-03-04","cited_by_count":1838},{"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":"1803.07728","title":"Unsupervised Representation Learning by Predicting Image Rotations","created":"2018-03-21","cited_by_count":1591},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"1905.02249","title":"MixMatch: A Holistic Approach to Semi-Supervised Learning","created":"2019-05-06","cited_by_count":1391},{"id":"2006.10029","title":"Big Self-Supervised Models are Strong Semi-Supervised Learners","created":"2020-06-17","cited_by_count":1380},{"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":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"2107.08430","title":"YOLOX: Exceeding YOLO Series in 2021","created":"2021-07-18","cited_by_count":1071},{"id":"1505.05192","title":"Unsupervised Visual Representation Learning by Context Prediction","created":"2015-05-19","cited_by_count":1066},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"id":"2105.04906","title":"VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning","created":"2021-05-11","cited_by_count":1057},{"id":"2111.07832","title":"iBOT: Image BERT Pre-Training with Online Tokenizer","created":"2021-11-15","cited_by_count":903},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"1602.00763","title":"Simple Online and Realtime Tracking","created":"2016-02-02","cited_by_count":868},{"id":"2110.06864","title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","created":"2021-10-13","cited_by_count":823},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"id":"1808.01244","title":"CornerNet: Detecting Objects as Paired Keypoints","created":"2018-08-03","cited_by_count":763},{"id":"1704.08063","title":"SphereFace: Deep Hypersphere Embedding for Face Recognition","created":"2017-04-26","cited_by_count":737},{"id":"2211.07636","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","created":"2022-11-14","cited_by_count":691},{"id":"2309.17421","title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","created":"2023-09-29","cited_by_count":681},{"id":"1904.08189","title":"CenterNet: Keypoint Triplets for Object Detection","created":"2019-04-17","cited_by_count":654},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"1607.08221","title":"MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition","created":"2016-07-27","cited_by_count":624},{"id":"1805.00932","title":"Exploring the Limits of Weakly Supervised Pretraining","created":"2018-05-02","cited_by_count":605},{"id":"1802.00434","title":"DensePose: Dense Human Pose Estimation In The Wild","created":"2018-02-01","cited_by_count":575},{"id":"2201.12329","title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","created":"2022-01-28","cited_by_count":573},{"id":"2110.08263","title":"FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling","created":"2021-10-15","cited_by_count":540},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","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":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522},{"id":"1712.04851","title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","created":"2017-12-13","cited_by_count":521},{"id":"2101.02702","title":"TrackFormer: Multi-Object Tracking with Transformers","created":"2021-01-07","cited_by_count":518},{"id":"2112.10003","title":"Image Segmentation Using Text and Image Prompts","created":"2021-12-18","cited_by_count":512},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497},{"id":"1406.5298","title":"Semi-Supervised Learning with Deep Generative Models","created":"2014-06-20","cited_by_count":496},{"id":"2203.01305","title":"DN-DETR: Accelerate DETR Training by Introducing Query DeNoising","created":"2022-03-02","cited_by_count":488},{"id":"2112.02413","title":"PointCLIP: Point Cloud Understanding by CLIP","created":"2021-12-04","cited_by_count":463},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"2212.03191","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","created":"2022-12-06","cited_by_count":447},{"id":"1605.06409","title":"R-FCN: Object Detection via Region-based Fully Convolutional Networks","created":"2016-05-20","cited_by_count":414},{"id":"1711.10305","title":"Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks","created":"2017-11-28","cited_by_count":387},{"id":"2105.03247","title":"MOTR: End-to-End Multiple-Object Tracking with Transformer","created":"2021-05-07","cited_by_count":381},{"id":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381},{"id":"2012.15460","title":"TransTrack: Multiple Object Tracking with Transformer","created":"2020-12-31","cited_by_count":371},{"id":"2003.09003","title":"MOT20: A benchmark for multi object tracking in crowded scenes","created":"2020-03-19","cited_by_count":357},{"id":"2203.14360","title":"Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking","created":"2022-03-27","cited_by_count":346},{"id":"1905.03677","title":"Learning Loss for Active Learning","created":"2019-05-09","cited_by_count":336},{"id":"1907.09702","title":"BMN: Boundary-Matching Network for Temporal Action Proposal Generation","created":"2019-07-23","cited_by_count":329},{"id":"1711.08496","title":"Temporal Relational Reasoning in Videos","created":"2017-11-22","cited_by_count":324},{"id":"2206.14651","title":"BoT-SORT: Robust Associations Multi-Pedestrian Tracking","created":"2022-06-29","cited_by_count":320},{"id":"1403.6382","title":"CNN Features off-the-shelf: an Astounding Baseline for Recognition","created":"2014-03-23","cited_by_count":316},{"id":"1812.02707","title":"Video Action Transformer Network","created":"2018-12-06","cited_by_count":316},{"id":"2007.08489","title":"Do Adversarially Robust ImageNet Models Transfer Better?","created":"2020-07-16","cited_by_count":316},{"id":"2202.07925","title":"ActionFormer: Localizing Moments of Actions with Transformers","created":"2022-02-16","cited_by_count":311},{"id":"2112.04478","title":"Prompting Visual-Language Models for Efficient Video Understanding","created":"2021-12-08","cited_by_count":310},{"id":"2306.00989","title":"Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles","created":"2023-06-01","cited_by_count":290},{"id":"2306.08637","title":"TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement","created":"2023-06-14","cited_by_count":287},{"id":"1806.02964","title":"BSN: Boundary Sensitive Network for Temporal Action Proposal Generation","created":"2018-06-08","cited_by_count":271},{"id":"2309.16671","title":"Demystifying CLIP Data","created":"2023-09-28","cited_by_count":270}],"next_cursor":"100"}